revert back & relint & reformat

revert

revised to experimentals

try to resolve conflict

reverse change

try to resolve conflict

revised unittest

reformat & relint

revert

update poetry

Author: mpskex

docs/extras/modules/data_connection/retrievers/how_to/self_query/myscale_self_query.ipynb

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "13afcae7",
    "metadata": {},
@@ -18,7 +17,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "68e75fb9",
    "metadata": {},
@@ -42,7 +40,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
    "metadata": {},
@@ -86,7 +83,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "bf7f6fc4",
    "metadata": {},
@@ -145,7 +141,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "5ecaab6d",
    "metadata": {},
@@ -203,7 +198,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "ea9df8d4",
    "metadata": {},
@@ -274,7 +268,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "86371ac8",
    "metadata": {},
@@ -331,7 +324,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
    "metadata": {},
@@ -374,178 +366,6 @@
     "# This example only specifies a relevant query\n",
     "retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
    ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "d25c52b0",
-   "metadata": {},
-   "source": [
-    "## SQL Self-Query Retriever with MyScale"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0f824b20",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip3 install clickhouse-sqlalchemy InstructorEmbedding sentence_transformers openai"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a7af1d99",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from os import environ\n",
-    "\n",
-    "environ[\"HTTPS_PROXY\"] = \"http://192.168.40.161:7890\"\n",
-    "environ[\"OPENAI_API_BASE\"] = \"https://one-api.myscale.cloud/v1\"\n",
-    "import getpass\n",
-    "from typing import Dict, Any\n",
-    "from langchain import OpenAI, SQLDatabase, SQLDatabaseChain, LLMChain\n",
-    "from sqlalchemy import create_engine, Column, MetaData\n",
-    "from langchain import PromptTemplate\n",
-    "\n",
-    "\n",
-    "from sqlalchemy import create_engine\n",
-    "\n",
-    "MYSCALE_HOST = \"msc-1decbcc9.us-east-1.aws.staging.myscale.cloud\"\n",
-    "MYSCALE_PORT = 443\n",
-    "MYSCALE_USER = \"chatdata\"\n",
-    "MYSCALE_PASSWORD = \"myscale_rocks\"\n",
-    "OPENAI_API_KEY = getpass.getpass(\"OpenAI API Key:\")\n",
-    "\n",
-    "engine = create_engine(\n",
-    "    f\"clickhouse://{MYSCALE_USER}:{MYSCALE_PASSWORD}@{MYSCALE_HOST}:{MYSCALE_PORT}/default?protocol=https\"\n",
-    ")\n",
-    "environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "eceb0f9e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings import HuggingFaceInstructEmbeddings\n",
-    "from langchain.chains.sql_database.parser import VectorSQLOutputParser\n",
-    "\n",
-    "output_parser = VectorSQLOutputParser.from_embeddings(\n",
-    "    model=HuggingFaceInstructEmbeddings(\n",
-    "        model_name=\"hkunlp/instructor-base\", model_kwargs={\"device\": \"cpu\"}\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c7b3e108",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.callbacks import StdOutCallbackHandler\n",
-    "\n",
-    "metadata = MetaData(bind=engine)\n",
-    "\n",
-    "from langchain.chains.sql_database.base import SQLDatabaseChain\n",
-    "from langchain.chains.sql_database.prompt import MYSCALE_PROMPT\n",
-    "from langchain.sql_database import SQLDatabase\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "chain = SQLDatabaseChain(\n",
-    "    llm_chain=LLMChain(\n",
-    "        llm=OpenAI(openai_api_key=OPENAI_API_KEY, temperature=0),\n",
-    "        prompt=MYSCALE_PROMPT,\n",
-    "        output_parser=output_parser,\n",
-    "    ),\n",
-    "    top_k=10,\n",
-    "    return_direct=True,\n",
-    "    database=SQLDatabase(engine, None, metadata),\n",
-    "    native_format=True,\n",
-    ")\n",
-    "\n",
-    "import pandas as pd\n",
-    "\n",
-    "pd.DataFrame(\n",
-    "    chain.run(\n",
-    "        \"Please give me 10 papers to ask what is PageRank?\",\n",
-    "        callbacks=[StdOutCallbackHandler()],\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "9d6b1385",
-   "metadata": {},
-   "source": [
-    "## SQL Database as Retriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "864ad4b1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.retrievers import SQLDatabaseChainRetriever\n",
-    "from langchain.chains.sql_database.parser import VectorSQLRetrieveAllOutputParser\n",
-    "from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain\n",
-    "\n",
-    "output_parser_retrieve_all = VectorSQLRetrieveAllOutputParser.from_embeddings(\n",
-    "    output_parser.model\n",
-    ")\n",
-    "\n",
-    "chain = SQLDatabaseChain.from_llm(\n",
-    "    llm=OpenAI(openai_api_key=OPENAI_API_KEY, temperature=0),\n",
-    "    prompt=MYSCALE_PROMPT,\n",
-    "    top_k=10,\n",
-    "    return_direct=True,\n",
-    "    db=SQLDatabase(engine, None, metadata),\n",
-    "    sql_cmd_parser=output_parser_retrieve_all,\n",
-    "    native_format=True,\n",
-    ")\n",
-    "\n",
-    "# You need all those keys to get docs\n",
-    "retriever = SQLDatabaseChainRetriever(sql_db_chain=chain, page_content_key=\"abstract\")\n",
-    "\n",
-    "document_with_metadata_prompt = PromptTemplate(\n",
-    "    input_variables=[\"page_content\", \"id\", \"title\", \"authors\", \"pubdate\", \"categories\"],\n",
-    "    template=\"Content:\\n\\tTitle: {title}\\n\\tAbstract: {page_content}\\n\\tAuthors: {authors}\\n\\tDate of Publication: {pubdate}\\n\\tCategories: {categories}\\nSOURCE: {id}\",\n",
-    ")\n",
-    "\n",
-    "chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
-    "    ChatOpenAI(\n",
-    "        model_name=\"gpt-3.5-turbo-16k\", openai_api_key=OPENAI_API_KEY, temperature=0.6\n",
-    "    ),\n",
-    "    retriever=retriever,\n",
-    "    chain_type=\"stuff\",\n",
-    "    chain_type_kwargs={\n",
-    "        \"document_prompt\": document_with_metadata_prompt,\n",
-    "    },\n",
-    "    return_source_documents=True,\n",
-    ")\n",
-    "ans = chain(\"Please give me 10 papers to ask what is PageRank?\")\n",
-    "print(ans[\"answer\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1b1dddf5",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -564,7 +384,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.11.3"
   }
  },
  "nbformat": 4,