github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-03 03:59:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150)

Browse Source 
This PR adds 

* `ZeroShotAgent.as_sql_agent`, which returns an agent for interacting
with a sql database. This builds off of `SQLDatabaseChain`. The main
advantages are 1) answering general questions about the db, 2) access to
a tool for double checking queries, and 3) recovering from errors
* `ZeroShotAgent.as_json_agent` which returns an agent for interacting
with json blobs.
* Several examples in notebooks

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Ankush Gola
2023-02-28 19:44:39 -08:00
committed by GitHub
parent 35f1e8f569
commit 82baecc892
58 changed files with 5994 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

190
docs/modules/agents/agent_toolkits/json.ipynb Normal file
View File

@@ -0,0 +1,190 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
"metadata": {},
"source": [
"# JSON Agent\n",
"\n",
"This notebook showcases an agent designed to interact with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.\n",
"\n",
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml).\n",
"\n",
"We will use the JSON agent to answer some questions about the API spec."
]
},
{
"cell_type": "markdown",
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
"metadata": {},
"source": [
"## Initialization"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import yaml\n",
"\n",
"from langchain.agents import (\n",
" create_json_agent,\n",
" AgentExecutor\n",
")\n",
"from langchain.agents.agent_toolkits import JsonToolkit\n",
"from langchain.chains import LLMChain\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.requests import RequestsWrapper\n",
"from langchain.tools.json.tool import JsonSpec"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"with open(\"openai_openapi.yml\") as f:\n",
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
"json_spec = JsonSpec(dict_=data, max_value_length=4000)\n",
"json_toolkit = JsonToolkit(spec=json_spec)\n",
"\n",
"json_agent_executor = create_json_agent(\n",
" llm=OpenAI(temperature=0),\n",
" toolkit=json_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "05cfcb24-4389-4b8f-ad9e-466e3fca8db0",
"metadata": {},
"source": [
"## Example: getting the required POST parameters for a request"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "faf13702-50f0-4d1b-b91f-48c750ccfd98",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"required\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mTrue\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The required parameters in the request body to the /completions endpoint are 'model'.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"The required parameters in the request body to the /completions endpoint are 'model'.\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"json_agent_executor.run(\"What are the required parameters in the request body to the /completions endpoint?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ba9c9d30",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

3124
docs/modules/agents/agent_toolkits/openai_openapi.yml Normal file
View File

File diff suppressed because it is too large Load Diff

242
docs/modules/agents/agent_toolkits/openapi.ipynb Normal file
View File

@@ -0,0 +1,242 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
"metadata": {},
"source": [
"# OpenAPI Agent\n",
"\n",
"This notebook showcases an agent designed to interact with an OpenAPI spec and make a correct API request based on the information it has gathered from the spec.\n",
"\n",
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml)."
]
},
{
"cell_type": "markdown",
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
"metadata": {},
"source": [
"## Initialization"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import yaml\n",
"\n",
"from langchain.agents import create_openapi_agent\n",
"from langchain.agents.agent_toolkits import OpenAPIToolkit\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.requests import RequestsWrapper\n",
"from langchain.tools.json.tool import JsonSpec"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"with open(\"openai_openapi.yml\") as f:\n",
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
"json_spec=JsonSpec(dict_=data, max_value_length=4000)\n",
"headers = {\n",
" \"Authorization\": f\"Bearer {os.getenv('OPENAI_API_KEY')}\"\n",
"}\n",
"requests_wrapper=RequestsWrapper(headers=headers)\n",
"openapi_toolkit = OpenAPIToolkit.from_llm(OpenAI(temperature=0), json_spec, requests_wrapper, verbose=True)\n",
"openapi_agent_executor = create_openapi_agent(\n",
" llm=OpenAI(temperature=0),\n",
" toolkit=openapi_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "f111879d-ae84-41f9-ad82-d3e6b72c41ba",
"metadata": {},
"source": [
"## Example: agent capable of analyzing OpenAPI spec and making requests"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "548db7f7-337b-4ba8-905c-e7fd58c01799",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_explorer\n",
"Action Input: What is the base url for the API?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the servers key to see what the base url is\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"servers\"][0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"servers\"][0]` is not a dict, get the value directly.')\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should get the value of the servers key\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"servers\"][0]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{'url': 'https://api.openai.com/v1'}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the base url for the API\n",
"Final Answer: The base url for the API is https://api.openai.com/v1\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mThe base url for the API is https://api.openai.com/v1\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should find the path for the /completions endpoint.\n",
"Action: json_explorer\n",
"Action Input: What is the path for the /completions endpoint?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the path for the /completions endpoint\n",
"Final Answer: data[\"paths\"][2]\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mdata[\"paths\"][2]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should find the required parameters for the POST request.\n",
"Action: json_explorer\n",
"Action Input: What are the required parameters for a POST request to the /completions endpoint?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]` is not a dict, get the value directly.')\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to get the value directly\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mThe required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the parameters needed to make the request.\n",
"Action: requests_post\n",
"Action Input: { \"url\": \"https://api.openai.com/v1/completions\", \"data\": { \"model\": \"davinci\", \"prompt\": \"tell me a joke\" } }\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{\"id\":\"cmpl-6oeEcNETfq8TOuIUQvAct6NrBXihs\",\"object\":\"text_completion\",\"created\":1677529082,\"model\":\"davinci\",\"choices\":[{\"text\":\"\\n\\n\\n\\nLove is a battlefield\\n\\n\\n\\nIt's me...And some\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Love is a battlefield. It's me...And some.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Love is a battlefield. It's me...And some.\""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"openapi_agent_executor.run(\"Make a post request to openai /completions. The prompt should be 'tell me a joke.'\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6ec9582b",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

210
docs/modules/agents/agent_toolkits/python.ipynb Normal file
View File

@@ -0,0 +1,210 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "82a4c2cc-20ea-4b20-a565-63e905dee8ff",
"metadata": {},
"source": [
"## Python Agent\n",
"\n",
"This notebook showcases an agent designed to write and execute python code to answer a question."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import create_python_agent\n",
"from langchain.tools.python.tool import PythonREPLTool\n",
"from langchain.python import PythonREPL\n",
"from langchain.llms.openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"agent_executor = create_python_agent(\n",
" llm=OpenAI(temperature=0, max_tokens=1000),\n",
" tool=PythonREPLTool(),\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to calculate the 10th fibonacci number\n",
"Action: Python REPL\n",
"Action Input: def fibonacci(n):\n",
" if n == 0:\n",
" return 0\n",
" elif n == 1:\n",
" return 1\n",
" else:\n",
" return fibonacci(n-1) + fibonacci(n-2)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to call the function with 10 as the argument\n",
"Action: Python REPL\n",
"Action Input: fibonacci(10)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 55\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'55'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What is the 10th fibonacci number?\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to write a neural network in PyTorch and train it on the given data.\n",
"Action: Python REPL\n",
"Action Input: \n",
"import torch\n",
"\n",
"# Define the model\n",
"model = torch.nn.Sequential(\n",
" torch.nn.Linear(1, 1)\n",
")\n",
"\n",
"# Define the loss\n",
"loss_fn = torch.nn.MSELoss()\n",
"\n",
"# Define the optimizer\n",
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
"\n",
"# Define the data\n",
"x_data = torch.tensor([[1.0], [2.0], [3.0], [4.0]])\n",
"y_data = torch.tensor([[2.0], [4.0], [6.0], [8.0]])\n",
"\n",
"# Train the model\n",
"for epoch in range(1000):\n",
" # Forward pass\n",
" y_pred = model(x_data)\n",
"\n",
" # Compute and print loss\n",
" loss = loss_fn(y_pred, y_data)\n",
" if (epoch+1) % 100 == 0:\n",
" print(f'Epoch {epoch+1}: loss = {loss.item():.4f}')\n",
"\n",
" # Zero the gradients\n",
" optimizer.zero_grad()\n",
"\n",
" # Backward pass\n",
" loss.backward()\n",
"\n",
" # Update the weights\n",
" optimizer.step()\n",
"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mEpoch 100: loss = 0.0013\n",
"Epoch 200: loss = 0.0007\n",
"Epoch 300: loss = 0.0004\n",
"Epoch 400: loss = 0.0002\n",
"Epoch 500: loss = 0.0001\n",
"Epoch 600: loss = 0.0001\n",
"Epoch 700: loss = 0.0000\n",
"Epoch 800: loss = 0.0000\n",
"Epoch 900: loss = 0.0000\n",
"Epoch 1000: loss = 0.0000\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The prediction for x = 5 is 10.0.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The prediction for x = 5 is 10.0.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"\"\"Understand, write a single neuron neural network in PyTorch.\n",
"Take synthetic data for y=2x. Train for 1000 epochs and print every 100 epochs.\n",
"Return prediction for x = 5\"\"\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb654671",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

527
docs/modules/agents/agent_toolkits/sql_database.ipynb Normal file
View File

@@ -0,0 +1,527 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "0e499e90-7a6d-4fab-8aab-31a4df417601",
"metadata": {},
"source": [
"# SQL Database Agent\n",
"\n",
"This notebook showcases an agent designed to interact with a sql databases. The agent builds off of [SQLDatabaseChain](https://langchain.readthedocs.io/en/latest/modules/chains/examples/sqlite.html) and is designed to answer more general questions about a database, as well as recover from errors.\n",
"\n",
"Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your database given certain questions. Be careful running it on sensitive data!\n",
"\n",
"This uses the example Chinook database. To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository."
]
},
{
"cell_type": "markdown",
"id": "ec927ac6-9b2a-4e8a-9a6e-3e429191875c",
"metadata": {
"tags": []
},
"source": [
"## Initialization"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "53422913-967b-4f2a-8022-00269c1be1b1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.agents import create_sql_agent\n",
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
"from langchain.sql_database import SQLDatabase\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.agents import AgentExecutor"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "090f3699-79c6-4ce1-ab96-a94f0121fd64",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
"toolkit = SQLDatabaseToolkit(db=db)\n",
"\n",
"agent_executor = create_sql_agent(\n",
" llm=OpenAI(temperature=0),\n",
" toolkit=toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
"metadata": {},
"source": [
"## Example: describing a table"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
"metadata": {
"tags": []
},
"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;3mArtist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the playlisttrack table\n",
"Action: schema_sql_db\n",
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"PlaylistTrack\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
"PlaylistId TrackId\n",
"1 3402\n",
"1 3389\n",
"1 3390\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Describe the playlisttrack table\")"
]
},
{
"cell_type": "markdown",
"id": "9abcfe8e-1868-42a4-8345-ad2d9b44c681",
"metadata": {},
"source": [
"## Example: describing a table, recovering from an error\n",
"\n",
"In this example, the agent tries to search for a table that doesn't exist, but finds the next best result"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "bea76658-a65b-47e2-b294-6d52c5556246",
"metadata": {
"tags": []
},
"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;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the PlaylistSong table\n",
"Action: schema_sql_db\n",
"Action Input: \"PlaylistSong\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mError: table_names {'PlaylistSong'} not found in database\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should check the spelling of the table\n",
"Action: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m The table is called PlaylistTrack\n",
"Action: schema_sql_db\n",
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"PlaylistTrack\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
"PlaylistId TrackId\n",
"1 3402\n",
"1 3389\n",
"1 3390\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.'"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Describe the playlistsong table\")"
]
},
{
"cell_type": "markdown",
"id": "6fbc26af-97e4-4a21-82aa-48bdc992da26",
"metadata": {},
"source": [
"## Example: running queries"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "17bea710-4a23-4de0-b48e-21d57be48293",
"metadata": {
"tags": []
},
"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;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the relevant tables to see what columns I can use.\n",
"Action: schema_sql_db\n",
"Action Input: \"Invoice, Customer\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"Customer\" (\n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
"\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
"\t\"Company\" NVARCHAR(80), \n",
"\t\"Address\" NVARCHAR(70), \n",
"\t\"City\" NVARCHAR(40), \n",
"\t\"State\" NVARCHAR(40), \n",
"\t\"Country\" NVARCHAR(40), \n",
"\t\"PostalCode\" NVARCHAR(10), \n",
"\t\"Phone\" NVARCHAR(24), \n",
"\t\"Fax\" NVARCHAR(24), \n",
"\t\"Email\" NVARCHAR(60) NOT NULL, \n",
"\t\"SupportRepId\" INTEGER, \n",
"\tPRIMARY KEY (\"CustomerId\"), \n",
"\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
")\n",
"\n",
"SELECT * FROM 'Customer' LIMIT 3;\n",
"CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId\n",
"1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3\n",
"2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5\n",
"3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3\n",
"\n",
"\n",
"CREATE TABLE \"Invoice\" (\n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"InvoiceDate\" DATETIME NOT NULL, \n",
"\t\"BillingAddress\" NVARCHAR(70), \n",
"\t\"BillingCity\" NVARCHAR(40), \n",
"\t\"BillingState\" NVARCHAR(40), \n",
"\t\"BillingCountry\" NVARCHAR(40), \n",
"\t\"BillingPostalCode\" NVARCHAR(10), \n",
"\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceId\"), \n",
"\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
")\n",
"\n",
"SELECT * FROM 'Invoice' LIMIT 3;\n",
"InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total\n",
"1 2 2009-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98\n",
"2 4 2009-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96\n",
"3 8 2009-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should query the Invoice and Customer tables to get the total sales per country.\n",
"Action: query_sql_db\n",
"Action Input: SELECT c.Country, SUM(i.Total) AS TotalSales FROM Invoice i INNER JOIN Customer c ON i.CustomerId = c.CustomerId GROUP BY c.Country ORDER BY TotalSales DESC LIMIT 10\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The customers from the USA spent the most, with a total of $523.06.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The customers from the USA spent the most, with a total of $523.06.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"List the total sales per country. Which country's customers spent the most?\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "474dddda-c067-4eeb-98b1-e763ee78b18c",
"metadata": {
"tags": []
},
"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;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Playlist and PlaylistTrack tables to see what columns I can use.\n",
"Action: schema_sql_db\n",
"Action Input: \"Playlist, PlaylistTrack\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"Playlist\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'Playlist' LIMIT 3;\n",
"PlaylistId Name\n",
"1 Music\n",
"2 Movies\n",
"3 TV Shows\n",
"\n",
"\n",
"CREATE TABLE \"PlaylistTrack\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
"PlaylistId TrackId\n",
"1 3402\n",
"1 3389\n",
"1 3390\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can use a SELECT statement to get the total number of tracks in each playlist.\n",
"Action: query_checker_sql_db\n",
"Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3m\n",
"\n",
"SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m The query looks correct, I can now execute it.\n",
"Action: query_sql_db\n",
"Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name LIMIT 10\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1)]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Show the total number of tracks in each playlist. The Playlist name should be included in the result.\")"
]
},
{
"cell_type": "markdown",
"id": "7c7503b5-d9d9-4faa-b064-29fcdb5ff213",
"metadata": {},
"source": [
"## Recovering from an error\n",
"\n",
"In this example, the agent is able to recover from an error after initially trying to access an attribute (`Track.ArtistId`) which doesn't exist."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "9fe4901e-f9e1-4022-b6bc-80e2b2d6a3a4",
"metadata": {
"tags": []
},
"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;3mMediaType, Track, Invoice, Album, Playlist, Customer, Employee, InvoiceLine, PlaylistTrack, Genre, Artist\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Artist, InvoiceLine, and Track tables to see what columns I can use.\n",
"Action: schema_sql_db\n",
"Action Input: \"Artist, InvoiceLine, Track\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"Artist\" (\n",
"\t\"ArtistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"ArtistId\")\n",
")\n",
"\n",
"SELECT * FROM 'Artist' LIMIT 3;\n",
"ArtistId Name\n",
"1 AC/DC\n",
"2 Accept\n",
"3 Aerosmith\n",
"\n",
"\n",
"CREATE TABLE \"Track\" (\n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(200) NOT NULL, \n",
"\t\"AlbumId\" INTEGER, \n",
"\t\"MediaTypeId\" INTEGER NOT NULL, \n",
"\t\"GenreId\" INTEGER, \n",
"\t\"Composer\" NVARCHAR(220), \n",
"\t\"Milliseconds\" INTEGER NOT NULL, \n",
"\t\"Bytes\" INTEGER, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\tPRIMARY KEY (\"TrackId\"), \n",
"\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
"\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
"\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
")\n",
"\n",
"SELECT * FROM 'Track' LIMIT 3;\n",
"TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice\n",
"1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99\n",
"2 Balls to the Wall 2 2 1 None 342562 5510424 0.99\n",
"3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99\n",
"\n",
"\n",
"CREATE TABLE \"InvoiceLine\" (\n",
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\t\"Quantity\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
")\n",
"\n",
"SELECT * FROM 'InvoiceLine' LIMIT 3;\n",
"InvoiceLineId InvoiceId TrackId UnitPrice Quantity\n",
"1 1 2 0.99 1\n",
"2 1 4 0.99 1\n",
"3 2 6 0.99 1\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should query the database to get the top 3 best selling artists.\n",
"Action: query_sql_db\n",
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such column: Track.ArtistId\n",
"[SQL: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3]\n",
"(Background on this error at: https://sqlalche.me/e/14/e3q8)\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should double check my query before executing it.\n",
"Action: query_checker_sql_db\n",
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3m\n",
"\n",
"SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity \n",
"FROM Artist \n",
"INNER JOIN Track ON Artist.ArtistId = Track.ArtistId \n",
"INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId \n",
"GROUP BY Artist.Name \n",
"ORDER BY TotalQuantity DESC \n",
"LIMIT 3;\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Action: query_sql_db\n",
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Album ON Artist.ArtistId = Album.ArtistId INNER JOIN Track ON Album.AlbumId = Track.AlbumId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: The top 3 best selling artists are Iron Maiden, U2, and Metallica.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The top 3 best selling artists are Iron Maiden, U2, and Metallica.'"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Who are the top 3 best selling artists?\")"
]
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

417
docs/modules/agents/agent_toolkits/vectorstore.ipynb Normal file
View File

@@ -0,0 +1,417 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "18ada398-dce6-4049-9b56-fc0ede63da9c",
"metadata": {},
"source": [
"# Vectorstore Agent\n",
"\n",
"This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources."
]
},
{
"cell_type": "markdown",
"id": "eecb683b-3a46-4b9d-81a3-7caefbfec1a1",
"metadata": {},
"source": [
"## Create the Vectorstores"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9bfd0ed8-a5eb-443e-8e92-90be8cabb0a7",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain import OpenAI, VectorDBQA\n",
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "345bb078-4ec1-4e3a-827b-cd238c49054d",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"state_of_union_store = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5f50eb82-e1a5-4252-8306-8ec1b478d9b4",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"from langchain.document_loaders import WebBaseLoader\n",
"loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")\n",
"docs = loader.load()\n",
"ruff_texts = text_splitter.split_documents(docs)\n",
"ruff_store = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")"
]
},
{
"cell_type": "markdown",
"id": "f4814175-964d-42f1-aa9d-22801ce1e912",
"metadata": {},
"source": [
"## Initalize Toolkit and Agent\n",
"\n",
"First, we'll create an agent with a single vectorstore."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5b3b3206",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import (\n",
" create_vectorstore_agent,\n",
" VectorStoreToolkit,\n",
" VectorStoreInfo,\n",
")\n",
"vectorstore_info = VectorStoreInfo(\n",
" name=\"state_of_union_address\",\n",
" description=\"the most recent state of the Union adress\",\n",
" vectorstore=state_of_union_store\n",
")\n",
"toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)\n",
"agent_executor = create_vectorstore_agent(\n",
" llm=llm,\n",
" toolkit=toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "8a38ad10",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "3f2f455c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find the answer in the state of the union address\n",
"Action: state_of_union_address\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d61e1e63",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address_with_sources tool to answer this question.\n",
"Action: state_of_union_address_with_sources\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{\"answer\": \" Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\\n\", \"sources\": \"../../state_of_the_union.txt\"}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\""
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address? List the source.\")"
]
},
{
"cell_type": "markdown",
"id": "7ca07707",
"metadata": {},
"source": [
"## Multiple Vectorstores\n",
"We can also easily use this initialize an agent with multiple vectorstores and use the agent to route between them. To do this. This agent is optimized for routing, so it is a different toolkit and initializer."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c3209fd3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import (\n",
" create_vectorstore_router_agent,\n",
" VectorStoreRouterToolkit,\n",
" VectorStoreInfo,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "815c4f39-308d-4949-b992-1361036e6e09",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"ruff_vectorstore_info = VectorStoreInfo(\n",
" name=\"ruff\",\n",
" description=\"Information about the Ruff python linting library\",\n",
" vectorstore=ruff_store\n",
")\n",
"router_toolkit = VectorStoreRouterToolkit(\n",
" vectorstores=[vectorstore_info, ruff_vectorstore_info],\n",
" llm=llm\n",
")\n",
"agent_executor = create_vectorstore_agent(\n",
" llm=llm,\n",
" toolkit=router_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "71680984-edaf-4a63-90f5-94edbd263550",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "3cd1bf3e-e3df-4e69-bbe1-71c64b1af947",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address tool to answer this question.\n",
"Action: state_of_union_address\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "c5998b8d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks\n",
"Action: ruff\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks?\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "744e9b51-fbd9-4778-b594-ea957d0f3467",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses and if the president mentioned it in the state of the union.\n",
"Action: ruff\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out if the president mentioned nbQA in the state of the union.\n",
"Action: state_of_union_address\n",
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'No, the president did not mention nbQA in the state of the union.'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "92203aa9-f63a-4ce1-b562-fadf4474ad9d",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

2
docs/modules/agents/examples/async_agent.ipynb
View File

@@ -403,7 +403,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,

15
docs/modules/agents/how_to_guides.rst
View File

@@ -21,7 +21,7 @@ The first category of how-to guides here cover specific parts of working with ag
`Asynchronous <./examples/async_agent.html>`_: Covering asynchronous functionality.
The next set of examples are all end-to-end agents for specific applications.
The next set of examples are all end-to-end example of different agent types.
In all examples there is an Agent with a particular set of tools.
- Tools: A tool can be anything that takes in a string and returns a string. This means that you can use both the primitives AND the chains found in `this <../chains.html>`_ documentation. LangChain also provides a list of easily loadable tools. For detailed information on those, please see `this documentation <./tools.html>`_
@@ -50,6 +50,19 @@ In all examples there is an Agent with a particular set of tools.
- `Example Notebook <./implementations/react.html>`_
The final set of examples covers agents with toolkits.
As opposed to the examples above, these examples are not intended to show off an agent `type`,
but rather to show off an agent applied to particular use case.
`SQLDatabase Agent <./agent_toolkits/sql_database.html>`_: This notebook covers how to interact with an arbitrary SQL database using an agent.
`JSON Agent <./agent_toolkits/json.html>`_: This notebook covers how to interact with a JSON dictionary using an agent.
`OpenAPI Agent <./agent_toolkits/openapi.html>`_: This notebook covers how to interact with an arbitrary OpenAPI endpoint using an agent.
`VectorStore Agent <./agent_toolkits/vectorstore.html>`_: This notebook covers how to interact with VectorStores using an agent.
`Python Agent <./agent_toolkits/python.html>`_: This notebook covers how to produce and execute python code using an agent.
.. toctree::
:maxdepth: 1

2
docs/modules/agents/implementations/mrkl.ipynb
View File

@@ -205,7 +205,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,

4
docs/modules/agents/implementations/self_ask_with_search.ipynb
View File

@@ -63,7 +63,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.0 64-bit ('llm-env')",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@@ -77,7 +77,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.0"
"version": "3.10.9"
},
"vscode": {
"interpreter": {