diff --git a/src/docs.json b/src/docs.json index c28f9452db..563da7f272 100644 --- a/src/docs.json +++ b/src/docs.json @@ -1280,8 +1280,8 @@ "group": "OpenAI", "pages": [ "oss/javascript/integrations/providers/openai", - "/oss/javascript/integrations/chat/openai", - "/oss/javascript/integrations/text_embedding/openai" + "/oss/integrations/chat/openai", + "/oss/integrations/text_embedding/openai" ] }, { diff --git a/src/langsmith/managing-model-configurations.mdx b/src/langsmith/managing-model-configurations.mdx index e05b2c17d1..763d9fd40c 100644 --- a/src/langsmith/managing-model-configurations.mdx +++ b/src/langsmith/managing-model-configurations.mdx @@ -68,7 +68,7 @@ The **Extra Parameters** field allows you to pass additional model parameters th TypeError: AsyncCompletions.create() got an unexpected keyword argument 'max_concurrency' ``` - If you receive an error about unnecessary parameters (which is more common when using [LangChain JS](/oss/javascript/langchain/overview) for run tracing), you can use this field to remove the extra parameters. + If you receive an error about unnecessary parameters (which is more common when using [LangChain JS](/oss/langchain/overview) for run tracing), you can use this field to remove the extra parameters. ## Tool settings diff --git a/src/oss/contributing/code.mdx b/src/oss/contributing/code.mdx index fc1c49a78b..9e7b30107b 100644 --- a/src/oss/contributing/code.mdx +++ b/src/oss/contributing/code.mdx @@ -316,7 +316,7 @@ Set up a development environment for the package(s) you're working on: :::js Located in `libs/providers/`, these are independently versioned packages for specific integrations. For example: - **[`@langchain/openai`](https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-openai#readme)**: [OpenAI](/oss/integrations/providers/openai) integrations - - **[`@langchain/anthropic`](https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-anthropic#readme)**: [Anthropic](oss/javascript/integrations/providers/anthropic) integrations + - **[`@langchain/anthropic`](https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-anthropic#readme)**: [Anthropic](/oss/integrations/providers/anthropic) integrations - **[`@langchain/google-genai`](https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-google-genai#readme)**: [Google Generative AI](/oss/integrations/chat/google_generative_ai) integrations ::: diff --git a/src/oss/javascript/integrations/chat/anthropic.mdx b/src/oss/javascript/integrations/chat/anthropic.mdx index 52e92258fe..6f0e1c8532 100644 --- a/src/oss/javascript/integrations/chat/anthropic.mdx +++ b/src/oss/javascript/integrations/chat/anthropic.mdx @@ -990,7 +990,7 @@ Learn more about tool calling [here](https://js.langchain.com/docs/how_to/tool_c ### Using with text splitters -Anthropic also lets you specify your own splits using [custom document](https://docs.anthropic.com/en/docs/build-with-claude/citations#custom-content-documents) types. LangChain [text splitters](/oss/concepts/text_splitters/) can be used to generate meaningful splits for this purpose. See the below example, where we split the LangChain.js README (a markdown document) and pass it to Claude as context: +Anthropic also lets you specify your own splits using [custom document](https://docs.anthropic.com/en/docs/build-with-claude/citations#custom-content-documents) types. LangChain text splitters can be used to generate meaningful splits for this purpose. See the below example, where we split the LangChain.js README (a markdown document) and pass it to Claude as context: ```typescript import { ChatAnthropic } from "@langchain/anthropic"; diff --git a/src/oss/javascript/integrations/chat/openai.mdx b/src/oss/javascript/integrations/chat/openai.mdx index ae2b2a055c..ed93e77723 100644 --- a/src/oss/javascript/integrations/chat/openai.mdx +++ b/src/oss/javascript/integrations/chat/openai.mdx @@ -335,15 +335,7 @@ console.dir(responseMessageWithLogprobs.response_metadata.logprobs, { depth: nul } ``` -## Tool calling - -Tool calling with OpenAI models works in a similar to [other models](/oss/langchain/tools). Additionally, the following guides have some information especially relevant to OpenAI: - -- [How to: disable parallel tool calling](/oss/langchain/tools_parallel/) -- [How to: force a tool call](/oss/how-to/tool_choice/) -- [How to: bind model-specific tool formats to a model](/oss/langchain/tools#binding-model-specific-formats-advanced). - -### Custom Tools +## Custom Tools [Custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) support tools with arbitrary string inputs. They can be particularly useful when you expect your string arguments to be long or complex. diff --git a/src/oss/javascript/integrations/llm_caching/index.mdx b/src/oss/javascript/integrations/llm_caching/index.mdx index ace78dff63..93ad290490 100644 --- a/src/oss/javascript/integrations/llm_caching/index.mdx +++ b/src/oss/javascript/integrations/llm_caching/index.mdx @@ -2,7 +2,7 @@ title: Model caches --- -[Caching LLM calls](/oss/how-to/chat_model_caching) can be useful for testing, cost savings, and speed. +[Caching LLM calls](/oss/langchain/models#caching) can be useful for testing, cost savings, and speed. Below are some integrations that allow you to cache results of individual LLM calls using different caches with different strategies. diff --git a/src/oss/javascript/integrations/llms/azure.mdx b/src/oss/javascript/integrations/llms/azure.mdx index 183037db29..82f017158a 100644 --- a/src/oss/javascript/integrations/llms/azure.mdx +++ b/src/oss/javascript/integrations/llms/azure.mdx @@ -5,7 +5,7 @@ title: Azure OpenAI ```{=mdx} -**You are currently on a page documenting the use of Azure OpenAI [text completion models](/oss/concepts/text_llms). The latest and most popular Azure OpenAI models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Azure OpenAI text completion models. The latest and most popular Azure OpenAI models are [chat completion models](/oss/langchain/models).** Unless you are specifically using `gpt-3.5-turbo-instruct`, you are probably looking for [this page instead](/oss/integrations/chat/azure/). diff --git a/src/oss/javascript/integrations/llms/bedrock.mdx b/src/oss/javascript/integrations/llms/bedrock.mdx index e6dd546dd0..1978bf489a 100644 --- a/src/oss/javascript/integrations/llms/bedrock.mdx +++ b/src/oss/javascript/integrations/llms/bedrock.mdx @@ -7,7 +7,7 @@ title: Bedrock ```{=mdx} -**You are currently on a page documenting the use of Amazon Bedrock models as [text completion models](/oss/concepts/text_llms). Many popular models available on Bedrock are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Amazon Bedrock models as text completion models. Many popular models available on Bedrock are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/bedrock/). diff --git a/src/oss/javascript/integrations/llms/cohere.mdx b/src/oss/javascript/integrations/llms/cohere.mdx index 36a92b2b45..0062d816bf 100644 --- a/src/oss/javascript/integrations/llms/cohere.mdx +++ b/src/oss/javascript/integrations/llms/cohere.mdx @@ -9,7 +9,7 @@ Cohere has marked their `generate` endpoint for LLMs as deprecated. Follow their -**You are currently on a page documenting the use of Cohere models as [text completion models](/oss/concepts/text_llms). Many popular models available on Cohere are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Cohere models as text completion models. Many popular models available on Cohere are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/cohere/). diff --git a/src/oss/javascript/integrations/llms/fireworks.mdx b/src/oss/javascript/integrations/llms/fireworks.mdx index 82212ebb82..224ff6a947 100644 --- a/src/oss/javascript/integrations/llms/fireworks.mdx +++ b/src/oss/javascript/integrations/llms/fireworks.mdx @@ -5,7 +5,7 @@ title: Fireworks ```{=mdx} -**You are currently on a page documenting the use of Fireworks models as [text completion models](/oss/concepts/text_llms). Many popular models available on Fireworks are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Fireworks models as text completion models. Many popular models available on Fireworks are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/fireworks/). diff --git a/src/oss/javascript/integrations/llms/google_vertex_ai.mdx b/src/oss/javascript/integrations/llms/google_vertex_ai.mdx index 32f1d2b408..a3d7c0622d 100644 --- a/src/oss/javascript/integrations/llms/google_vertex_ai.mdx +++ b/src/oss/javascript/integrations/llms/google_vertex_ai.mdx @@ -5,7 +5,7 @@ title: Google Vertex AI ```{=mdx} -**You are currently on a page documenting the use of Google Vertex models as [text completion models](/oss/concepts/text_llms). Many popular models available on Google Vertex are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Google Vertex models as text completion models. Many popular models available on Google Vertex are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/google_vertex_ai/). diff --git a/src/oss/javascript/integrations/llms/index.mdx b/src/oss/javascript/integrations/llms/index.mdx index 8662c2112d..e45e5d87a7 100644 --- a/src/oss/javascript/integrations/llms/index.mdx +++ b/src/oss/javascript/integrations/llms/index.mdx @@ -3,7 +3,7 @@ title: LLMs --- -**You are currently on a page documenting the use of [text completion models](/oss/concepts/text_llms). Many of the latest and most popular models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of text completion models. Many of the latest and most popular models are [chat completion models](/oss/langchain/models).** Unless you are specifically using more advanced prompting techniques, you are probably looking for [this page instead](/oss/integrations/chat/). diff --git a/src/oss/javascript/integrations/llms/mistral.mdx b/src/oss/javascript/integrations/llms/mistral.mdx index 5d6e9cbae5..a7802de166 100644 --- a/src/oss/javascript/integrations/llms/mistral.mdx +++ b/src/oss/javascript/integrations/llms/mistral.mdx @@ -10,7 +10,7 @@ title: MistralAI ::: caution -You are currently on a page documenting the use of Mistral models as [text completion models](/oss/concepts/text_llms). Many popular models available on Mistral are [chat completion models](/oss/langchain/models). +You are currently on a page documenting the use of Mistral models as text completion models. Many popular models available on Mistral are [chat completion models](/oss/langchain/models). You may be looking for [this page instead](/oss/integrations/chat/mistral/). ::: diff --git a/src/oss/javascript/integrations/llms/ollama.mdx b/src/oss/javascript/integrations/llms/ollama.mdx index 3bd32efcbf..2cd39c8c45 100644 --- a/src/oss/javascript/integrations/llms/ollama.mdx +++ b/src/oss/javascript/integrations/llms/ollama.mdx @@ -5,7 +5,7 @@ title: Ollama ```{=mdx} -**You are currently on a page documenting the use of Ollama models as [text completion models](/oss/concepts/text_llms). Many popular models available on Ollama are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Ollama models as text completion models. Many popular models available on Ollama are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/ollama/). diff --git a/src/oss/javascript/integrations/llms/openai.mdx b/src/oss/javascript/integrations/llms/openai.mdx index 1b604bab2d..c72505d8d3 100644 --- a/src/oss/javascript/integrations/llms/openai.mdx +++ b/src/oss/javascript/integrations/llms/openai.mdx @@ -5,7 +5,7 @@ title: OpenAI ```{=mdx} -**You are currently on a page documenting the use of OpenAI [text completion models](/oss/concepts/text_llms). The latest and most popular OpenAI models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of OpenAI text completion models. The latest and most popular OpenAI models are [chat completion models](/oss/langchain/models).** Unless you are specifically using `gpt-3.5-turbo-instruct`, you are probably looking for [this page instead](/oss/integrations/chat/openai/). diff --git a/src/oss/javascript/integrations/llms/together.mdx b/src/oss/javascript/integrations/llms/together.mdx index 87452d36f4..28c602fd22 100644 --- a/src/oss/javascript/integrations/llms/together.mdx +++ b/src/oss/javascript/integrations/llms/together.mdx @@ -3,7 +3,7 @@ title: TogetherAI --- -**You are currently on a page documenting the use of Together AI models as [text completion models](/oss/concepts/text_llms). Many popular models available on Together AI are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Together AI models as text completion models. Many popular models available on Together AI are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/togetherai/). diff --git a/src/oss/javascript/integrations/providers/all_providers.mdx b/src/oss/javascript/integrations/providers/all_providers.mdx index c55fabaa83..9be17a92d8 100644 --- a/src/oss/javascript/integrations/providers/all_providers.mdx +++ b/src/oss/javascript/integrations/providers/all_providers.mdx @@ -53,14 +53,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Alibaba's Tongyi language model for Chinese and multilingual applications. Claude models for advanced conversational AI and reasoning. @@ -68,14 +68,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Security-focused AI chat integration with built-in protections. OpenAI models through Microsoft Azure's enterprise platform. @@ -83,21 +83,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Baidu's Qianfan platform for Chinese language AI models. Baidu's Wenxin (ERNIE) models for natural language processing. Access foundation models through Amazon Bedrock's managed service. @@ -105,7 +105,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Unified Bedrock Converse API for multiple foundation models. @@ -113,21 +113,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Ultra-fast inference with Cerebras Systems' AI processors. Run AI models on Cloudflare's edge computing platform. Cohere's language models for text generation and understanding. @@ -135,28 +135,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Access open-source models through Deep Infra's cloud platform. DeepSeek's advanced reasoning and coding models. Mock chat model for testing and development purposes. High-performance inference for open-source models. @@ -164,14 +164,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Optimized inference engine for efficient model serving. Google's Gemini models and generative AI capabilities. @@ -179,7 +179,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Enterprise AI platform with Google Cloud's Vertex AI. @@ -187,7 +187,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Ultra-fast inference with Groq's specialized hardware. @@ -195,28 +195,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri IBM Watson AI models and enterprise solutions. Run local Llama models with llama.cpp backend. Minimax's conversational AI models and services. Mistral's efficient and powerful language models. @@ -224,28 +224,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Moonshot's AI models for various language tasks. Decentralized AI network through Bittensor protocol. Novita's AI models and cloud computing platform. Run local models with Ollama's lightweight inference engine. @@ -253,7 +253,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Function calling capabilities with Ollama models. @@ -261,7 +261,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri GPT models and OpenAI's comprehensive chat capabilities. @@ -269,35 +269,35 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Perplexity's search-augmented language models. PremAI's platform for AI model deployment and management. OpenAI integration with PromptLayer's observability features. Tencent's Hunyuan models for Chinese language processing. Open-source models through Together AI's cloud platform. @@ -305,28 +305,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Run language models directly in web browsers. xAI's Grok models for conversational AI. Yandex's AI models and language processing services. ZhipuAI's ChatGLM and other Chinese language models. @@ -337,28 +337,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri AI21 Labs' Jurassic models for text generation. European AI company's multilingual language models. Security-focused LLM integration with built-in protections. Deploy models on Amazon SageMaker's ML platform. @@ -366,7 +366,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri OpenAI models through Microsoft Azure's enterprise platform. @@ -374,7 +374,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Foundation models through Amazon Bedrock service. @@ -382,21 +382,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Browser-based AI using Chrome's built-in capabilities. AI models on Cloudflare's edge computing platform. Cohere's language models for various NLP tasks. @@ -404,14 +404,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Open-source models through Deep Infra's infrastructure. Fast inference for open-source language models. @@ -419,14 +419,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Optimized serving for efficient model inference. Google Cloud's enterprise AI and ML platform. @@ -434,49 +434,49 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Private AI model training and deployment platform. Access thousands of models via Hugging Face Inference API. IBM Watson AI and language model services. JigsawStack's AI infrastructure and model services. Security-enhanced LLM integration with monitoring. Run Llama models locally with C++ implementation. Mistral's open-source and commercial language models. @@ -484,14 +484,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Decentralized AI through Bittensor's peer-to-peer network. Local model serving with Ollama's simple interface. @@ -499,7 +499,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri GPT models and OpenAI's language model APIs. @@ -507,28 +507,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri OpenAI with PromptLayer's logging and observability. AI integration for Raycast productivity tool. Run open-source models through Replicate's cloud platform. Fast inference for open-source models on Together's platform. @@ -536,14 +536,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Writer's enterprise AI platform for content generation. Yandex's language models and AI services. @@ -554,14 +554,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Alibaba's embedding models for multilingual text representation. OpenAI embeddings through Microsoft Azure platform. @@ -569,14 +569,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Baidu's text embedding models for Chinese content. Foundation model embeddings through Amazon Bedrock. @@ -584,21 +584,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri ByteDance's embedding models for content understanding. Text embeddings on Cloudflare's edge AI platform. Cohere's multilingual embedding models. @@ -606,14 +606,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Open-source embedding models via DeepInfra. Fast embedding inference through Fireworks platform. @@ -621,7 +621,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Google's embedding models for text representation. @@ -629,7 +629,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Enterprise embedding models through Vertex AI. @@ -637,49 +637,49 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Private embedding models with Gradient AI platform. Thousands of embedding models via Hugging Face. IBM Watson embedding models and AI services. Jina's neural search and embedding models. Local embedding generation with llama.cpp. Minimax's text embedding and representation models. Mistral's efficient embedding models. @@ -687,21 +687,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri High-quality multilingual embedding models. Nomic's open-source embedding models. Local embedding models through Ollama. @@ -709,7 +709,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri OpenAI's text-embedding models for semantic search. @@ -717,35 +717,35 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Pinecone's embedding models and vector database. PremAI's embedding models and AI platform. Tencent's embedding models for Chinese text. TensorFlow-based embedding models and inference. Open-source embedding models on Together platform. @@ -753,21 +753,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Local transformer-based embedding models. Voyage AI's domain-specific embedding models. ZhipuAI's Chinese language embedding models. @@ -778,28 +778,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Alibaba Cloud's AnalyticDB for vector storage and search. DataStax Astra DB vector database for scalable storage. Edge-based vector storage with Azion's EdgeSQL. Microsoft Azure's AI-powered search and vector storage. @@ -807,7 +807,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Vector search in Azure Cosmos DB with MongoDB API. @@ -815,7 +815,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Vector storage in Azure Cosmos DB NoSQL API. @@ -823,70 +823,70 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Apache Cassandra vector search capabilities. Open-source embedding database for AI applications. Fast columnar database with vector search support. High-performance vector database for similarity search. Serverless vector database on Cloudflare's edge. Full-stack platform with integrated vector storage. NoSQL database with vector search capabilities. Distributed search engine with vector search support. Facebook's library for efficient similarity search. PostgreSQL with vector extensions on Google Cloud. @@ -894,7 +894,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Vector search through Google Vertex AI platform. @@ -902,238 +902,238 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Enterprise vector database with SAP HANA. Fast approximate nearest neighbor search library. Developer-friendly embedded vector database. SQLite-compatible database with vector extensions. Open-source database with vector search capabilities. In-memory vector storage for development and testing. Open-source vector database for AI applications. Serverless vector indexing with Momento's platform. Vector search in MongoDB Atlas cloud database. SQL-compatible vector database for analytics. Graph database with integrated vector search. Serverless PostgreSQL with vector extensions. Open-source search engine with vector capabilities. PostgreSQL extension for vector similarity search. Managed vector database for machine learning applications. Type-safe database client with vector support. Open-source vector similarity search engine. In-memory database with vector search capabilities. Real-time analytics database with vector search. Distributed database with built-in vector functions. Open-source Firebase alternative with vector support. Developer-focused database with vector search. High-performance vector database for embeddings. TypeScript ORM with vector database support. Open-source search engine with vector capabilities. Serverless vector database with Redis compatibility. Smaller and faster single-file vector search engine. Neural search platform with built-in understanding. PostgreSQL database with vector extensions on Vercel. WebAssembly-based vector database for browsers. Open-source vector database with GraphQL API. Serverless database with built-in vector search. Long-term memory for AI assistants in the cloud. Long-term memory for AI assistants and agents. @@ -1146,105 +1146,105 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load and parse ChatGPT conversation exports. Load data from CSV files with customizable parsing. Recursively load documents from filesystem directories. Extract text and metadata from Microsoft Word documents. Load and parse EPUB e-book files. Load and parse JSON files with flexible structure handling. Load newline-delimited JSON files. Load multiple files of different types simultaneously. Load Notion pages exported as Markdown. Transcribe audio files using OpenAI's Whisper model. Extract text from PDF documents. Load Microsoft PowerPoint presentations. Load subtitle files (SRT, VTT formats). Load plain text files with encoding detection. Load various file formats using Unstructured.io. @@ -1255,28 +1255,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load records from Airtable bases. Load data from Apify web scraping datasets. Transcribe audio using AssemblyAI's API. Load files from Azure Blob Storage containers. @@ -1284,7 +1284,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load individual files from Azure Blob Storage. @@ -1292,63 +1292,63 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load web content using Browserbase's cloud browsers. Scrape College Confidential forum content. Load pages from Atlassian Confluence. Load documents from Couchbase databases. Load Figma design files and comments. Crawl websites using Firecrawl's web scraping API. Load content from GitBook documentation sites. Load files and repositories from GitHub. Load files from Google Cloud Storage buckets. @@ -1356,7 +1356,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load data from Google Cloud SQL PostgreSQL databases. @@ -1364,56 +1364,56 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load posts and comments from Hacker News. Load movie scripts from the Internet Movie Script Database. Load issues and projects from Atlassian Jira. Load runs and datasets from LangSmith. Load pages and databases from Notion. Load PDF files from web URLs. Recursively crawl and load web pages. Load files from Amazon S3 buckets. @@ -1421,77 +1421,77 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Load search results using SearchAPI. Load search results using SerpAPI. Load URLs from website sitemaps. Transcribe audio using Sonix's transcription API. Load blockchain data from Sort.xyz. Fast web crawling using Spider API. Load projects and tasks from Taskade. Scrape web pages using Cheerio for server-side parsing. Load dynamic web content using Playwright browser automation. Scrape JavaScript-heavy websites using Puppeteer. Load YouTube video transcripts and metadata. @@ -1502,21 +1502,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Convert HTML content to clean, readable text. Extract main content from web pages using Mozilla's Readability. Generate metadata tags for documents using OpenAI. @@ -1528,7 +1528,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Rerank documents using Cohere's reranking models. @@ -1536,14 +1536,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Document compression using IBM Watson AI services. Rerank and compress documents using MixedBread AI. @@ -1554,14 +1554,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Persistent memory storage using DataStax AstraDB. Memory storage using Amazon Aurora DSQL. @@ -1569,7 +1569,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Memory storage in Azure Cosmos DB with MongoDB vCore. @@ -1577,7 +1577,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Store conversation memory in Azure Cosmos DB. @@ -1585,28 +1585,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Distributed memory storage using Apache Cassandra. Edge-based memory storage with Cloudflare D1. Full-stack memory storage with Convex. Serverless memory storage using Amazon DynamoDB. @@ -1614,14 +1614,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Local file-based memory storage for development. NoSQL memory storage using Google Firestore. @@ -1629,7 +1629,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri PostgreSQL memory storage on Google Cloud. @@ -1637,84 +1637,84 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Decentralized memory storage using IPFS. AI-powered personalized memory using Mem0. Serverless cache for conversation memory. Document-based memory storage using MongoDB. Long-term memory management with Motorhead. Serverless MySQL memory storage with PlanetScale. Relational memory storage using PostgreSQL. Fast in-memory storage using Redis. Serverless Redis memory storage with Upstash. Serverless database memory storage with Xata. Long-term memory for AI assistants with Zep. Cloud-hosted long-term memory with Zep. @@ -1725,14 +1725,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Execute OpenAI ChatGPT plugins as tools. Secure code execution in Azure Dynamic Sessions. @@ -1740,21 +1740,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Modular AI actions and integrations with Connery. Access Connery's toolkit of pre-built actions. Generate images using OpenAI's DALL-E models. @@ -1762,35 +1762,35 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Code execution and analysis with Decodo. Interact with Discord servers and channels. Privacy-focused web search with DuckDuckGo. AI-powered search engine for better results. Read and send emails through Gmail API. @@ -1798,14 +1798,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Simple tool execution framework. Manage events and schedules in Google Calendar. @@ -1813,7 +1813,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Search for places using Google Places API. @@ -1821,7 +1821,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Get directions and routing information. @@ -1829,7 +1829,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Search academic papers and citations. @@ -1837,7 +1837,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Analyze search trends and popularity data. @@ -1845,28 +1845,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Access IBM Watson AI tools and services. AI infrastructure tools from JigsawStack. Parse and manipulate JSON data structures. Execute code in AWS Lambda functions. @@ -1874,49 +1874,49 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Model Context Protocol tools and utilities. Generate tools from OpenAPI specifications. Execute Python code in a sandboxed environment. Web search capabilities through SearchAPI. Privacy-respecting metasearch engine. Google Search results through SerpAPI. Execute AWS Step Functions workflows. @@ -1924,91 +1924,91 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Query databases using natural language. Search Stack Overflow and other SE sites. Browser automation for web interactions. Web crawling capabilities with Tavily. Extract structured data from web pages. Map and visualize web crawling results. AI-optimized search for retrieval applications. Community-powered search through Tavily. Query vector databases as tools. Automated web browsing and interaction. Search and retrieve Wikipedia articles. Computational knowledge through Wolfram Alpha. Automate workflows using Zapier integrations. @@ -2019,21 +2019,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Search and retrieve academic papers from ArXiv. Edge-based document retrieval with Azion. Retrieve from Amazon Bedrock Knowledge Bases. @@ -2041,21 +2041,21 @@ Browse the complete collection of integrations available for JavaScript/TypeScri BM25 algorithm for keyword-based retrieval. Document retrieval using Chaindesk platform. Official ChatGPT retriever plugin integration. @@ -2063,28 +2063,28 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Decentralized knowledge retrieval with Dria. AI-powered web search and retrieval. Hypothetical Document Embeddings for better retrieval. Enterprise search with Amazon Kendra. @@ -2092,49 +2092,49 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Managed vector search with Metal. Hybrid search combining vector and keyword search. AI-optimized search for RAG applications. Time-aware document retrieval and ranking. Big data serving engine for vector search. Cloud-based long-term memory retrieval. Long-term memory and context retrieval. @@ -2145,56 +2145,56 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Self-querying retriever for Chroma vector store. Self-querying retriever for Hnswlib. Self-querying retriever for in-memory storage. Self-querying retriever for Pinecone. Self-querying retriever for Qdrant. Self-querying retriever for Supabase. Self-querying retriever for Vectara. Self-querying retriever for Weaviate. @@ -2205,42 +2205,42 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Distributed key-value storage using Cassandra. Local file system storage for development. Fast in-memory storage for temporary data. Redis-based storage using IoRedis client. Serverless Redis storage with Upstash. Key-value storage on Vercel's edge network. @@ -2251,7 +2251,7 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Cache LLM responses in Azure Cosmos DB. @@ -2263,14 +2263,14 @@ Browse the complete collection of integrations available for JavaScript/TypeScri Monitor and trace LangChain applications with Datadog. Rate limiting for AI applications using Upstash. diff --git a/src/oss/javascript/integrations/providers/index.mdx b/src/oss/javascript/integrations/providers/index.mdx index c32af66254..5012d1c66a 100644 --- a/src/oss/javascript/integrations/providers/index.mdx +++ b/src/oss/javascript/integrations/providers/index.mdx @@ -13,25 +13,25 @@ These providers have standalone `@langchain/{provider}` packages for improved ve | Provider | Package | Downloads | Latest | | :------- | :------ | :-------- | :------| | [Anthropic](/oss/integrations/providers/anthropic) | [@langchain/anthropic](https://www.npmjs.com/package/@langchain/anthropic) | ![Downloads](https://img.shields.io/npm/dm/@langchain/anthropic) | ![NPM](https://img.shields.io/npm/v/@langchain/anthropic) | -| [Azure CosmosDB](/oss/integrations/providers/azure_cosmosdb) | [@langchain/azure-cosmosdb](https://www.npmjs.com/package/@langchain/azure-cosmosdb) | ![Downloads](https://img.shields.io/npm/dm/@langchain/azure-cosmosdb) | ![NPM](https://img.shields.io/npm/v/@langchain/azure-cosmosdb) | -| [Cerebras](/oss/integrations/providers/cerebras) | [@langchain/cerebras](https://www.npmjs.com/package/@langchain/cerebras) | ![Downloads](https://img.shields.io/npm/dm/@langchain/cerebras) | ![NPM](https://img.shields.io/npm/v/@langchain/cerebras) | -| [Cloudflare](/oss/integrations/providers/cloudflare) | [@langchain/cloudflare](https://www.npmjs.com/package/@langchain/cloudflare) | ![Downloads](https://img.shields.io/npm/dm/@langchain/cloudflare) | ![NPM](https://img.shields.io/npm/v/@langchain/cloudflare) | -| [Cohere](/oss/integrations/providers/cohere) | [@langchain/cohere](https://www.npmjs.com/package/@langchain/cohere) | ![Downloads](https://img.shields.io/npm/dm/@langchain/cohere) | ![NPM](https://img.shields.io/npm/v/@langchain/cohere) | -| [Exa](/oss/integrations/providers/exa) | [langchain-exa](https://www.npmjs.com/package/@langchain/exa) | ![Downloads](https://img.shields.io/npm/dm/@langchain/exa) | ![NPM](https://img.shields.io/npm/v/@langchain/exa) | -| [Google GenAI](/oss/integrations/providers/google_genai) | [@langchain/google-genai](https://www.npmjs.com/package/@langchain/google-genai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/google-genai) | ![NPM](https://img.shields.io/npm/v/@langchain/google-genai) | -| [Google VertexAI](/oss/integrations/providers/google_vertexai) | [@langchain/google-vertexai](https://www.npmjs.com/package/@langchain/google-vertexai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/google-vertexai) | ![NPM](https://img.shields.io/npm/v/@langchain/google-vertexai) | -| [Google VertexAI (Web Environments)](/oss/integrations/providers/google_vertexai_web) | [@langchain/google-vertexai-web](https://www.npmjs.com/package/@langchain/google-vertexai-web) | ![Downloads](https://img.shields.io/npm/dm/@langchain/google-vertexai-web) | ![NPM](https://img.shields.io/npm/v/@langchain/google-vertexai-web) | -| [Groq](/oss/integrations/providers/groq) | [@langchain/groq](https://www.npmjs.com/package/@langchain/groq) | ![Downloads](https://img.shields.io/npm/dm/@langchain/groq) | ![NPM](https://img.shields.io/npm/v/@langchain/groq) | -| [MistralAI](/oss/integrations/providers/mistralai) | [@langchain/mistralai](https://www.npmjs.com/package/@langchain/mistralai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/mistralai) | ![NPM](https://img.shields.io/npm/v/@langchain/mistralai) | -| [MongoDB](/oss/integrations/providers/mongodb) | [@langchain/mongodb](https://www.npmjs.com/package/@langchain/mongodb) | ![Downloads](https://img.shields.io/npm/dm/@langchain/mongodb) | ![NPM](https://img.shields.io/npm/v/@langchain/mongodb) | -| [Nomic](/oss/integrations/providers/nomic) | [@langchain/nomic](https://www.npmjs.com/package/@langchain/nomic) | ![Downloads](https://img.shields.io/npm/dm/@langchain/nomic) | ![NPM](https://img.shields.io/npm/v/@langchain/nomic) | +| [Azure CosmosDB](/oss/integrations/vectorstores/azure_cosmosdb_nosql) | [@langchain/azure-cosmosdb](https://www.npmjs.com/package/@langchain/azure-cosmosdb) | ![Downloads](https://img.shields.io/npm/dm/@langchain/azure-cosmosdb) | ![NPM](https://img.shields.io/npm/v/@langchain/azure-cosmosdb) | +| [Cerebras](/oss/integrations/chat/cerebras) | [@langchain/cerebras](https://www.npmjs.com/package/@langchain/cerebras) | ![Downloads](https://img.shields.io/npm/dm/@langchain/cerebras) | ![NPM](https://img.shields.io/npm/v/@langchain/cerebras) | +| Cloudflare | [@langchain/cloudflare](https://www.npmjs.com/package/@langchain/cloudflare) | ![Downloads](https://img.shields.io/npm/dm/@langchain/cloudflare) | ![NPM](https://img.shields.io/npm/v/@langchain/cloudflare) | +| [Cohere](/oss/integrations/chat/cohere) | [@langchain/cohere](https://www.npmjs.com/package/@langchain/cohere) | ![Downloads](https://img.shields.io/npm/dm/@langchain/cohere) | ![NPM](https://img.shields.io/npm/v/@langchain/cohere) | +| [Exa](/oss/integrations/retrievers/exa) | [langchain-exa](https://www.npmjs.com/package/@langchain/exa) | ![Downloads](https://img.shields.io/npm/dm/@langchain/exa) | ![NPM](https://img.shields.io/npm/v/@langchain/exa) | +| [Google GenAI](/oss/integrations/chat/google_generative_ai) | [@langchain/google-genai](https://www.npmjs.com/package/@langchain/google-genai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/google-genai) | ![NPM](https://img.shields.io/npm/v/@langchain/google-genai) | +| [Google VertexAI](/oss/integrations/chat/google_vertex_ai) | [@langchain/google-vertexai](https://www.npmjs.com/package/@langchain/google-vertexai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/google-vertexai) | ![NPM](https://img.shields.io/npm/v/@langchain/google-vertexai) | +| [Google VertexAI (Web Environments) | [@langchain/google-vertexai-web](https://www.npmjs.com/package/@langchain/google-vertexai-web) | ![Downloads](https://img.shields.io/npm/dm/@langchain/google-vertexai-web) | ![NPM](https://img.shields.io/npm/v/@langchain/google-vertexai-web) | +| [Groq](/oss/integrations/chat/groq) | [@langchain/groq](https://www.npmjs.com/package/@langchain/groq) | ![Downloads](https://img.shields.io/npm/dm/@langchain/groq) | ![NPM](https://img.shields.io/npm/v/@langchain/groq) | +| [MistralAI](/oss/integrations/chat/mistral) | [@langchain/mistralai](https://www.npmjs.com/package/@langchain/mistralai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/mistralai) | ![NPM](https://img.shields.io/npm/v/@langchain/mistralai) | +| [MongoDB](/oss/integrations/memory/mongodb) | [@langchain/mongodb](https://www.npmjs.com/package/@langchain/mongodb) | ![Downloads](https://img.shields.io/npm/dm/@langchain/mongodb) | ![NPM](https://img.shields.io/npm/v/@langchain/mongodb) | +| [Nomic](/oss/integrations/text_embedding/nomic) | [@langchain/nomic](https://www.npmjs.com/package/@langchain/nomic) | ![Downloads](https://img.shields.io/npm/dm/@langchain/nomic) | ![NPM](https://img.shields.io/npm/v/@langchain/nomic) | | [OpenAI](/oss/integrations/providers/openai) | [@langchain/openai](https://www.npmjs.com/package/@langchain/openai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/openai) | ![NPM](https://img.shields.io/npm/v/@langchain/openai) | -| [Pinecone](/oss/integrations/providers/pinecone) | [@langchain/pinecone](https://www.npmjs.com/package/@langchain/pinecone) | ![Downloads](https://img.shields.io/npm/dm/@langchain/pinecone) | ![NPM](https://img.shields.io/npm/v/@langchain/pinecone) | -| [Qdrant](/oss/integrations/providers/qdrant) | [@langchain/qdrant](https://www.npmjs.com/package/@langchain/qdrant) | ![Downloads](https://img.shields.io/npm/dm/@langchain/qdrant) | ![NPM](https://img.shields.io/npm/v/@langchain/qdrant) | -| [Tavily](/oss/integrations/providers/tavily) | [@langchain/tavily](https://www.npmjs.com/package/@langchain/tavily) | ![Downloads](https://img.shields.io/npm/dm/@langchain/tavily) | ![NPM](https://img.shields.io/npm/v/@langchain/tavily) | -| [Weaviate](/oss/integrations/providers/weaviate) | [@langchain/weaviate](https://www.npmjs.com/package/@langchain/weaviate) | ![Downloads](https://img.shields.io/npm/dm/@langchain/weaviate) | ![NPM](https://img.shields.io/npm/v/@langchain/weaviate) | -| [xAI](/oss/integrations/providers/xai) | [@langchain/xai](https://www.npmjs.com/package/@langchain/xai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/xai) | ![NPM](https://img.shields.io/npm/v/@langchain/xai) | -| [Yandex](/oss/integrations/providers/yandex) | [@langchain/yandex](https://www.npmjs.com/package/@langchain/yandex) | ![Downloads](https://img.shields.io/npm/dm/@langchain/yandex) | ![NPM](https://img.shields.io/npm/v/@langchain/yandex) | +| [Pinecone](/oss/integrations/vectorstores/pinecone) | [@langchain/pinecone](https://www.npmjs.com/package/@langchain/pinecone) | ![Downloads](https://img.shields.io/npm/dm/@langchain/pinecone) | ![NPM](https://img.shields.io/npm/v/@langchain/pinecone) | +| [Qdrant](/oss/integrations/vectorstores/qdrant) | [@langchain/qdrant](https://www.npmjs.com/package/@langchain/qdrant) | ![Downloads](https://img.shields.io/npm/dm/@langchain/qdrant) | ![NPM](https://img.shields.io/npm/v/@langchain/qdrant) | +| [Tavily](/oss/integrations/retrievers/tavily) | [@langchain/tavily](https://www.npmjs.com/package/@langchain/tavily) | ![Downloads](https://img.shields.io/npm/dm/@langchain/tavily) | ![NPM](https://img.shields.io/npm/v/@langchain/tavily) | +| [Weaviate](/oss/integrations/vectorstores/weaviate) | [@langchain/weaviate](https://www.npmjs.com/package/@langchain/weaviate) | ![Downloads](https://img.shields.io/npm/dm/@langchain/weaviate) | ![NPM](https://img.shields.io/npm/v/@langchain/weaviate) | +| [xAI](/oss/integrations/chat/xai) | [@langchain/xai](https://www.npmjs.com/package/@langchain/xai) | ![Downloads](https://img.shields.io/npm/dm/@langchain/xai) | ![NPM](https://img.shields.io/npm/v/@langchain/xai) | +| [Yandex](/oss/integrations/chat/yandex) | [@langchain/yandex](https://www.npmjs.com/package/@langchain/yandex) | ![Downloads](https://img.shields.io/npm/dm/@langchain/yandex) | ![NPM](https://img.shields.io/npm/v/@langchain/yandex) | ## All providers diff --git a/src/oss/javascript/integrations/stores/cassandra_storage.mdx b/src/oss/javascript/integrations/stores/cassandra_storage.mdx index a7daa11d4a..f1496d450c 100644 --- a/src/oss/javascript/integrations/stores/cassandra_storage.mdx +++ b/src/oss/javascript/integrations/stores/cassandra_storage.mdx @@ -56,4 +56,4 @@ import CassandraStorage from "/snippets/javascript-integrations/examples/stores/ ## Related -- [Key-value store conceptual guide](/oss/concepts/key_value_stores) +- [Key-value store conceptual guide](/oss/integrations/stores) diff --git a/src/oss/javascript/integrations/stores/file_system.mdx b/src/oss/javascript/integrations/stores/file_system.mdx index e21ae7f743..5927de40a5 100644 --- a/src/oss/javascript/integrations/stores/file_system.mdx +++ b/src/oss/javascript/integrations/stores/file_system.mdx @@ -14,7 +14,7 @@ Only available on Node.js. ``` -This will help you get started with [LocalFileStore](/oss/concepts/key_value_stores). For detailed documentation of all LocalFileStore features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain.storage_file_system.LocalFileStore.html). +This will help you get started with [LocalFileStore](/oss/integrations/stores). For detailed documentation of all LocalFileStore features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain.storage_file_system.LocalFileStore.html). ## Overview diff --git a/src/oss/javascript/integrations/stores/in_memory.mdx b/src/oss/javascript/integrations/stores/in_memory.mdx index f5fde4e55e..2a8023b52c 100644 --- a/src/oss/javascript/integrations/stores/in_memory.mdx +++ b/src/oss/javascript/integrations/stores/in_memory.mdx @@ -2,7 +2,7 @@ title: InMemoryStore --- -This will help you get started with [InMemoryStore](/oss/concepts/key_value_stores). For detailed documentation of all InMemoryStore features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain_core.stores.InMemoryStore.html). +This will help you get started with [InMemoryStore](/oss/integrations/stores). For detailed documentation of all InMemoryStore features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain_core.stores.InMemoryStore.html). The `InMemoryStore` allows for a generic type to be assigned to the values in the store. We'll assign type `BaseMessage` as the type of our values, keeping with the theme of a chat history store. diff --git a/src/oss/javascript/integrations/stores/index.mdx b/src/oss/javascript/integrations/stores/index.mdx index fb2defc8ad..58cdc16d40 100644 --- a/src/oss/javascript/integrations/stores/index.mdx +++ b/src/oss/javascript/integrations/stores/index.mdx @@ -2,7 +2,7 @@ title: Key-value stores --- -[Key-value stores](/oss/concepts/key_value_stores) are used by other LangChain components to store and retrieve data. +[Key-value stores](/oss/integrations/stores) are used by other LangChain components to store and retrieve data. ## All key-value stores diff --git a/src/oss/javascript/integrations/stores/ioredis_storage.mdx b/src/oss/javascript/integrations/stores/ioredis_storage.mdx index b3e2f9bd73..53873b13c6 100644 --- a/src/oss/javascript/integrations/stores/ioredis_storage.mdx +++ b/src/oss/javascript/integrations/stores/ioredis_storage.mdx @@ -18,4 +18,4 @@ import IoredisStorage from "/snippets/javascript-integrations/examples/stores/io ## Related -- [Key-value store conceptual guide](/oss/concepts/key_value_stores) +- [Key-value store conceptual guide](/oss/integrations/stores) diff --git a/src/oss/javascript/integrations/stores/upstash_redis_storage.mdx b/src/oss/javascript/integrations/stores/upstash_redis_storage.mdx index 89bbd43a94..0c520d619d 100644 --- a/src/oss/javascript/integrations/stores/upstash_redis_storage.mdx +++ b/src/oss/javascript/integrations/stores/upstash_redis_storage.mdx @@ -18,4 +18,4 @@ import UpstashRedisStorage from "/snippets/javascript-integrations/examples/stor ## Related -- [Key-value store conceptual guide](/oss/concepts/key_value_stores) +- [Key-value store conceptual guide](/oss/integrations/stores) diff --git a/src/oss/javascript/integrations/stores/vercel_kv_storage.mdx b/src/oss/javascript/integrations/stores/vercel_kv_storage.mdx index a21f4a33a0..5e93f3c007 100644 --- a/src/oss/javascript/integrations/stores/vercel_kv_storage.mdx +++ b/src/oss/javascript/integrations/stores/vercel_kv_storage.mdx @@ -18,4 +18,4 @@ import VercelKvStorage from "/snippets/javascript-integrations/examples/stores/v ## Related -- [Key-value store conceptual guide](/oss/concepts/key_value_stores) +- [Key-value store conceptual guide](/oss/integrations/stores) diff --git a/src/oss/javascript/integrations/tools/connery.mdx b/src/oss/javascript/integrations/tools/connery.mdx index 363b3446f2..3f4e3d191f 100644 --- a/src/oss/javascript/integrations/tools/connery.mdx +++ b/src/oss/javascript/integrations/tools/connery.mdx @@ -11,7 +11,7 @@ Using this tool, you can integrate individual Connery Action into your LangChain **If you want to use more than one Connery Action in your agent,** -check out the [Connery Toolkit](/oss/integrations/toolkits/connery) documentation. +check out the [Connery Toolkit](/oss/integrations/tools/connery_toolkit) documentation. ## What is Connery? diff --git a/src/oss/javascript/integrations/tools/index.mdx b/src/oss/javascript/integrations/tools/index.mdx index 92572f0442..2f801d1e6a 100644 --- a/src/oss/javascript/integrations/tools/index.mdx +++ b/src/oss/javascript/integrations/tools/index.mdx @@ -4,7 +4,7 @@ title: Tools and Toolkits [Tools](/oss/langchain/tools) are utilities designed to be called by a model: their inputs are designed to be generated by models, and their outputs are designed to be passed back to models. -A [toolkit](/oss/langchain/tools#toolkits) is a collection of tools meant to be used together. For a list of toolkit integrations, see [this page](/oss/integrations/toolkits/). +A [toolkit](/oss/langchain/tools#toolkits) is a collection of tools meant to be used together. If you'd like to write your own tool, see [this how-to](/oss/langchain/tools#customize-tool-properties). If you'd like to contribute an integration, see [Contributing integrations](/oss/contributing#add-a-new-integration). diff --git a/src/oss/javascript/integrations/tools/mcp_toolbox.mdx b/src/oss/javascript/integrations/tools/mcp_toolbox.mdx index b4b474a405..938f14e05d 100644 --- a/src/oss/javascript/integrations/tools/mcp_toolbox.mdx +++ b/src/oss/javascript/integrations/tools/mcp_toolbox.mdx @@ -11,8 +11,6 @@ started](https://googleapis.github.io/genai-toolbox/getting-started/local_quicks Toolbox, see the [documentation](https://googleapis.github.io/genai-toolbox/getting-started/introduction/). -![architecture](./assets/mcp_db_toolbox.png) - ### Configure and deploy Toolbox is an open source server that you deploy and manage yourself. For more diff --git a/src/oss/langchain/human-in-the-loop.mdx b/src/oss/langchain/human-in-the-loop.mdx index d9d77f3e78..214690cb7a 100644 --- a/src/oss/langchain/human-in-the-loop.mdx +++ b/src/oss/langchain/human-in-the-loop.mdx @@ -6,7 +6,7 @@ import AlphaCallout from '/snippets/alpha-lc-callout.mdx'; -The Human-in-the-Loop (HITL) middleware lets you add human oversight to agent tool calls. +The Human-in-the-Loop (HITL) middleware lets you add human oversight to agent tool calls. When a model proposes an action that might require review — for example, writing to a file or executing SQL — the middleware can pause execution and wait for a decision. It does this by checking each tool call against a configurable policy. If intervention is needed, the middleware issues an @[interrupt] that halts execution. The graph state is saved using LangGraph’s [persistence layer](/oss/langgraph/persistence), so execution can pause safely and resume later. @@ -40,7 +40,7 @@ You configure it with a mapping of tool actions to the response types that are a :::python ```python -from langchain.agents import create_agent +from langchain.agents import create_agent from langchain.agents.middleware import HumanInTheLoopMiddleware # [!code highlight] from langgraph.checkpoint.memory import InMemorySaver # [!code highlight] @@ -109,7 +109,7 @@ const agent = createAgent({ In production, use a persistent checkpointer like @[AsyncPostgresSaver]. For testing or prototyping, use @[InMemorySaver]. When invoking the agent, pass a `config` that includes the **thread ID** to associate execution with a conversation thread. - See the [LangGraph human-in-the-loop documentation](/oss/langgraph/human-in-the-loop) for details. + See the [LangGraph human-in-the-loop documentation](/oss/langgraph/add-human-in-the-loop) for details. @@ -283,11 +283,11 @@ await agent.invoke( resume: [ { type: "edit", - // Tool name to call. + // Tool name to call. // Will usually be the same as the original action. - action: "new_tool_name", + action: "new_tool_name", // Arguments to pass to the tool. - args: { key1: "new_value", key2: "original_value" }, + args: { key1: "new_value", key2: "original_value" }, } ] }), diff --git a/src/oss/langgraph/memory.mdx b/src/oss/langgraph/memory.mdx index 1e6e9a3c56..6fb0f9c8f3 100644 --- a/src/oss/langgraph/memory.mdx +++ b/src/oss/langgraph/memory.mdx @@ -85,7 +85,7 @@ Regardless of memory management approach, the central point is that the agent wi [Episodic memory](https://en.wikipedia.org/wiki/Episodic_memory), in both humans and AI agents, involves recalling past events or actions. The [CoALA paper](https://arxiv.org/pdf/2309.02427) frames this well: facts can be written to semantic memory, whereas *experiences* can be written to episodic memory. For AI agents, episodic memory is often used to help an agent remember how to accomplish a task. :::python -In practice, episodic memories are often implemented through [few-shot example prompting](https://python.langchain.com/docs/concepts/few_shot_prompting/), where agents learn from past sequences to perform tasks correctly. Sometimes it's easier to "show" than "tell" and LLMs learn well from examples. Few-shot learning lets you ["program"](https://x.com/karpathy/status/1627366413840322562) your LLM by updating the prompt with input-output examples to illustrate the intended behavior. While various [best-practices](https://python.langchain.com/docs/concepts/#1-generating-examples) can be used to generate few-shot examples, often the challenge lies in selecting the most relevant examples based on user input. +In practice, episodic memories are often implemented through [few-shot example prompting](/langsmith/create-few-shot-evaluators), where agents learn from past sequences to perform tasks correctly. Sometimes it's easier to "show" than "tell" and LLMs learn well from examples. Few-shot learning lets you ["program"](https://x.com/karpathy/status/1627366413840322562) your LLM by updating the prompt with input-output examples to illustrate the intended behavior. While various [best-practices](https://python.langchain.com/docs/concepts/#1-generating-examples) can be used to generate few-shot examples, often the challenge lies in selecting the most relevant examples based on user input. ::: :::js diff --git a/src/oss/python/integrations/chat/anthropic.mdx b/src/oss/python/integrations/chat/anthropic.mdx index 3c6333fc40..232efcee1d 100644 --- a/src/oss/python/integrations/chat/anthropic.mdx +++ b/src/oss/python/integrations/chat/anthropic.mdx @@ -334,7 +334,7 @@ print(json.dumps(response.content_blocks, indent=2)) ## Prompt caching -Anthropic supports [caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching) of [elements of your prompts](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#what-can-be-cached), including messages, tool definitions, tool results, images and documents. This allows you to re-use large documents, instructions, [few-shot documents](/oss/concepts/few_shot_prompting/), and other data to reduce latency and costs. +Anthropic supports [caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching) of [elements of your prompts](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#what-can-be-cached), including messages, tool definitions, tool results, images and documents. This allows you to re-use large documents, instructions, [few-shot documents](/langsmith/create-few-shot-evaluators), and other data to reduce latency and costs. To enable caching on an element of a prompt, mark its associated content block using the `cache_control` key. See examples below: @@ -476,7 +476,7 @@ Prompt caching can be used in [multi-turn conversations](https://docs.anthropic. We can enable incremental caching by marking the final message with `cache_control`. Claude will automatically use the longest previously-cached prefix for follow-up messages. -Below, we implement a simple chatbot that incorporates this feature. We follow the LangChain [chatbot tutorial](/oss/tutorials/chatbot/), but add a custom [reducer](/oss/langgraph/graph-api#reducers) that automatically marks the last content block in each user message with `cache_control`. See below: +Below, we implement a simple chatbot that incorporates this feature. We follow the LangChain [chatbot tutorial](/oss/langchain/quickstart), but add a custom [reducer](/oss/langgraph/graph-api#reducers) that automatically marks the last content block in each user message with `cache_control`. See below: ```python import requests diff --git a/src/oss/python/integrations/chat/bedrock.mdx b/src/oss/python/integrations/chat/bedrock.mdx index 00d6bfc3a8..4fe9444d22 100644 --- a/src/oss/python/integrations/chat/bedrock.mdx +++ b/src/oss/python/integrations/chat/bedrock.mdx @@ -197,7 +197,7 @@ ai_msg.content_blocks ## Prompt caching -Bedrock supports [caching](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html) of elements of your prompts, including messages and tools. This allows you to re-use large documents, instructions, [few-shot documents](/oss/concepts/few_shot_prompting/), and other data to reduce latency and costs. +Bedrock supports [caching](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html) of elements of your prompts, including messages and tools. This allows you to re-use large documents, instructions, [few-shot documents](/langsmith/create-few-shot-evaluators), and other data to reduce latency and costs. **Not all models support prompt caching. See supported models [here](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html#prompt-caching-models).** diff --git a/src/oss/python/integrations/chat/cohere.mdx b/src/oss/python/integrations/chat/cohere.mdx index b36934c456..c5f68345eb 100644 --- a/src/oss/python/integrations/chat/cohere.mdx +++ b/src/oss/python/integrations/chat/cohere.mdx @@ -77,25 +77,6 @@ chat.batch([messages]) [AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-8d6fade2-1b39-4e31-ab23-4be622dd0027-0')] ``` -## Chaining - -You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/oss/concepts/lcel) - -```python -from langchain_core.prompts import ChatPromptTemplate - -prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}") -chain = prompt | chat -``` - -```python -chain.invoke({"topic": "bears"}) -``` - -```output -AIMessage(content='What color socks do bears wear?\n\nThey don’t wear socks, they have bear feet. \n\nHope you laughed! If not, maybe this will help: laughter is the best medicine, and a good sense of humor is infectious!', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, id='run-ef7f9789-0d4d-43bf-a4f7-f2a0e27a5320-0') -``` - ## Tool calling Cohere supports tool calling functionalities! diff --git a/src/oss/python/integrations/chat/databricks.mdx b/src/oss/python/integrations/chat/databricks.mdx index b6024687de..4832680662 100644 --- a/src/oss/python/integrations/chat/databricks.mdx +++ b/src/oss/python/integrations/chat/databricks.mdx @@ -307,7 +307,7 @@ messages = [{"role": "user", "content": "What is the current temperature of Chic print(model.invoke(messages)) ``` -See [Databricks Unity Catalog](docs/integrations/tools/databricks.ipynb) about how to use UC functions in chains. +See [Databricks Unity Catalog](/oss/integrations/tools/databricks) about how to use UC functions in chains. ## API reference diff --git a/src/oss/python/integrations/chat/google_generative_ai.mdx b/src/oss/python/integrations/chat/google_generative_ai.mdx index 9f18e1abd4..e624bf6278 100644 --- a/src/oss/python/integrations/chat/google_generative_ai.mdx +++ b/src/oss/python/integrations/chat/google_generative_ai.mdx @@ -273,8 +273,6 @@ image_base64 = _get_image_base64(response) display(Image(data=base64.b64decode(image_base64), width=300)) ``` -You can also use LangGraph to manage the conversation history for you as in [this tutorial](/oss/tutorials/chatbot/). - ## Tool Calling You can equip the model with tools to call. diff --git a/src/oss/python/integrations/chat/greennode.mdx b/src/oss/python/integrations/chat/greennode.mdx index 0311eb63e0..ecd9936031 100644 --- a/src/oss/python/integrations/chat/greennode.mdx +++ b/src/oss/python/integrations/chat/greennode.mdx @@ -4,7 +4,7 @@ title: ChatGreenNode >[GreenNode](https://greennode.ai/) is a global AI solutions provider and a **NVIDIA Preferred Partner**, delivering full-stack AI capabilities—from infrastructure to application—for enterprises across the US, MENA, and APAC regions. Operating on **world-class infrastructure** (LEED Gold, TIA‑942, Uptime Tier III), GreenNode empowers enterprises, startups, and researchers with a comprehensive suite of AI services -This page will help you get started with GreenNode Serverless AI [chat models](../../concepts/chat_models). For detailed documentation of all ChatGreenNode features and configurations head to the [API reference](https://python.langchain.com/api_reference/greennode/chat_models/langchain_greennode.chat_models.ChatGreenNode.html). +This page will help you get started with GreenNode Serverless AI [chat models](/oss/langchain/models). For detailed documentation of all ChatGreenNode features and configurations head to the [API reference](https://python.langchain.com/api_reference/greennode/chat_models/langchain_greennode.chat_models.ChatGreenNode.html). [GreenNode AI](https://greennode.ai/) offers an API to query [20+ leading open-source models](https://aiplatform.console.greennode.ai/models) @@ -18,7 +18,7 @@ This page will help you get started with GreenNode Serverless AI [chat models](. ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | diff --git a/src/oss/python/integrations/chat/groq.mdx b/src/oss/python/integrations/chat/groq.mdx index d53f2bac87..f81fb158bc 100644 --- a/src/oss/python/integrations/chat/groq.mdx +++ b/src/oss/python/integrations/chat/groq.mdx @@ -2,7 +2,7 @@ title: ChatGroq --- -This will help you get started with Groq [chat models](../../concepts/chat_models). For detailed documentation of all ChatGroq features and configurations head to the [API reference](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html). For a list of all Groq models, visit this [link](https://console.groq.com/docs/models?utm_source=langchain). +This will help you get started with Groq [chat models](/oss/langchain/models). For detailed documentation of all ChatGroq features and configurations head to the [API reference](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html). For a list of all Groq models, visit this [link](https://console.groq.com/docs/models?utm_source=langchain). ## Overview @@ -14,7 +14,7 @@ This will help you get started with Groq [chat models](../../concepts/chat_model ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | @@ -102,7 +102,7 @@ J'aime la programmation. ## Chaining -We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so: +We can [chain](/oss/python/how-to/sequence/) our model with a prompt template like so: ```python from langchain_core.prompts import ChatPromptTemplate diff --git a/src/oss/python/integrations/chat/index.mdx b/src/oss/python/integrations/chat/index.mdx index f1de097dd6..0b576d6e3b 100644 --- a/src/oss/python/integrations/chat/index.mdx +++ b/src/oss/python/integrations/chat/index.mdx @@ -372,14 +372,6 @@ the feature. cta="View guide" /> - - -**You can use [LangGraph](https://langchain-ai.github.io/langgraph/) to manage conversational threads for you in a variety of backends, including in-memory and Postgres. See [this tutorial](/oss/tutorials/chatbot/) to get started.** +**You can use [LangGraph](https://langchain-ai.github.io/langgraph/) to manage conversational threads for you in a variety of backends, including in-memory and Postgres. See [this tutorial](/oss/langgraph/quickstart) to get started.** @@ -1017,11 +1017,11 @@ AIMessage(content="J'adore la programmation.", additional_kwargs={'refusal': Non ## Multimodal Inputs (images, PDFs, audio) -OpenAI has models that support multimodal inputs. You can pass in images, PDFs, or audio to these models. For more information on how to do this in LangChain, head to the [multimodal inputs](/oss/how-to/multimodal_inputs) docs. +OpenAI has models that support multimodal inputs. You can pass in images, PDFs, or audio to these models. For more information on how to do this in LangChain, head to the [multimodal inputs](/oss/langchain/messages#multimodal) docs. You can see the list of models that support different modalities in [OpenAI's documentation](https://platform.openai.com/docs/models). -For all modalities, LangChain supports both its [cross-provider standard](/oss/concepts/multimodality/#multimodality-in-chat-models) as well as OpenAI's native content-block format. +For all modalities, LangChain supports both its cross-provider standard as well as OpenAI's native content-block format. To pass multimodal data into `ChatOpenAI`, create a [content block](/oss/langchain/messages/) containing the data and incorporate it into a message, e.g., as below: @@ -1043,7 +1043,7 @@ See below for examples of content blocks. -Refer to examples in the how-to guide [here](/oss/langchain/messages#multimodal#images). +Refer to examples in the how-to guide [here](/oss/langchain/messages#multimodal). URLs: diff --git a/src/oss/python/integrations/chat/perplexity.mdx b/src/oss/python/integrations/chat/perplexity.mdx index 7891bc3c92..da5d6a89b9 100644 --- a/src/oss/python/integrations/chat/perplexity.mdx +++ b/src/oss/python/integrations/chat/perplexity.mdx @@ -3,7 +3,7 @@ title: ChatPerplexity --- -This page will help you get started with Perplexity [chat models](../../concepts/chat_models). For detailed documentation of all `ChatPerplexity` features and configurations head to the [API reference](https://python.langchain.com/api_reference/perplexity/chat_models/langchain_perplexity.chat_models.ChatPerplexity.html). +This page will help you get started with Perplexity [chat models](/oss/langchain/models). For detailed documentation of all `ChatPerplexity` features and configurations head to the [API reference](https://python.langchain.com/api_reference/perplexity/chat_models/langchain_perplexity.chat_models.ChatPerplexity.html). ## Overview @@ -15,7 +15,7 @@ This page will help you get started with Perplexity [chat models](../../concepts ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | diff --git a/src/oss/python/integrations/chat/qwen.mdx b/src/oss/python/integrations/chat/qwen.mdx index c36991db46..949979b2de 100644 --- a/src/oss/python/integrations/chat/qwen.mdx +++ b/src/oss/python/integrations/chat/qwen.mdx @@ -2,7 +2,7 @@ title: ChatQwen --- -This will help you get started with Qwen [chat models](../../concepts/chat_models). For detailed documentation of all ChatQwen features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/). +This will help you get started with Qwen [chat models](/oss/langchain/models). For detailed documentation of all ChatQwen features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/). ## Overview @@ -14,7 +14,7 @@ This will help you get started with Qwen [chat models](../../concepts/chat_model ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ✅ | ✅ | ✅ |✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | @@ -79,7 +79,7 @@ AIMessage(content="J'adore la programmation.", additional_kwargs={}, response_me ## Chaining -We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so: +We can [chain](/oss/python/how-to/sequence/) our model with a prompt template like so: ```python from langchain_core.prompts import ChatPromptTemplate diff --git a/src/oss/python/integrations/chat/qwq.mdx b/src/oss/python/integrations/chat/qwq.mdx index b32089c267..484cf76407 100644 --- a/src/oss/python/integrations/chat/qwq.mdx +++ b/src/oss/python/integrations/chat/qwq.mdx @@ -2,7 +2,7 @@ title: ChatQwQ --- -This will help you get started with QwQ [chat models](../../concepts/chat_models). For detailed documentation of all ChatQwQ features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/). +This will help you get started with QwQ [chat models](/oss/langchain/models). For detailed documentation of all ChatQwQ features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/). ## Overview @@ -14,7 +14,7 @@ This will help you get started with QwQ [chat models](../../concepts/chat_models ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ✅ | ✅ | ✅ |✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | @@ -79,7 +79,7 @@ AIMessage(content="J'aime la programmation.", additional_kwargs={'reasoning_cont ## Chaining -We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so: +We can [chain](/oss/python/how-to/sequence/) our model with a prompt template like so: ```python from langchain_core.prompts import ChatPromptTemplate diff --git a/src/oss/python/integrations/chat/reka.mdx b/src/oss/python/integrations/chat/reka.mdx index cf69f07756..ad76d341c0 100644 --- a/src/oss/python/integrations/chat/reka.mdx +++ b/src/oss/python/integrations/chat/reka.mdx @@ -2,7 +2,7 @@ title: ChatReka --- -This guide provides a quick overview for getting started with Reka [chat models](../../concepts/chat_models). +This guide provides a quick overview for getting started with Reka [chat models](/oss/langchain/models). Reka has several chat models. You can find information about their latest models and their costs, context windows, and supported input types in the [Reka docs](https://docs.reka.ai/available-models). diff --git a/src/oss/python/integrations/chat/runpod.mdx b/src/oss/python/integrations/chat/runpod.mdx index 43beebfd00..f26492a66f 100644 --- a/src/oss/python/integrations/chat/runpod.mdx +++ b/src/oss/python/integrations/chat/runpod.mdx @@ -170,7 +170,7 @@ The availability of advanced features depends **heavily** on the specific implem | [Tool calling](/oss/langchain/tools) | ❌ | ✅ | Requires handler to process tool definitions and return tool calls (e.g., OpenAI format). Integration needs parsing logic. | | [Structured output](/oss/how-to/structured_output) | ❌ | ✅ | Requires handler support for forcing structured output (JSON mode, function calling). Integration needs parsing logic. | | JSON mode | ❌ | ✅ | Requires handler to accept a `json_mode` parameter (or similar) and guarantee JSON output. | -| [Image input](/oss/how-to/multimodal_inputs) | ❌ | ✅ | Requires multimodal handler accepting image data (e.g., base64). Integration does not support multimodal messages. | +| [Image input](/oss/langchain/messages#multimodal) | ❌ | ✅ | Requires multimodal handler accepting image data (e.g., base64). Integration does not support multimodal messages. | | Audio input | ❌ | ✅ | Requires handler accepting audio data. Integration does not support audio messages. | | Video input | ❌ | ✅ | Requires handler accepting video data. Integration does not support video messages. | | [Token-level streaming](/oss/langchain/streaming) | ✅ (Simulated) | ✅ | Polls `/stream`. Requires handler to populate `stream` list in status response with token chunks (e.g., `[{"output": "token"}]`). True low-latency streaming not built-in. | diff --git a/src/oss/python/integrations/chat/together.mdx b/src/oss/python/integrations/chat/together.mdx index e5c5ac4c45..74bed038fd 100644 --- a/src/oss/python/integrations/chat/together.mdx +++ b/src/oss/python/integrations/chat/together.mdx @@ -3,7 +3,7 @@ title: ChatTogether --- -This page will help you get started with Together AI [chat models](../../concepts/chat_models). For detailed documentation of all ChatTogether features and configurations, head to the [API reference](https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html). +This page will help you get started with Together AI [chat models](/oss/langchain/models). For detailed documentation of all ChatTogether features and configurations, head to the [API reference](https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html). [Together AI](https://www.together.ai/) offers an API to query [50+ leading open-source models](https://docs.together.ai/docs/chat-models) @@ -17,7 +17,7 @@ This page will help you get started with Together AI [chat models](../../concept ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | @@ -97,7 +97,7 @@ J'adore la programmation. ## Chaining -We can [chain](../../how_to/sequence.ipynb) our model with a prompt template as follows: +We can [chain](/oss/python/how-to/sequence/) our model with a prompt template as follows: ```python from langchain_core.prompts import ChatPromptTemplate diff --git a/src/oss/python/integrations/chat/xai.mdx b/src/oss/python/integrations/chat/xai.mdx index 682d586723..a51e51461c 100644 --- a/src/oss/python/integrations/chat/xai.mdx +++ b/src/oss/python/integrations/chat/xai.mdx @@ -3,7 +3,7 @@ title: ChatXAI --- -This page will help you get started with xAI [chat models](../../concepts/chat_models). For detailed documentation of all `ChatXAI` features and configurations, head to the [API reference](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html). +This page will help you get started with xAI [chat models](/oss/langchain/models). For detailed documentation of all `ChatXAI` features and configurations, head to the [API reference](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html). [xAI](https://console.x.ai/) offers an API to interact with Grok models. @@ -17,7 +17,7 @@ This page will help you get started with xAI [chat models](../../concepts/chat_m ### Model features -| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) | +| [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output) | JSON mode | [Image input](/oss/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/langchain/streaming#llm-tokens) | Native async | [Token usage](/oss/langchain/models#token-usage) | [Logprobs](/oss/langchain/models#log-probabilities) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | @@ -97,7 +97,7 @@ J'adore programmer. ## Chaining -We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so: +We can [chain](/oss/python/how-to/sequence/) our model with a prompt template like so: ```python from langchain_core.prompts import ChatPromptTemplate diff --git a/src/oss/python/integrations/document_loaders/docugami.mdx b/src/oss/python/integrations/document_loaders/docugami.mdx index 4d07f62853..525813dc53 100644 --- a/src/oss/python/integrations/document_loaders/docugami.mdx +++ b/src/oss/python/integrations/document_loaders/docugami.mdx @@ -72,7 +72,7 @@ You can control chunking behavior by setting the following properties on the `Do 1. You can set min and max chunk size, which the system tries to adhere to with minimal truncation. You can set `loader.min_text_length` and `loader.max_text_length` to control these. 2. By default, only the text for chunks is returned. However, Docugami's XML knowledge graph has additional rich information including semantic tags for entities inside the chunk. Set `loader.include_xml_tags = True` if you want the additional xml metadata on the returned chunks. -3. In addition, you can set `loader.parent_hierarchy_levels` if you want Docugami to return parent chunks in the chunks it returns. The child chunks point to the parent chunks via the `loader.parent_id_key` value. This is useful e.g. with the [MultiVector Retriever](/oss/how-to/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. See detailed example later in this notebook. +3. In addition, you can set `loader.parent_hierarchy_levels` if you want Docugami to return parent chunks in the chunks it returns. The child chunks point to the parent chunks via the `loader.parent_id_key` value. This is useful e.g. with the MultiVector Retriever for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. See detailed example later in this notebook. ```python loader.min_text_length = 64 @@ -261,7 +261,7 @@ This time the answer is correct, since the self-querying retriever created a fil # Advanced Topic: Small-to-Big Retrieval with Document Knowledge Graph Hierarchy -Documents are inherently semi-structured and the DocugamiLoader is able to navigate the semantic and structural contours of the document to provide parent chunk references on the chunks it returns. This is useful e.g. with the [MultiVector Retriever](/oss/how-to/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. +Documents are inherently semi-structured and the DocugamiLoader is able to navigate the semantic and structural contours of the document to provide parent chunk references on the chunks it returns. This is useful e.g. with the MultiVector Retriever for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. To get parent chunk references, you can set `loader.parent_hierarchy_levels` to a non-zero value. diff --git a/src/oss/python/integrations/document_loaders/index.mdx b/src/oss/python/integrations/document_loaders/index.mdx index 8e0a022d5e..fcb3983628 100644 --- a/src/oss/python/integrations/document_loaders/index.mdx +++ b/src/oss/python/integrations/document_loaders/index.mdx @@ -47,7 +47,6 @@ The below document loaders allow you to load webpages. | [Docling](/oss/integrations/document_loaders/docling) | Uses Docling to load and parse web pages | Package | | [Hyperbrowser](/oss/integrations/document_loaders/hyperbrowser) | Platform for running and scaling headless browsers, can be used to scrape/crawl any site | API | | [AgentQL](/oss/integrations/document_loaders/agentql) | Web interaction and structured data extraction from any web page using an AgentQL query or a Natural Language prompt | API | -| [Oxylabs](/oss/integrations/document_loaders/oxylabs) | Web intelligence platform enabling the access to various data sources | API | ### PDFs @@ -146,191 +145,188 @@ The below document loaders allow you to load data from common data formats. ## All document loaders - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/src/oss/python/integrations/document_loaders/tomarkdown.mdx b/src/oss/python/integrations/document_loaders/tomarkdown.mdx index af6b02f058..47b11f6a15 100644 --- a/src/oss/python/integrations/document_loaders/tomarkdown.mdx +++ b/src/oss/python/integrations/document_loaders/tomarkdown.mdx @@ -76,14 +76,6 @@ note These docs focus on the Python LangChain library. [Head here](https://js.langchain.com) for docs on the JavaScript LangChain library. -## LangChain Expression Language (LCEL) [​](\#langchain-expression-language-lcel "Direct link to LangChain Expression Language (LCEL)") - -LCEL is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains. - -- **[Overview](/oss/concepts/lcel)**: LCEL and its benefits -- **[Interface](/oss/concepts/runnables)**: The standard interface for LCEL objects -- **[How-to](/docs/expression_language/how_to)**: Key features of LCEL -- **[Cookbook](/docs/expression_language/cookbook)**: Example code for accomplishing common tasks ## Modules [​](\#modules "Direct link to Modules") diff --git a/src/oss/python/integrations/graphs/memgraph.mdx b/src/oss/python/integrations/graphs/memgraph.mdx index 745e7ea309..5cd67490bf 100644 --- a/src/oss/python/integrations/graphs/memgraph.mdx +++ b/src/oss/python/integrations/graphs/memgraph.mdx @@ -285,7 +285,7 @@ The generated Cypher query looks fine, but we didn't receive any information in #### Prompt refinement -To address this, we can adjust the initial Cypher prompt of the QA chain. This involves adding guidance to the LLM on how users can refer to specific platforms, such as PS5 in our case. We achieve this using the LangChain [PromptTemplate](/docs/how_to#prompt-templates), creating a modified initial prompt. This modified prompt is then supplied as an argument to our refined `MemgraphQAChain` instance. +To address this, we can adjust the initial Cypher prompt of the QA chain. This involves adding guidance to the LLM on how users can refer to specific platforms, such as PS5 in our case. We achieve this using the LangChain PromptTemplate, creating a modified initial prompt. This modified prompt is then supplied as an argument to our refined `MemgraphQAChain` instance. ```python MEMGRAPH_GENERATION_TEMPLATE = """Your task is to directly translate natural language inquiry into precise and executable Cypher query for Memgraph database. @@ -409,11 +409,9 @@ graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL") graph.add_graph_documents(graph_documents) ``` -Here is how the graph looks like in Memgraph Lab (check on `localhost:3000`): - -![memgraph-kg](../../../static/img/memgraph_kg.png) - -In case you tried this out and got a different graph, that is expected behavior. The graph construction process is non-deterministic, since LLM which is used to generate nodes and relationships from unstructured data in non-deterministic. + +The graph construction process is non-deterministic, since LLM which is used to generate nodes and relationships from unstructured data in non-deterministic. + ### Additional options @@ -438,10 +436,6 @@ Nodes:[Node(id='Charles Robert Darwin', type='Person', properties={}), Node(id=' Relationships:[Relationship(source=Node(id='Charles Robert Darwin', type='Person', properties={}), target=Node(id='English', type='Nationality', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Charles Robert Darwin', type='Person', properties={}), target=Node(id='Evolutionary Biology', type='Concept', properties={}), type='INVOLVED_IN', properties={}), Relationship(source=Node(id='Charles Robert Darwin', type='Person', properties={}), target=Node(id='Natural Selection', type='Concept', properties={}), type='INVOLVED_IN', properties={}), Relationship(source=Node(id='Charles Robert Darwin', type='Person', properties={}), target=Node(id='Alfred Russel Wallace', type='Person', properties={}), type='COLLABORATES_WITH', properties={})] ``` -Here's how the graph would like in such case: - -![memgraph-kg-2](../../../static/img/memgraph_kg_2.png) - Your graph can also have `__Entity__` labels on all nodes which will be indexed for faster retrieval. ```python @@ -454,10 +448,6 @@ graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL") graph.add_graph_documents(graph_documents, baseEntityLabel=True) ``` -Here's how the graph would look like: - -![memgraph-kg-3](../../../static/img/memgraph_kg_3.png) - There is also an option to include the source of the information that's obtained in the graph. To do that, set `include_source` to `True` and then the source document is stored and it is linked to the nodes in the graph using the `MENTIONS` relationship. ```python @@ -470,10 +460,6 @@ graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL") graph.add_graph_documents(graph_documents, include_source=True) ``` -The constructed graph would look like this: - -![memgraph-kg-4](../../../static/img/memgraph_kg_4.png) - Notice how the content of the source is stored and `id` property is generated since the document didn't have any `id`. You can combine having both `__Entity__` label and document source. Still, be aware that both take up memory, especially source included due to long strings for content. diff --git a/src/oss/python/integrations/llms/aimlapi.mdx b/src/oss/python/integrations/llms/aimlapi.mdx index a1ed777024..c4372d41dd 100644 --- a/src/oss/python/integrations/llms/aimlapi.mdx +++ b/src/oss/python/integrations/llms/aimlapi.mdx @@ -3,7 +3,7 @@ title: AimlapiLLM --- -**You are currently on a page documenting the use of AI/ML API models as [text completion models](/oss/concepts/text_llms). Many of the latest and most popular AI/ML API models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of AI/ML API models as text completion models. Many of the latest and most popular AI/ML API models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/aimlapi). @@ -93,23 +93,6 @@ for chunk in llm.stream("List top 5 programming languages in 2025 with reasons." print(chunk, end="", flush=True) ``` -## Chaining - -You can easily combine the LLM with a prompt template for structured inputs using [LCEL](/oss/concepts/lcel): - -```python -from langchain_core.prompts import PromptTemplate - -prompt = PromptTemplate.from_template("Tell me a joke about {topic}") -chain = prompt | llm - -chain.invoke({"topic": "bears"}) -``` - -```output -"Why do bears have fur coats? Because they'd look silly in sweaters!" -``` - ## API reference For detailed documentation of all AimlapiLLM features and configurations head to the [API reference](https://python.langchain.com/api_reference/aimlapi/llms/langchain_aimlapi.llms.AimlapiLLM.html). diff --git a/src/oss/python/integrations/llms/anthropic.mdx b/src/oss/python/integrations/llms/anthropic.mdx index 72b6e1a6fb..20633596df 100644 --- a/src/oss/python/integrations/llms/anthropic.mdx +++ b/src/oss/python/integrations/llms/anthropic.mdx @@ -4,7 +4,7 @@ title: AnthropicLLM -**You are currently on a page documenting the use of Anthropic legacy Claude 2 models as [text completion models](/oss/concepts/text_llms). The latest and most popular Anthropic models are [chat completion models](/oss/langchain/models), and the text completion models have been deprecated.** +**You are currently on a page documenting the use of Anthropic legacy Claude 2 models as text completion models. The latest and most popular Anthropic models are [chat completion models](/oss/langchain/models), and the text completion models have been deprecated.** You are probably looking for [this page instead](/oss/integrations/chat/anthropic/). diff --git a/src/oss/python/integrations/llms/azure_openai.mdx b/src/oss/python/integrations/llms/azure_openai.mdx index 5982f58725..d37232e0a2 100644 --- a/src/oss/python/integrations/llms/azure_openai.mdx +++ b/src/oss/python/integrations/llms/azure_openai.mdx @@ -3,7 +3,7 @@ title: Azure OpenAI --- -**You are currently on a page documenting the use of Azure OpenAI [text completion models](/oss/concepts/text_llms). The latest and most popular Azure OpenAI models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Azure OpenAI text completion models. The latest and most popular Azure OpenAI models are [chat completion models](/oss/langchain/models).** Unless you are specifically using `gpt-3.5-turbo-instruct`, you are probably looking for [this page instead](/oss/integrations/chat/azure_chat_openai/). diff --git a/src/oss/python/integrations/llms/bedrock.mdx b/src/oss/python/integrations/llms/bedrock.mdx index c0d4f31826..62b64c6329 100644 --- a/src/oss/python/integrations/llms/bedrock.mdx +++ b/src/oss/python/integrations/llms/bedrock.mdx @@ -3,7 +3,7 @@ title: Bedrock --- -**You are currently on a page documenting the use of Amazon Bedrock models as [text completion models](/oss/concepts/text_llms). Many popular models available on Bedrock are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Amazon Bedrock models as text completion models. Many popular models available on Bedrock are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/bedrock/). diff --git a/src/oss/python/integrations/llms/cohere.mdx b/src/oss/python/integrations/llms/cohere.mdx index 7e46bf1c7a..1f3cc57d10 100644 --- a/src/oss/python/integrations/llms/cohere.mdx +++ b/src/oss/python/integrations/llms/cohere.mdx @@ -3,7 +3,7 @@ title: Cohere --- -**You are currently on a page documenting the use of Cohere models as [text completion models](/oss/concepts/text_llms). Many popular Cohere models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Cohere models as text completion models. Many popular Cohere models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/cohere/). @@ -96,25 +96,6 @@ model.batch([message]) [" Who's there?"] ``` -## Chaining - -You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/oss/concepts/lcel) - -```python -from langchain_core.prompts import PromptTemplate - -prompt = PromptTemplate.from_template("Tell me a joke about {topic}") -chain = prompt | model -``` - -```python -chain.invoke({"topic": "bears"}) -``` - -```output -' Why did the teddy bear cross the road?\nBecause he had bear crossings.\n\nWould you like to hear another joke? ' -``` - ## API reference For detailed documentation of all `Cohere` llm features and configurations head to the API reference: [python.langchain.com/api_reference/community/llms/langchain_community.llms.cohere.Cohere.html](https://python.langchain.com/api_reference/community/llms/langchain_community.llms.cohere.Cohere.html) diff --git a/src/oss/python/integrations/llms/fireworks.mdx b/src/oss/python/integrations/llms/fireworks.mdx index da1f12c555..808670ebf7 100644 --- a/src/oss/python/integrations/llms/fireworks.mdx +++ b/src/oss/python/integrations/llms/fireworks.mdx @@ -3,7 +3,7 @@ title: Fireworks --- -**You are currently on a page documenting the use of Fireworks models as [text completion models](/oss/concepts/text_llms). Many popular Fireworks models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Fireworks models as text completion models. Many popular Fireworks models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/fireworks/). diff --git a/src/oss/python/integrations/llms/google_ai.mdx b/src/oss/python/integrations/llms/google_ai.mdx index 1153db49c6..248a9c311a 100644 --- a/src/oss/python/integrations/llms/google_ai.mdx +++ b/src/oss/python/integrations/llms/google_ai.mdx @@ -4,7 +4,7 @@ title: Google AI -**You are currently on a page documenting the use of Google models as [text completion models](/oss/concepts/text_llms). Many popular Google models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Google models as text completion models. Many popular Google models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/google_generative_ai/). diff --git a/src/oss/python/integrations/llms/google_vertex_ai_palm.mdx b/src/oss/python/integrations/llms/google_vertex_ai_palm.mdx index b114bad733..dd545bfbb4 100644 --- a/src/oss/python/integrations/llms/google_vertex_ai_palm.mdx +++ b/src/oss/python/integrations/llms/google_vertex_ai_palm.mdx @@ -3,7 +3,7 @@ title: Google Cloud Vertex AI --- -**You are currently on a page documenting the use of Google Vertex [text completion models](/oss/concepts/text_llms). Many Google models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Google Vertex text completion models. Many Google models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/google_vertex_ai_palm/). @@ -168,32 +168,6 @@ result "## Pros of Python\n\n* **Easy to learn:** Python's clear syntax and simple structure make it easy for beginners to pick up, even if they have no prior programming experience.\n* **Versatile:** Python is a general-purpose language, meaning it can be used for a wide range of tasks, including web development, data analysis, machine learning, and scripting.\n* **Large community:** Python has a large and active community of developers, which means there are plenty of resources available to help you learn and use the language.\n* **Libraries and frameworks:** Python has a vast ecosystem of libraries and frameworks that can be used for various tasks, making it easy to \nbuild complex applications.\n* **Open-source:** Python is an open-source language, which means it is free to use and distribute. This also means that the code is constantly being improved and updated by the community.\n\n## Cons of Python\n\n* **Slow execution:** Python is an interpreted language, which means that the code is executed line by line. This can make Python slower than compiled languages like C++ or Java.\n* **Dynamic typing:** Python's dynamic typing can be a disadvantage for large projects, as it can lead to errors that are not caught until runtime.\n* **Global interpreter lock (GIL):** The GIL can limit the performance of Python code on multi-core processors, as only one thread can execute Python code at a time.\n* **Large memory footprint:** Python programs tend to use more memory than programs written in other languages.\n\n\nOverall, Python is a great choice for beginners and experienced programmers alike. Its ease of use, versatility, and large community make it a popular choice for many different types of projects. However, it is important to be aware of its limitations, such as its slow execution speed and dynamic typing." ``` -You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/oss/concepts/lcel) - -```python -from langchain_core.prompts import PromptTemplate - -template = """Question: {question} - -Answer: Let's think step by step.""" -prompt = PromptTemplate.from_template(template) - -chain = prompt | model - -question = """ -I have five apples. I throw two away. I eat one. How many apples do I have left? -""" -print(chain.invoke({"question": question})) -``` - -```output -1. You start with 5 apples. -2. You throw away 2 apples, so you have 5 - 2 = 3 apples left. -3. You eat 1 apple, so you have 3 - 1 = 2 apples left. - -Therefore, you have 2 apples left. -``` - You can use different foundational models for specialized in different tasks. For an updated list of available models visit [VertexAI documentation](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/overview) diff --git a/src/oss/python/integrations/llms/index.mdx b/src/oss/python/integrations/llms/index.mdx index a9871eeb28..68a5015892 100644 --- a/src/oss/python/integrations/llms/index.mdx +++ b/src/oss/python/integrations/llms/index.mdx @@ -5,7 +5,7 @@ sidebar_position: 0 # LLMs -**You are currently on a page documenting the use of [text completion models](/oss/concepts/text_llms). Many of the latest and most popular models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of text completion models. Many of the latest and most popular models are [chat completion models](/oss/langchain/models).** Unless you are specifically using more advanced prompting techniques, you are probably looking for [this page instead](/oss/integrations/chat/). diff --git a/src/oss/python/integrations/llms/ollama.mdx b/src/oss/python/integrations/llms/ollama.mdx index 79c44b7389..97ee8f960b 100644 --- a/src/oss/python/integrations/llms/ollama.mdx +++ b/src/oss/python/integrations/llms/ollama.mdx @@ -3,7 +3,7 @@ title: Ollama --- -**You are currently on a page documenting the use of Ollama models as [text completion models](/oss/concepts/text_llms). Many popular Ollama models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Ollama models as text completion models. Many popular Ollama models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/ollama/). diff --git a/src/oss/python/integrations/llms/openai.mdx b/src/oss/python/integrations/llms/openai.mdx index 531bfcada3..3436754308 100644 --- a/src/oss/python/integrations/llms/openai.mdx +++ b/src/oss/python/integrations/llms/openai.mdx @@ -3,7 +3,7 @@ title: OpenAI --- -**You are currently on a page documenting the use of OpenAI [text completion models](/oss/concepts/text_llms). The latest and most popular OpenAI models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of OpenAI text completion models. The latest and most popular OpenAI models are [chat completion models](/oss/langchain/models).** Unless you are specifically using `gpt-3.5-turbo-instruct`, you are probably looking for [this page instead](/oss/integrations/chat/openai/). diff --git a/src/oss/python/integrations/llms/sambanovacloud.mdx b/src/oss/python/integrations/llms/sambanovacloud.mdx index 9380bd8836..e3ef7e68c6 100644 --- a/src/oss/python/integrations/llms/sambanovacloud.mdx +++ b/src/oss/python/integrations/llms/sambanovacloud.mdx @@ -5,7 +5,7 @@ title: SambaNovaCloud **[SambaNova](https://sambanova.ai/)'s [SambaNova Cloud](https://cloud.sambanova.ai/)** is a platform for performing inference with open-source models -**You are currently on a page documenting the use of SambaNovaCloud models as [text completion models](/oss/concepts/text_llms/). We recommend you to use the [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of SambaNovaCloud models as text completion models. We recommend you to use the [chat completion models](/oss/langchain/models).** You may be looking for [SambaNovaCloud Chat Models](/oss/integrations/chat/sambanova/) . diff --git a/src/oss/python/integrations/llms/sambastudio.mdx b/src/oss/python/integrations/llms/sambastudio.mdx index 2ddd0f3935..e9933b18d2 100644 --- a/src/oss/python/integrations/llms/sambastudio.mdx +++ b/src/oss/python/integrations/llms/sambastudio.mdx @@ -5,7 +5,7 @@ title: SambaStudio **[SambaNova](https://sambanova.ai/)'s** [Sambastudio](https://sambanova.ai/technology/full-stack-ai-platform) is a platform that allows you to train, run batch inference jobs, and deploy online inference endpoints to run open source models that you fine tuned yourself. -**You are currently on a page documenting the use of SambaStudio models as [text completion models](/oss/concepts/text_llms). We recommend you to use the [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of SambaStudio models as text completion models. We recommend you to use the [chat completion models](/oss/langchain/models).** You may be looking for [SambaStudio Chat Models](/oss/integrations/chat/sambastudio/) . diff --git a/src/oss/python/integrations/llms/solar.mdx b/src/oss/python/integrations/llms/solar.mdx index 0554dc0c6f..1104b2de9a 100644 --- a/src/oss/python/integrations/llms/solar.mdx +++ b/src/oss/python/integrations/llms/solar.mdx @@ -2,7 +2,7 @@ title: Solar --- -*This community integration is deprecated. You should use [`ChatUpstage`](../../chat/upstage) instead to access Solar LLM via the chat model connector.* +*This community integration is deprecated. You should use [`ChatUpstage`](/oss/integrations/chat/upstage) instead to access Solar LLM via the chat model connector.* ```python import os diff --git a/src/oss/python/integrations/llms/together.mdx b/src/oss/python/integrations/llms/together.mdx index e959aa5622..c47cc50692 100644 --- a/src/oss/python/integrations/llms/together.mdx +++ b/src/oss/python/integrations/llms/together.mdx @@ -3,7 +3,7 @@ title: Together AI --- -**You are currently on a page documenting the use of Together AI models as [text completion models](/oss/concepts/text_llms). Many popular Together AI models are [chat completion models](/oss/langchain/models).** +**You are currently on a page documenting the use of Together AI models as text completion models. Many popular Together AI models are [chat completion models](/oss/langchain/models).** You may be looking for [this page instead](/oss/integrations/chat/together/). diff --git a/src/oss/python/integrations/providers/all_providers.mdx b/src/oss/python/integrations/providers/all_providers.mdx index 89e38da0e0..706070481d 100644 --- a/src/oss/python/integrations/providers/all_providers.mdx +++ b/src/oss/python/integrations/providers/all_providers.mdx @@ -3061,35 +3061,35 @@ Browse the complete collection of integrations available for Python. LangChain P Custom AI chat integration platform. AI21 Labs' Jurassic models for conversation. Unified API for multiple chat models. Alibaba Cloud's model serving platform. Claude models for advanced reasoning. @@ -3097,7 +3097,7 @@ Browse the complete collection of integrations available for Python. LangChain P Function calling with Claude models. @@ -3105,7 +3105,7 @@ Browse the complete collection of integrations available for Python. LangChain P Microsoft Azure AI chat services. @@ -3113,7 +3113,7 @@ Browse the complete collection of integrations available for Python. LangChain P OpenAI models through Azure platform. @@ -3121,7 +3121,7 @@ Browse the complete collection of integrations available for Python. LangChain P Azure Machine Learning chat endpoints. @@ -3129,21 +3129,21 @@ Browse the complete collection of integrations available for Python. LangChain P Baichuan AI's Chinese language models. Baidu's Qianfan large model platform. Foundation models through Amazon Bedrock. @@ -3151,21 +3151,21 @@ Browse the complete collection of integrations available for Python. LangChain P Ultra-fast inference with Cerebras processors. AI models on Cloudflare's edge platform. Cohere's language models for conversation. @@ -3173,77 +3173,77 @@ Browse the complete collection of integrations available for Python. LangChain P Context-aware conversational AI. ByteDance's conversational AI platform. Real-time AI data platform. Foundation models on Databricks platform. Serverless inference for chat models. Advanced reasoning and coding models. Unified API for multiple chat providers. Baidu's ERNIE language model. Serverless AI inference platform. Optimized model serving platform. Fast inference for open-source models. @@ -3251,21 +3251,21 @@ Browse the complete collection of integrations available for Python. LangChain P Optimized serving engine for chat models. Interpretable AI chat models. Google's Gemini models for conversation. @@ -3273,7 +3273,7 @@ Browse the complete collection of integrations available for Python. LangChain P Enterprise AI platform with PaLM models. @@ -3281,28 +3281,28 @@ Browse the complete collection of integrations available for Python. LangChain P Route requests across multiple GPT providers. Private AI model training and chat. Sustainable AI computing platform. Ultra-fast inference with specialized hardware. @@ -3310,91 +3310,91 @@ Browse the complete collection of integrations available for Python. LangChain P Open-source models via Hugging Face. IBM's enterprise AI foundation models. Jina's conversational AI models. Real-time analytics with chat interface. Generative AI platform for chat models. Unified interface for 100+ chat APIs. Hosted Llama models via API. Edge computing for Llama models. Meta's Llama 2 chat models. Local inference with llama.cpp. Brazilian Portuguese conversational AI. Chinese AI company's chat models. Mistral's efficient language models. @@ -3402,77 +3402,77 @@ Browse the complete collection of integrations available for Python. LangChain P Apple's machine learning framework. Alibaba's model hub chat interface. Moonshot AI's conversational models. Naver's HyperCLOVA language models. AI cloud platform for chat models. Decentralized AI computing network. NVIDIA's foundation model endpoints. Oracle Cloud Infrastructure data science. Oracle's generative AI services. Efficient AI compute and model serving. Run large language models locally. @@ -3480,7 +3480,7 @@ Browse the complete collection of integrations available for Python. LangChain P GPT models and OpenAI's chat platform. @@ -3488,126 +3488,126 @@ Browse the complete collection of integrations available for Python. LangChain P Structured generation for language models. AI-powered search and reasoning. AI content moderation platform. Secure and compliant AI models. AI platform for model deployment. OpenAI with PromptLayer observability. Alibaba's Qwen language models. Alibaba's reasoning-focused model. Multimodal AI models from Reka. GPU cloud platform for chat models. AI platform with specialized hardware. SambaNova's enterprise AI platform. AI workflow and automation platform. AI models on Snowflake data platform. iFlytek's Spark language models. Conversation intelligence platform. Tencent's Hunyuan language models. Fast inference for open-source models. @@ -3615,77 +3615,77 @@ Browse the complete collection of integrations available for Python. LangChain P Alibaba's Tongyi Qianwen models. Document AI and chat models. Fast and memory-efficient inference. ByteDance's model-as-a-service platform. Enterprise AI writing platform. xAI's Grok models for conversation. Distributed inference framework. Yandex's language models and AI. 01.AI's bilingual language models. IEIT Systems' Yuan 2.0 models. ChatGLM and other Chinese models. diff --git a/src/oss/python/integrations/providers/anyscale.mdx b/src/oss/python/integrations/providers/anyscale.mdx index 601d6ecd8f..1d232644fc 100644 --- a/src/oss/python/integrations/providers/anyscale.mdx +++ b/src/oss/python/integrations/providers/anyscale.mdx @@ -33,14 +33,6 @@ See a [usage example](/oss/integrations/llms/anyscale). from langchain_community.llms.anyscale import Anyscale ``` -## Chat Models - -See a [usage example](/oss/integrations/chat/anyscale). - -```python -from langchain_community.chat_models.anyscale import ChatAnyscale -``` - ## Embeddings See a [usage example](/oss/integrations/text_embedding/anyscale). diff --git a/src/oss/python/integrations/providers/llamacpp.mdx b/src/oss/python/integrations/providers/llamacpp.mdx index 044227bc3d..a2e276fd79 100644 --- a/src/oss/python/integrations/providers/llamacpp.mdx +++ b/src/oss/python/integrations/providers/llamacpp.mdx @@ -36,7 +36,7 @@ from langchain_community.chat_models import ChatLlamaCpp ``` ## LLMs -See a [usage example](/oss/integrations/llms/llamacpp). +See a [usage example](/oss/integrations/llms/llama_cpp). ```python from langchain_community.llms import LlamaCpp diff --git a/src/oss/python/integrations/providers/upstage.mdx b/src/oss/python/integrations/providers/upstage.mdx index d6dffe99b9..71f6da86df 100644 --- a/src/oss/python/integrations/providers/upstage.mdx +++ b/src/oss/python/integrations/providers/upstage.mdx @@ -12,10 +12,10 @@ title: Upstage | API | Description | Import | Example usage | | --- | --- | --- | --- | -| Chat | Build assistants using Solar Chat | `from langchain_upstage import ChatUpstage` | [Go](../../chat/upstage) | -| Text Embedding | Embed strings to vectors | `from langchain_upstage import UpstageEmbeddings` | [Go](../../text_embedding/upstage) | -| Groundedness Check | Verify groundedness of assistant's response | `from langchain_upstage import UpstageGroundednessCheck` | [Go](../../tools/upstage_groundedness_check) | -| Document Parse | Serialize documents with tables and figures | `from langchain_upstage import UpstageDocumentParseLoader` | [Go](../../document_loaders/upstage) | +| Chat | Build assistants using Solar Chat | `from langchain_upstage import ChatUpstage` | [Go](/oss/integrations/chat/upstage) | +| Text Embedding | Embed strings to vectors | `from langchain_upstage import UpstageEmbeddings` | [Go](/oss/integrations/text_embedding/upstage) | +| Groundedness Check | Verify groundedness of assistant's response | `from langchain_upstage import UpstageGroundednessCheck` | [Go](/oss/integrations/tools/upstage_groundedness_check) | +| Document Parse | Serialize documents with tables and figures | `from langchain_upstage import UpstageDocumentParseLoader` | [Go](/oss/integrations/document_loaders/upstage) | See [documentations](https://console.upstage.ai/docs/getting-started/overview) for more details about the models and features. diff --git a/src/oss/python/integrations/providers/vectara.mdx b/src/oss/python/integrations/providers/vectara.mdx index 8b3a989528..7ad24c0c6b 100644 --- a/src/oss/python/integrations/providers/vectara.mdx +++ b/src/oss/python/integrations/providers/vectara.mdx @@ -201,10 +201,3 @@ For more details about Vectara chat [go to this notebook](../chat/vectara.ipynb) Vectara offers Intelligent Query Rewriting option which enhances search precision by automatically generating metadata filter expressions from natural language queries. This capability analyzes user queries, extracts relevant metadata filters, and rephrases the query to focus on the core information need. For more details [go to this notebook](../retrievers/self_query/vectara_self_query.ipynb). -## Vectara tools - -Vectara provides serval tools that can be used with LangChain. For more details [go to this notebook](../tools/vectara.ipynb) - -```python - -``` diff --git a/src/oss/python/integrations/retrievers/zotero.mdx b/src/oss/python/integrations/retrievers/zotero.mdx index cf89fbd98a..5ce0db53bf 100644 --- a/src/oss/python/integrations/retrievers/zotero.mdx +++ b/src/oss/python/integrations/retrievers/zotero.mdx @@ -78,7 +78,7 @@ retriever.invoke("", tag=tags) ## Use within a chain -Due to the way the Zotero API search operates, directly passing a user question to the ZoteroRetriever will often not return satisfactory results. For use in chains or agentic frameworks, it is recommended to turn the ZoteroRetriever into a [tool](https://python.langchain.com/docs/how_to/custom_tools/#creating-tools-from-functions). This way, the LLM can turn the user query into a more concise search query for the API. Furthermore, this allows the LLM to fill in additional search parameters, such as tag or item type. +Due to the way the Zotero API search operates, directly passing a user question to the ZoteroRetriever will often not return satisfactory results. For use in chains or agentic frameworks, it is recommended to turn the ZoteroRetriever into a [tool](/oss/langchain/tools). This way, the LLM can turn the user query into a more concise search query for the API. Furthermore, this allows the LLM to fill in additional search parameters, such as tag or item type. ```python from typing import List, Optional, Union diff --git a/src/oss/python/integrations/stores/astradb.mdx b/src/oss/python/integrations/stores/astradb.mdx index e3e23554d6..1506cebee7 100644 --- a/src/oss/python/integrations/stores/astradb.mdx +++ b/src/oss/python/integrations/stores/astradb.mdx @@ -2,7 +2,7 @@ title: AstraDBByteStore --- -This will help you get started with Astra DB [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all `AstraDBByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/astradb/storage/langchain_astradb.storage.AstraDBByteStore.html). +This will help you get started with Astra DB [key-value stores](/oss/integrations/stores). For detailed documentation of all `AstraDBByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/astradb/storage/langchain_astradb.storage.AstraDBByteStore.html). ## Overview diff --git a/src/oss/python/integrations/stores/cassandra.mdx b/src/oss/python/integrations/stores/cassandra.mdx index 85467ba1fb..a69cf5648b 100644 --- a/src/oss/python/integrations/stores/cassandra.mdx +++ b/src/oss/python/integrations/stores/cassandra.mdx @@ -2,7 +2,7 @@ title: CassandraByteStore --- -This will help you get started with Cassandra [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all `CassandraByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.cassandra.CassandraByteStore.html). +This will help you get started with Cassandra [key-value stores](/oss/integrations/stores). For detailed documentation of all `CassandraByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.cassandra.CassandraByteStore.html). ## Overview diff --git a/src/oss/python/integrations/stores/elasticsearch.mdx b/src/oss/python/integrations/stores/elasticsearch.mdx index 9e8fb2c236..a748f29d1e 100644 --- a/src/oss/python/integrations/stores/elasticsearch.mdx +++ b/src/oss/python/integrations/stores/elasticsearch.mdx @@ -2,7 +2,7 @@ title: ElasticsearchEmbeddingsCache --- -This will help you get started with Elasticsearch [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all `ElasticsearchEmbeddingsCache` features and configurations head to the [API reference](https://python.langchain.com/api_reference/elasticsearch/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html). +This will help you get started with Elasticsearch [key-value stores](/oss/integrations/stores). For detailed documentation of all `ElasticsearchEmbeddingsCache` features and configurations head to the [API reference](https://python.langchain.com/api_reference/elasticsearch/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html). ## Overview @@ -95,7 +95,7 @@ kv_store.mget( ## Use as an embeddings cache -Like other `ByteStores`, you can use an `ElasticsearchEmbeddingsCache` instance for [persistent caching in document ingestion](/oss/how-to/caching_embeddings/) for RAG. +Like other `ByteStores`, you can use an `ElasticsearchEmbeddingsCache` instance for [persistent caching in document ingestion](/oss/integrations/text_embedding#caching) for RAG. However, cached vectors won't be searchable by default. The developer can customize the building of the Elasticsearch document in order to add indexed vector field. diff --git a/src/oss/python/integrations/stores/file_system.mdx b/src/oss/python/integrations/stores/file_system.mdx index 10897d5792..b337b015b5 100644 --- a/src/oss/python/integrations/stores/file_system.mdx +++ b/src/oss/python/integrations/stores/file_system.mdx @@ -2,7 +2,7 @@ title: LocalFileStore --- -This will help you get started with local filesystem [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all LocalFileStore features and configurations head to the [API reference](https://python.langchain.com/api_reference/langchain/storage/langchain.storage.file_system.LocalFileStore.html). +This will help you get started with local filesystem [key-value stores](/oss/integrations/stores). For detailed documentation of all LocalFileStore features and configurations head to the [API reference](https://python.langchain.com/api_reference/langchain/storage/langchain.storage.file_system.LocalFileStore.html). ## Overview diff --git a/src/oss/python/integrations/stores/in_memory.mdx b/src/oss/python/integrations/stores/in_memory.mdx index 582ef341f1..20d75d17a4 100644 --- a/src/oss/python/integrations/stores/in_memory.mdx +++ b/src/oss/python/integrations/stores/in_memory.mdx @@ -2,7 +2,7 @@ title: InMemoryByteStore --- -This guide will help you get started with in-memory [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all `InMemoryByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/core/stores/langchain_core.stores.InMemoryByteStore.html). +This guide will help you get started with in-memory [key-value stores](/oss/integrations/stores). For detailed documentation of all `InMemoryByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/core/stores/langchain_core.stores.InMemoryByteStore.html). ## Overview diff --git a/src/oss/python/integrations/stores/redis.mdx b/src/oss/python/integrations/stores/redis.mdx index eb56cc4eea..bfcbde435c 100644 --- a/src/oss/python/integrations/stores/redis.mdx +++ b/src/oss/python/integrations/stores/redis.mdx @@ -2,7 +2,7 @@ title: RedisStore --- -This will help you get started with Redis [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all `RedisStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.redis.RedisStore.html). +This will help you get started with Redis [key-value stores](/oss/integrations/stores). For detailed documentation of all `RedisStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.redis.RedisStore.html). ## Overview diff --git a/src/oss/python/integrations/stores/upstash_redis.mdx b/src/oss/python/integrations/stores/upstash_redis.mdx index 82f9b13447..158f3a9229 100644 --- a/src/oss/python/integrations/stores/upstash_redis.mdx +++ b/src/oss/python/integrations/stores/upstash_redis.mdx @@ -2,7 +2,7 @@ title: UpstashRedisByteStore --- -This will help you get started with Upstash redis [key-value stores](/oss/concepts/key_value_stores). For detailed documentation of all `UpstashRedisByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html). +This will help you get started with Upstash redis [key-value stores](/oss/integrations/stores). For detailed documentation of all `UpstashRedisByteStore` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html). ## Overview diff --git a/src/oss/python/integrations/text_embedding/index.mdx b/src/oss/python/integrations/text_embedding/index.mdx index d65286cf58..36c337db1a 100644 --- a/src/oss/python/integrations/text_embedding/index.mdx +++ b/src/oss/python/integrations/text_embedding/index.mdx @@ -466,7 +466,6 @@ In production, you would typically use a more robust persistent store, such as a - diff --git a/src/oss/python/integrations/tools/index.mdx b/src/oss/python/integrations/tools/index.mdx index 7d8e4a0a6b..a5c61be930 100644 --- a/src/oss/python/integrations/tools/index.mdx +++ b/src/oss/python/integrations/tools/index.mdx @@ -7,10 +7,7 @@ title: "Tools and toolkits" A toolkit is a collection of tools meant to be used together. - -If you'd like to write your own tool, see [this how-to](/docs/how_to/custom_tools/). If you'd like to contribute an integration, see [Contributing integrations](/oss/contributing#add-a-new-integration). - ## Search diff --git a/src/oss/python/integrations/tools/jina_search.mdx b/src/oss/python/integrations/tools/jina_search.mdx index 3a14816362..66307a151a 100644 --- a/src/oss/python/integrations/tools/jina_search.mdx +++ b/src/oss/python/integrations/tools/jina_search.mdx @@ -14,7 +14,7 @@ This guide provides a quick overview for getting started with Jina [tool](/oss/i ### Tool features -| [Returns artifact](/oss/how-to/tool_artifacts/) | Native async | Return data | Pricing | +| [Returns artifact](/oss/langchain/tools) | Native async | Return data | Pricing | | :---: | :---: | :---: | :---: | | ❌ | ❌ | URL, Snippet, Title, Page Content | 1M response tokens free | diff --git a/src/oss/python/integrations/tools/sql_database.mdx b/src/oss/python/integrations/tools/sql_database.mdx index fc24094675..e6c3aab3c0 100644 --- a/src/oss/python/integrations/tools/sql_database.mdx +++ b/src/oss/python/integrations/tools/sql_database.mdx @@ -127,7 +127,7 @@ from langchain_community.tools.sql_database.tool import ( ## Use within an agent -Following the [SQL Q&A Tutorial](/oss/tutorials/sql_qa/#agents), below we equip a simple question-answering agent with the tools in our toolkit. First we pull a relevant prompt and populate it with its required parameters: +Following the [SQL Q&A Tutorial](/oss/langchain/sql-agent), below we equip a simple question-answering agent with the tools in our toolkit. First we pull a relevant prompt and populate it with its required parameters: ```python from langchain import hub diff --git a/src/oss/python/integrations/tools/tavily_extract.mdx b/src/oss/python/integrations/tools/tavily_extract.mdx index 875a9577f6..524ef42c91 100644 --- a/src/oss/python/integrations/tools/tavily_extract.mdx +++ b/src/oss/python/integrations/tools/tavily_extract.mdx @@ -14,7 +14,7 @@ title: Tavily Extract ### Tool features -| [Returns artifact](/oss/how-to/tool_artifacts/) | Native async | Return data | Pricing | +| [Returns artifact](/oss/langchain/tools) | Native async | Return data | Pricing | | :---: | :---: |:--------------------------------------------------------:| :---: | | ❌ | ✅ | raw content and images | 1,000 free searches / month | diff --git a/src/oss/python/integrations/tools/tavily_search.mdx b/src/oss/python/integrations/tools/tavily_search.mdx index bcbc7b6e32..c16b7d28dc 100644 --- a/src/oss/python/integrations/tools/tavily_search.mdx +++ b/src/oss/python/integrations/tools/tavily_search.mdx @@ -14,7 +14,7 @@ title: Tavily Search ### Tool features -| [Returns artifact](/oss/how-to/tool_artifacts/) | Native async | Return data | Pricing | +| [Returns artifact](/oss/langchain/tools) | Native async | Return data | Pricing | | :---: | :---: |:--------------------------------------------------------:| :---: | | ❌ | ✅ | title, URL, content snippet, raw_content, answer, images | 1,000 free searches / month | diff --git a/src/oss/python/integrations/vectorstores/timescalevector.mdx b/src/oss/python/integrations/vectorstores/timescalevector.mdx index 539ef95be3..c0b99bf75e 100644 --- a/src/oss/python/integrations/vectorstores/timescalevector.mdx +++ b/src/oss/python/integrations/vectorstores/timescalevector.mdx @@ -293,7 +293,7 @@ def create_uuid(date_string: str): return str(uuid) ``` -Next, we'll define a metadata function to extract the relevant metadata from the JSON record. We'll pass this function to the JSONLoader. See the [JSON document loader docs](/oss/how-to/document_loader_json) for more details. +Next, we'll define a metadata function to extract the relevant metadata from the JSON record. We'll pass this function to the JSONLoader. See the [JSON document loader docs](/oss/integrations/document_loaders/json) for more details. ```python # Helper function to split name and email given an author string consisting of Name Lastname