Sync with LangChain master #3
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The object extends from langchain_community.chat_models.openai.ChatOpenAI which doesn't have `bind_tools` defined. I tried extending from `langchain_openai.ChatOpenAI` in langchain-ai#25975 but that PR got closed because this is not correct. So adding our own `bind_tools` (which for now copying from ChatOpenAI is good enough) will solve the tool calling issue we are having now. --------- Co-authored-by: Erick Friis <[email protected]>
Co-authored-by: Erick Friis <[email protected]>
Changed > "At a high-level, the steps of constructing a knowledge are from text are:" to > "At a high-level, the steps of constructing a knowledge graph from text are:" Co-authored-by: Erick Friis <[email protected]>
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Fix docstring for two functions that look like have
docstrings carried over from other functions.
- **Issue:** Not found issue reporting the miss-leading docstrings.
- **Dependencies:** None
- **Twitter handle:**
- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <[email protected]>
…e introduce in langchain-google-community 1.0.9 (langchain-ai#26184) Hello, fix: langchain-ai#26183 Adding documentation regarding SQL like filter for Google BigQuery Vector Search coming in next langchain-google-community 1.0.9 release. Note: langchain-google-community==1.0.9 is not yet released Question: There is no way to warn the user int the doc about the availability of a feature after a specific package version ? --------- Co-authored-by: Erick Friis <[email protected]>
Add tool calling example to AI21 docs
…n-ai#26235) This fixes the issue where `__start__` and `__end__` node labels are being interpreted as markdown, as of the most recent Mermaid update
Co-authored-by: Erick Friis <[email protected]>
Co-authored-by: Erick Friis <[email protected]>
Co-authored-by: Erick Friis <[email protected]>
Thank you for contributing to LangChain! - [ ] **PR title**: "package: description" docs:tutorials:llm_chain:fix typo - [ ] **PR message**: fix typo in llm chain tutorial - [ ] **Add tests and docs**: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. Co-authored-by: Erick Friis <[email protected]>
While going through the chatbot tutorial, I noticed a couple of typos and grammatical issues. Also, the pip install command for langchain_community was commented out, but the document mentions installing it. --------- Co-authored-by: Erick Friis <[email protected]>
Add standard tests for ChatHuggingFace. About half of these fail currently.
…-llm runs (langchain-ai#26270) - This takes a long time to compute, isn't used, and currently called on every invocation of every chain/retriever/etc
…n't output string (langchain-ai#26319) ### simple modify core: add supporting non english character target issue is langchain-ai#26315 same issue on langgraph - langchain-ai/langgraph#1504
…of Tool (langchain-ai#26327) ```python from langchain_core.tools import Tool from langchain_core.utils.function_calling import convert_to_openai_tool def my_function(x: int) -> int: return x + 2 tool = Tool( name="tool_name", func=my_function, description="test description", ) convert_to_openai_tool(tool) ``` Current: ``` {'type': 'function', 'function': {'name': 'tool_name', 'description': 'test description', 'parameters': {'type': 'object', 'properties': {'args': {'type': 'array', 'items': {}}, 'config': {'type': 'object', 'properties': {'tags': {'type': 'array', 'items': {'type': 'string'}}, 'metadata': {'type': 'object'}, 'callbacks': {'anyOf': [{'type': 'array', 'items': {}}, {}]}, 'run_name': {'type': 'string'}, 'max_concurrency': {'type': 'integer'}, 'recursion_limit': {'type': 'integer'}, 'configurable': {'type': 'object'}, 'run_id': {'type': 'string', 'format': 'uuid'}}}, 'kwargs': {'type': 'object'}}, 'required': ['config']}}} ``` Here: ``` {'type': 'function', 'function': {'name': 'tool_name', 'description': 'test description', 'parameters': {'properties': {'__arg1': {'title': '__arg1', 'type': 'string'}}, 'required': ['__arg1'], 'type': 'object'}}} ```
…ion in doc (langchain-ai#26359) 0.1.15 instead of just 0.1.5
) Fix langchain-ai#26232 --------- Co-authored-by: Eugene Yurtsev <[email protected]>
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Jess Ou <[email protected]>
Co-authored-by: Erick Friis <[email protected]>
api no longer throws an error https://console.groq.com/docs/tool-use#streaming
needed for thinking tokens --------- Co-authored-by: Erick Friis <[email protected]>
Support using additional import mapping. This allows users to override old mappings/add new imports to the loads function. - [x ] **Add tests and docs**: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ x] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/
…gchain-ai#26307) - This allows pydantic to correctly resolve annotations necessary when using openai new param `json_schema` Resolves issue: langchain-ai#26250 --------- Co-authored-by: Eugene Yurtsev <[email protected]> Co-authored-by: Bagatur <[email protected]>
…ai#26914) **Description:** Replaced blocking (sync) rate_limiter code in async methods. **Issue:** langchain-ai#26913 **Dependencies:** N/A **Twitter handle:** no need 🤗
…ai#26930) **Description:** Moves yield to after callback for `_stream` function for the titan takeoff model in the community llm package **Issue:** langchain-ai#16913
**Description:** Moves callback to before yield for `_stream` and `_astream` function for the textgen model in the community llm package **Issue:** langchain-ai#16913
…i#26928) **Description:** Moves yield to after callback for `_stream` function for the MLX pipeline model in the community llm package **Issue:** langchain-ai#16913
- [x] PR title: Fix typo in code example in mlflow.py - In libs/community/langchain_community/chat_models/mlflow.py
…26927) **Description:** Moves yield to after callback for `_stream` function for the cloudfare workersai model in the community llm package **Issue:** langchain-ai#16913
All auto-fixes.
Addressing some lingering comments from langchain-ai#26944, adding parameters for - python version - working directory 
…emory (langchain-ai#26855) This PR updates the documentation examples that used RunnableWithMessageHistory to show how to achieve the same implementation with langgraph memory. Some of the underlying PRs (not all of them): - docs[patch]: update chatbot tutorial and migration guide (langchain-ai#26780) - docs[patch]: update chatbot memory how-to (langchain-ai#26790) - docs[patch]: update chatbot tools how-to (langchain-ai#26816) - docs: update chat history in rag how-to (langchain-ai#26821) - docs: update trim messages notebook (langchain-ai#26793) - docs: clean up imports in how to guide for rag qa with chat history (langchain-ai#26825) - docs[patch]: update conversational rag tutorial (langchain-ai#26814) --------- Co-authored-by: ccurme <[email protected]> Co-authored-by: Vadym Barda <[email protected]> Co-authored-by: mercyspirit <[email protected]> Co-authored-by: aqiu7 <[email protected]> Co-authored-by: John <[email protected]> Co-authored-by: Erick Friis <[email protected]> Co-authored-by: William FH <[email protected]> Co-authored-by: Subhrajyoty Roy <[email protected]> Co-authored-by: Rajendra Kadam <[email protected]> Co-authored-by: Christophe Bornet <[email protected]> Co-authored-by: Devin Gaffney <[email protected]> Co-authored-by: Bagatur <[email protected]>
…6848) Co-authored-by: Eugene Yurtsev <[email protected]>
These allow converting linked documents (such as those used with GraphVectorStore) to networkx for rendering and/or in-memory graph algorithms such as community detection.
…support (langchain-ai#26960) **Description:** Update the code interpreter tools feature table to reflect Riza file upload support (blog announcement here: https://riza.io/blog/adding-support-for-input-files-and-http-credentials) **Issue:** N/A **Dependencies:** N/A
httpx clients aren't serializable
template_format is an init argument on ChatPromptTemplate but not an attribute on the object so was getting shoved into StructuredPrompt.structured_ouptut_kwargs
* [chore]: Agent Observation should be casted to string to avoid errors * Merge branch 'master' into fix_observation_type_streaming * [chore]: Using Json.dumps * [chore]: Exact same logic as when casting agent oobservation to string
Description: Fix typo in list of PDF loaders. Co-authored-by: Eugene Yurtsev <[email protected]>
mrDzurb
approved these changes
Sep 30, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.