The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
Deprecating sql_database access for creating UC functions for agent tools (#29745)
Sunish Shethf42dafa80942
diff --git a/cookbook/README.md b/cookbook/README.mdindex 2b90e07c79..6b18e508af 100644--- a/cookbook/README.md+++ b/cookbook/README.md@@ -21,7 +21,6 @@ Notebook | Description[code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.-[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.[deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.[elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.[extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Toolsdiff --git a/cookbook/databricks_sql_db.ipynb b/cookbook/databricks_sql_db.ipynbdeleted file mode 100644index 78fba6b914..0000000000--- a/cookbook/databricks_sql_db.ipynb+++ /dev/null@@ -1,273 +0,0 @@-{- "cells": [- {- "cell_type": "markdown",- "id": "707d13a7",- "metadata": {},- "source": [- "# Databricks\n",- "\n",- "This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",- "It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."- ]- },- {- "cell_type": "markdown",- "id": "0076d072",- "metadata": {},- "source": [- "## Installation and Setup"- ]- },- {- "cell_type": "code",- "execution_count": 1,- "id": "739b489b",- "metadata": {},- "outputs": [],- "source": [- "!pip install databricks-sql-connector"- ]- },- {- "cell_type": "markdown",- "id": "73113163",- "metadata": {},- "source": [- "## Connecting to Databricks\n",- "\n",- "You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",- "\n",- "### Syntax\n",- "```python\n",- "SQLDatabase.from_databricks(\n",- " catalog: str,\n",- " schema: str,\n",- " host: Optional[str] = None,\n",- " api_token: Optional[str] = None,\n",- " warehouse_id: Optional[str] = None,\n",- " cluster_id: Optional[str] = None,\n",- " engine_args: Optional[dict] = None,\n",- " **kwargs: Any)\n",- "```\n",- "### Required Parameters\n",- "* `catalog`: The catalog name in the Databricks database.\n",- "* `schema`: The schema name in the catalog.\n",- "\n",- "### Optional Parameters\n",- "There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",- "* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",- "* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",- "* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",- "* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",- "* `engine_args`: The arguments to be used when connecting Databricks.\n",- "* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."- ]- },- {- "cell_type": "markdown",- "id": "b11c7e48",- "metadata": {},- "source": [- "## Examples"- ]- },- {- "cell_type": "code",- "execution_count": 2,- "id": "8102bca0",- "metadata": {},- "outputs": [],- "source": [- "# Connecting to Databricks with SQLDatabase wrapper\n",- "from langchain_community.utilities import SQLDatabase\n",- "\n",- "db = SQLDatabase.from_databricks(catalog=\"samples\", schema=\"nyctaxi\")"- ]- },- {- "cell_type": "code",- "execution_count": 3,- "id": "9dd36f58",- "metadata": {},- "outputs": [],- "source": [- "# Creating a OpenAI Chat LLM wrapper\n",- "from langchain_openai import ChatOpenAI\n",- "\n",- "llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"- ]- },- {- "cell_type": "markdown",- "id": "5b5c5f1a",- "metadata": {},- "source": [- "### SQL Chain example\n",- "\n",- "This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."- ]- },- {- "cell_type": "code",- "execution_count": 4,- "id": "36f2270b",- "metadata": {},- "outputs": [],- "source": [- "from langchain_community.utilities import SQLDatabaseChain\n",- "\n",- "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"- ]- },- {- "cell_type": "code",- "execution_count": 5,- "id": "4e2b5f25",- "metadata": {},- "outputs": [- {- "name": "stdout",- "output_type": "stream",- "text": [- "\n",- "\n",- "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",- "What is the average duration of taxi rides that start between midnight and 6am?\n",- "SQLQuery:\u001b[32;1m\u001b[1;3mSELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration\n",- "FROM trips\n",- "WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6\u001b[0m\n",- "SQLResult: \u001b[33;1m\u001b[1;3m[(987.8122786304605,)]\u001b[0m\n",- "Answer:\u001b[32;1m\u001b[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001b[0m\n",- "\u001b[1m> Finished chain.\u001b[0m\n"- ]- },- {- "data": {- "text/plain": [- "'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"- ]- },- "execution_count": 6,- "metadata": {},- "output_type": "execute_result"- }- ],- "source": [- "db_chain.run(\n",- " \"What is the average duration of taxi rides that start between midnight and 6am?\"\n",- ")"- ]- },- {- "cell_type": "markdown",- "id": "e496d5e5",- "metadata": {},- "source": [- "### SQL Database Agent example\n",- "\n",- "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/tools/sql_database) for answering questions over a Databricks database."- ]- },- {- "cell_type": "code",- "execution_count": 7,- "id": "9918e86a",- "metadata": {},- "outputs": [],- "source": [- "from langchain.agents import create_sql_agent\n",- "from langchain_community.agent_toolkits import SQLDatabaseToolkit\n",- "\n",- "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",- "agent = create_sql_agent(llm=llm, toolkit=toolkit, verbose=True)"- ]- },- {- "cell_type": "code",- "execution_count": 8,- "id": "c484a76e",- "metadata": {},- "outputs": [- {- "name": "stdout",- "output_type": "stream",- "text": [- "\n",- "\n",- "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",- "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",- "Action Input: \u001b[0m\n",- "Observation: \u001b[38;5;200m\u001b[1;3mtrips\u001b[0m\n",- "Thought:\u001b[32;1m\u001b[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",- "Action: schema_sql_db\n",- "Action Input: trips\u001b[0m\n",- "Observation: \u001b[33;1m\u001b[1;3m\n",- "CREATE TABLE trips (\n",- "\ttpep_pickup_datetime TIMESTAMP, \n",- "\ttpep_dropoff_datetime TIMESTAMP, \n",- "\ttrip_distance FLOAT, \n",- "\tfare_amount FLOAT, \n",- "\tpickup_zip INT, \n",- "\tdropoff_zip INT\n",- ") USING DELTA\n",- "\n",- "/*\n",- "3 rows from trips table:\n",- "tpep_pickup_datetime\ttpep_dropoff_datetime\ttrip_distance\tfare_amount\tpickup_zip\tdropoff_zip\n",- "2016-02-14 16:52:13+00:00\t2016-02-14 17:16:04+00:00\t4.94\t19.0\t10282\t10171\n",- "2016-02-04 18:44:19+00:00\t2016-02-04 18:46:00+00:00\t0.28\t3.5\t10110\t10110\n",- "2016-02-17 17:13:57+00:00\t2016-02-17 17:17:55+00:00\t0.7\t5.0\t10103\t10023\n",- "*/\u001b[0m\n",- "Thought:\u001b[32;1m\u001b[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",- "Action: query_checker_sql_db\n",- "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",- "Observation: \u001b[31;1m\u001b[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",- "Thought:\u001b[32;1m\u001b[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",- "Action: query_sql_db\n",- "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",- "Observation: \u001b[36;1m\u001b[1;3m[(30.6, '0 00:43:31.000000000')]\u001b[0m\n",- "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",- "Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.\u001b[0m\n",- "\n",- "\u001b[1m> Finished chain.\u001b[0m\n"- ]- },- {- "data": {- "text/plain": [- "'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'"- ]- },- "execution_count": 9,- "metadata": {},- "output_type": "execute_result"- }- ],- "source": [- "agent.run(\"What is the longest trip distance and how long did it take?\")"- ]- }- ],- "metadata": {- "kernelspec": {- "display_name": "Python 3 (ipykernel)",- "language": "python",- "name": "python3"- },- "language_info": {- "codemirror_mode": {- "name": "ipython",- "version": 3- },- "file_extension": ".py",- "mimetype": "text/x-python",- "name": "python",- "nbconvert_exporter": "python",- "pygments_lexer": "ipython3",- "version": "3.11.3"- }- },- "nbformat": 4,- "nbformat_minor": 5-}diff --git a/docs/docs/integrations/providers/databricks.md b/docs/docs/integrations/providers/databricks.mdindex a45e8e3e03..2cf4961971 100644--- a/docs/docs/integrations/providers/databricks.md+++ b/docs/docs/integrations/providers/databricks.md@@ -103,14 +103,7 @@ See [MLflow LangChain Integration](/docs/integrations/providers/mlflow_tracking)SQLDatabase------------You can connect to Databricks SQL using the SQLDatabase wrapper of LangChain.-```-from langchain.sql_database import SQLDatabase--db = SQLDatabase.from_databricks(catalog="samples", schema="nyctaxi")-```--See [Databricks SQL Agent](https://docs.databricks.com/en/large-language-models/langchain.html#databricks-sql-agent) for how to connect Databricks SQL with your LangChain Agent as a powerful querying tool.+To connect to Databricks SQL or query structured data, see the [Databricks structured retriever tool documentation](https://docs.databricks.com/en/generative-ai/agent-framework/structured-retrieval-tools.html#table-query-tool) and to create an agent using the above created SQL UDF see [Databricks UC Integration](https://docs.unitycatalog.io/ai/integrations/langchain/).Open Models-----------diff --git a/libs/community/langchain_community/utilities/sql_database.py b/libs/community/langchain_community/utilities/sql_database.pyindex d6ecc4ca00..2b6b84ca4a 100644--- a/libs/community/langchain_community/utilities/sql_database.py+++ b/libs/community/langchain_community/utilities/sql_database.py@@ -139,6 +139,14 @@ class SQLDatabase:return cls(create_engine(database_uri, **_engine_args), **kwargs)@classmethod+ @deprecated(+ "0.3.18",+ message="For performing structured retrieval using Databricks SQL, "+ "see the latest best practices and recommended APIs at "+ "https://docs.unitycatalog.io/ai/integrations/langchain/ " # noqa: E501+ "instead",+ removal="1.0",+ )def from_databricks(cls,catalog: str,