forked from Archives/langchain
Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150)
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>searx-doc
Ankush Gola
1 year ago
committed by
GitHub
parent
35f1e8f569
commit
82baecc892
@ -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
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@ -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
|
||||
}
|
||||
@ -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
|
||||
}
|
||||
@ -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
|
||||
}
|
||||
@ -0,0 +1,33 @@
|
||||
"""Agent toolkits."""
|
||||
|
||||
from langchain.agents.agent_toolkits.json.base import create_json_agent
|
||||
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
|
||||
from langchain.agents.agent_toolkits.openapi.base import create_openapi_agent
|
||||
from langchain.agents.agent_toolkits.openapi.toolkit import OpenAPIToolkit
|
||||
from langchain.agents.agent_toolkits.python.base import create_python_agent
|
||||
from langchain.agents.agent_toolkits.sql.base import create_sql_agent
|
||||
from langchain.agents.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
|
||||
from langchain.agents.agent_toolkits.vectorstore.base import (
|
||||
create_vectorstore_agent,
|
||||
create_vectorstore_router_agent,
|
||||
)
|
||||
from langchain.agents.agent_toolkits.vectorstore.toolkit import (
|
||||
VectorStoreInfo,
|
||||
VectorStoreRouterToolkit,
|
||||
VectorStoreToolkit,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"create_json_agent",
|
||||
"create_sql_agent",
|
||||
"create_openapi_agent",
|
||||
"create_python_agent",
|
||||
"create_vectorstore_agent",
|
||||
"JsonToolkit",
|
||||
"SQLDatabaseToolkit",
|
||||
"OpenAPIToolkit",
|
||||
"VectorStoreToolkit",
|
||||
"create_vectorstore_router_agent",
|
||||
"VectorStoreInfo",
|
||||
"VectorStoreRouterToolkit",
|
||||
]
|
||||
@ -0,0 +1,15 @@
|
||||
"""Toolkits for agents."""
|
||||
from abc import abstractmethod
|
||||
from typing import List
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from langchain.tools import BaseTool
|
||||
|
||||
|
||||
class BaseToolkit(BaseModel):
|
||||
"""Class responsible for defining a collection of related tools."""
|
||||
|
||||
@abstractmethod
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
@ -0,0 +1 @@
|
||||
"""Json agent."""
|
||||
@ -0,0 +1,43 @@
|
||||
"""Json agent."""
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from langchain.agents.agent import AgentExecutor
|
||||
from langchain.agents.agent_toolkits.json.prompt import JSON_PREFIX, JSON_SUFFIX
|
||||
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
|
||||
from langchain.agents.mrkl.base import ZeroShotAgent
|
||||
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.llms.base import BaseLLM
|
||||
|
||||
|
||||
def create_json_agent(
|
||||
llm: BaseLLM,
|
||||
toolkit: JsonToolkit,
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
prefix: str = JSON_PREFIX,
|
||||
suffix: str = JSON_SUFFIX,
|
||||
format_instructions: str = FORMAT_INSTRUCTIONS,
|
||||
input_variables: Optional[List[str]] = None,
|
||||
verbose: bool = False,
|
||||
**kwargs: Any,
|
||||
) -> AgentExecutor:
|
||||
"""Construct a json agent from an LLM and tools."""
|
||||
tools = toolkit.get_tools()
|
||||
prompt = ZeroShotAgent.create_prompt(
|
||||
tools,
|
||||
prefix=prefix,
|
||||
suffix=suffix,
|
||||
format_instructions=format_instructions,
|
||||
input_variables=input_variables,
|
||||
)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
return AgentExecutor.from_agent_and_tools(
|
||||
agent=agent, tools=toolkit.get_tools(), verbose=verbose
|
||||
)
|
||||
@ -0,0 +1,25 @@
|
||||
# flake8: noqa
|
||||
|
||||
JSON_PREFIX = """You are an agent designed to interact with JSON.
|
||||
Your goal is to return a final answer by interacting with the JSON.
|
||||
You have access to the following tools which help you learn more about the JSON you are interacting with.
|
||||
Only use the below tools. Only use the information returned by the below tools to construct your final answer.
|
||||
Do not make up any information that is not contained in the JSON.
|
||||
Your input to the tools should be in the form of `data["key"][0]` where `data` is the JSON blob you are interacting with, and the syntax used is Python.
|
||||
You should only use keys that you know for a fact exist. You must validate that a key exists by seeing it previously when calling `json_spec_list_keys`.
|
||||
If you have not seen a key in one of those responses, you cannot use it.
|
||||
You should only add one key at a time to the path. You cannot add multiple keys at once.
|
||||
If you encounter a "KeyError", go back to the previous key, look at the available keys, and try again.
|
||||
|
||||
If the question does not seem to be related to the JSON, just return "I don't know" as the answer.
|
||||
Always begin your interaction with the `json_spec_list_keys` tool with input "data" to see what keys exist in the JSON.
|
||||
|
||||
Note that sometimes the value at a given path is large. In this case, you will get an error "Value is a large dictionary, should explore its keys directly".
|
||||
In this case, you should ALWAYS follow up by using the `json_spec_list_keys` tool to see what keys exist at that path.
|
||||
Do not simply refer the user to the JSON or a section of the JSON, as this is not a valid answer. Keep digging until you find the answer and explicitly return it.
|
||||
"""
|
||||
JSON_SUFFIX = """Begin!"
|
||||
|
||||
Question: {input}
|
||||
Thought: I should look at the keys that exist in data to see what I have access to
|
||||
{agent_scratchpad}"""
|
||||
@ -0,0 +1,21 @@
|
||||
"""Toolkit for interacting with a JSON spec."""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import List
|
||||
|
||||
from langchain.agents.agent_toolkits.base import BaseToolkit
|
||||
from langchain.tools import BaseTool
|
||||
from langchain.tools.json.tool import JsonGetValueTool, JsonListKeysTool, JsonSpec
|
||||
|
||||
|
||||
class JsonToolkit(BaseToolkit):
|
||||
"""Toolkit for interacting with a JSON spec."""
|
||||
|
||||
spec: JsonSpec
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
return [
|
||||
JsonListKeysTool(spec=self.spec),
|
||||
JsonGetValueTool(spec=self.spec),
|
||||
]
|
||||
@ -0,0 +1 @@
|
||||
"""OpenAPI spec agent."""
|
||||
@ -0,0 +1,46 @@
|
||||
"""OpenAPI spec agent."""
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from langchain.agents.agent import AgentExecutor
|
||||
from langchain.agents.agent_toolkits.openapi.prompt import (
|
||||
OPENAPI_PREFIX,
|
||||
OPENAPI_SUFFIX,
|
||||
)
|
||||
from langchain.agents.agent_toolkits.openapi.toolkit import OpenAPIToolkit
|
||||
from langchain.agents.mrkl.base import ZeroShotAgent
|
||||
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.llms.base import BaseLLM
|
||||
|
||||
|
||||
def create_openapi_agent(
|
||||
llm: BaseLLM,
|
||||
toolkit: OpenAPIToolkit,
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
prefix: str = OPENAPI_PREFIX,
|
||||
suffix: str = OPENAPI_SUFFIX,
|
||||
format_instructions: str = FORMAT_INSTRUCTIONS,
|
||||
input_variables: Optional[List[str]] = None,
|
||||
verbose: bool = False,
|
||||
**kwargs: Any,
|
||||
) -> AgentExecutor:
|
||||
"""Construct a json agent from an LLM and tools."""
|
||||
tools = toolkit.get_tools()
|
||||
prompt = ZeroShotAgent.create_prompt(
|
||||
tools,
|
||||
prefix=prefix,
|
||||
suffix=suffix,
|
||||
format_instructions=format_instructions,
|
||||
input_variables=input_variables,
|
||||
)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
return AgentExecutor.from_agent_and_tools(
|
||||
agent=agent, tools=toolkit.get_tools(), verbose=verbose
|
||||
)
|
||||
@ -0,0 +1,29 @@
|
||||
# flake8: noqa
|
||||
|
||||
OPENAPI_PREFIX = """You are an agent designed to answer questions by making web requests to an API given the openapi spec.
|
||||
|
||||
If the question does not seem related to the API, return I don't know. Do not make up an answer.
|
||||
Only use information provided by the tools to construct your response.
|
||||
|
||||
First, find the base URL needed to make the request.
|
||||
|
||||
Second, find the relevant paths needed to answer the question. Take note that, sometimes, you might need to make more than one request to more than one path to answer the question.
|
||||
|
||||
Third, find the required parameters needed to make the request. For GET requests, these are usually URL parameters and for POST requests, these are request body parameters.
|
||||
|
||||
Fourth, make the requests needed to answer the question. Ensure that you are sending the correct parameters to the request by checking which parameters are required. For parameters with a fixed set of values, please use the spec to look at which values are allowed.
|
||||
|
||||
Use the exact parameter names as listed in the spec, do not make up any names or abbreviate the names of parameters.
|
||||
If you get a not found error, ensure that you are using a path that actually exists in the spec.
|
||||
"""
|
||||
OPENAPI_SUFFIX = """Begin!"
|
||||
|
||||
Question: {input}
|
||||
Thought: I should explore the spec to find the base url for the API.
|
||||
{agent_scratchpad}"""
|
||||
|
||||
DESCRIPTION = """Can be used to answer questions about the openapi spec for the API. Always use this tool before trying to make a request.
|
||||
Example inputs to this tool:
|
||||
'What are the required query parameters for a GET request to the /bar endpoint?`
|
||||
'What are the required parameters in the request body for a POST request to the /foo endpoint?'
|
||||
Always give this tool a specific question."""
|
||||
@ -0,0 +1,67 @@
|
||||
"""Requests toolkit."""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, List
|
||||
|
||||
from langchain.agents.agent import AgentExecutor
|
||||
from langchain.agents.agent_toolkits.base import BaseToolkit
|
||||
from langchain.agents.agent_toolkits.json.base import create_json_agent
|
||||
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
|
||||
from langchain.agents.agent_toolkits.openapi.prompt import DESCRIPTION
|
||||
from langchain.agents.tools import Tool
|
||||
from langchain.llms.base import BaseLLM
|
||||
from langchain.requests import RequestsWrapper
|
||||
from langchain.tools import BaseTool
|
||||
from langchain.tools.json.tool import JsonSpec
|
||||
from langchain.tools.requests.tool import (
|
||||
RequestsDeleteTool,
|
||||
RequestsGetTool,
|
||||
RequestsPatchTool,
|
||||
RequestsPostTool,
|
||||
RequestsPutTool,
|
||||
)
|
||||
|
||||
|
||||
class RequestsToolkit(BaseToolkit):
|
||||
"""Toolkit for making requests."""
|
||||
|
||||
requests_wrapper: RequestsWrapper
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Return a list of tools."""
|
||||
return [
|
||||
RequestsGetTool(requests_wrapper=self.requests_wrapper),
|
||||
RequestsPostTool(requests_wrapper=self.requests_wrapper),
|
||||
RequestsPatchTool(requests_wrapper=self.requests_wrapper),
|
||||
RequestsPutTool(requests_wrapper=self.requests_wrapper),
|
||||
RequestsDeleteTool(requests_wrapper=self.requests_wrapper),
|
||||
]
|
||||
|
||||
|
||||
class OpenAPIToolkit(BaseToolkit):
|
||||
"""Toolkit for interacting with a OpenAPI api."""
|
||||
|
||||
json_agent: AgentExecutor
|
||||
requests_wrapper: RequestsWrapper
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
json_agent_tool = Tool(
|
||||
name="json_explorer",
|
||||
func=self.json_agent.run,
|
||||
description=DESCRIPTION,
|
||||
)
|
||||
request_toolkit = RequestsToolkit(requests_wrapper=self.requests_wrapper)
|
||||
return [*request_toolkit.get_tools(), json_agent_tool]
|
||||
|
||||
@classmethod
|
||||
def from_llm(
|
||||
cls,
|
||||
llm: BaseLLM,
|
||||
json_spec: JsonSpec,
|
||||
requests_wrapper: RequestsWrapper,
|
||||
**kwargs: Any,
|
||||
) -> OpenAPIToolkit:
|
||||
"""Create json agent from llm, then initialize."""
|
||||
json_agent = create_json_agent(llm, JsonToolkit(spec=json_spec), **kwargs)
|
||||
return cls(json_agent=json_agent, requests_wrapper=requests_wrapper)
|
||||
@ -0,0 +1,31 @@
|
||||
"""Python agent."""
|
||||
|
||||
from typing import Any, Optional
|
||||
|
||||
from langchain.agents.agent import AgentExecutor
|
||||
from langchain.agents.agent_toolkits.python.prompt import PREFIX
|
||||
from langchain.agents.mrkl.base import ZeroShotAgent
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.llms.base import BaseLLM
|
||||
from langchain.tools.python.tool import PythonREPLTool
|
||||
|
||||
|
||||
def create_python_agent(
|
||||
llm: BaseLLM,
|
||||
tool: PythonREPLTool,
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
verbose: bool = False,
|
||||
**kwargs: Any,
|
||||
) -> AgentExecutor:
|
||||
"""Construct a python agent from an LLM and tool."""
|
||||
tools = [tool]
|
||||
prompt = ZeroShotAgent.create_prompt(tools, prefix=PREFIX)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)
|
||||
@ -0,0 +1,9 @@
|
||||
# flake8: noqa
|
||||
|
||||
PREFIX = """You are an agent designed to write and execute python code to answer questions.
|
||||
You have access to a python REPL, which you can use to execute python code.
|
||||
If you get an error, debug your code and try again.
|
||||
Only use the output of your code to answer the question.
|
||||
You might know the answer without running any code, but you should still run the code to get the answer.
|
||||
If it does not seem like you can write code to answer the question, just return "I don't know" as the answer.
|
||||
"""
|
||||
@ -0,0 +1 @@
|
||||
"""SQL agent."""
|
||||
@ -0,0 +1,45 @@
|
||||
"""SQL agent."""
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from langchain.agents.agent import AgentExecutor
|
||||
from langchain.agents.agent_toolkits.sql.prompt import SQL_PREFIX, SQL_SUFFIX
|
||||
from langchain.agents.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
|
||||
from langchain.agents.mrkl.base import ZeroShotAgent
|
||||
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.llms.base import BaseLLM
|
||||
|
||||
|
||||
def create_sql_agent(
|
||||
llm: BaseLLM,
|
||||
toolkit: SQLDatabaseToolkit,
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
prefix: str = SQL_PREFIX,
|
||||
suffix: str = SQL_SUFFIX,
|
||||
format_instructions: str = FORMAT_INSTRUCTIONS,
|
||||
input_variables: Optional[List[str]] = None,
|
||||
top_k: int = 10,
|
||||
verbose: bool = False,
|
||||
**kwargs: Any,
|
||||
) -> AgentExecutor:
|
||||
"""Construct a sql agent from an LLM and tools."""
|
||||
tools = toolkit.get_tools()
|
||||
prefix = prefix.format(dialect=toolkit.dialect, top_k=top_k)
|
||||
prompt = ZeroShotAgent.create_prompt(
|
||||
tools,
|
||||
prefix=prefix,
|
||||
suffix=suffix,
|
||||
format_instructions=format_instructions,
|
||||
input_variables=input_variables,
|
||||
)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
return AgentExecutor.from_agent_and_tools(
|
||||
agent=agent, tools=toolkit.get_tools(), verbose=verbose
|
||||
)
|
||||
@ -0,0 +1,21 @@
|
||||
# flake8: noqa
|
||||
|
||||
SQL_PREFIX = """You are an agent designed to interact with a SQL database.
|
||||
Given an input question, create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.
|
||||
Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results using the LIMIT clause.
|
||||
You can order the results by a relevant column to return the most interesting examples in the database.
|
||||
Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
|
||||
You have access to tools for interacting with the database.
|
||||
Only use the below tools. Only use the information returned by the below tools to construct your final answer.
|
||||
You MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.
|
||||
|
||||
DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
|
||||
|
||||
If the question does not seem related to the database, just return "I don't know" as the answer.
|
||||
"""
|
||||
|
||||
SQL_SUFFIX = """Begin!
|
||||
|
||||
Question: {input}
|
||||
Thought: I should look at the tables in the database to see what I can query.
|
||||
{agent_scratchpad}"""
|
||||
@ -0,0 +1,39 @@
|
||||
"""Toolkit for interacting with a SQL database."""
|
||||
from typing import List
|
||||
|
||||
from pydantic import Field
|
||||
|
||||
from langchain.agents.agent_toolkits.base import BaseToolkit
|
||||
from langchain.sql_database import SQLDatabase
|
||||
from langchain.tools import BaseTool
|
||||
from langchain.tools.sql_database.tool import (
|
||||
InfoSQLDatabaseTool,
|
||||
ListSQLDatabaseTool,
|
||||
QueryCheckerTool,
|
||||
QuerySQLDataBaseTool,
|
||||
)
|
||||
|
||||
|
||||
class SQLDatabaseToolkit(BaseToolkit):
|
||||
"""Toolkit for interacting with SQL databases."""
|
||||
|
||||
db: SQLDatabase = Field(exclude=True)
|
||||
|
||||
@property
|
||||
def dialect(self) -> str:
|
||||
"""Return string representation of dialect to use."""
|
||||
return self.db.dialect
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
return [
|
||||
QuerySQLDataBaseTool(db=self.db),
|
||||
InfoSQLDatabaseTool(db=self.db),
|
||||
ListSQLDatabaseTool(db=self.db),
|
||||
QueryCheckerTool(db=self.db),
|
||||
]
|
||||
@ -0,0 +1 @@
|
||||
"""Agent toolkit for interacting with vector stores."""
|
||||
@ -0,0 +1,55 @@
|
||||
"""VectorStore agent."""
|
||||
from typing import Any, Optional
|
||||
|
||||
from langchain.agents.agent import AgentExecutor
|
||||
from langchain.agents.agent_toolkits.vectorstore.prompt import PREFIX, ROUTER_PREFIX
|
||||
from langchain.agents.agent_toolkits.vectorstore.toolkit import (
|
||||
VectorStoreRouterToolkit,
|
||||
VectorStoreToolkit,
|
||||
)
|
||||
from langchain.agents.mrkl.base import ZeroShotAgent
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.llms.base import BaseLLM
|
||||
|
||||
|
||||
def create_vectorstore_agent(
|
||||
llm: BaseLLM,
|
||||
toolkit: VectorStoreToolkit,
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
prefix: str = PREFIX,
|
||||
verbose: bool = False,
|
||||
**kwargs: Any,
|
||||
) -> AgentExecutor:
|
||||
"""Construct a vectorstore agent from an LLM and tools."""
|
||||
tools = toolkit.get_tools()
|
||||
prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)
|
||||
|
||||
|
||||
def create_vectorstore_router_agent(
|
||||
llm: BaseLLM,
|
||||
toolkit: VectorStoreRouterToolkit,
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
prefix: str = ROUTER_PREFIX,
|
||||
verbose: bool = False,
|
||||
**kwargs: Any,
|
||||
) -> AgentExecutor:
|
||||
"""Construct a vectorstore router agent from an LLM and tools."""
|
||||
tools = toolkit.get_tools()
|
||||
prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)
|
||||
@ -0,0 +1,13 @@
|
||||
# flake8: noqa
|
||||
|
||||
PREFIX = """You are an agent designed to answer questions about sets of documents.
|
||||
You have access to tools for interacting with the documents, and the inputs to the tools are questions.
|
||||
Sometimes, you will be asked to provide sources for your questions, in which case you should use the appropriate tool to do so.
|
||||
If the question does not seem relevant to any of the tools provided, just return "I don't know" as the answer.
|
||||
"""
|
||||
|
||||
ROUTER_PREFIX = """You are an agent designed to answer questions.
|
||||
You have access to tools for interacting with different sources, and the inputs to the tools are questions.
|
||||
Your main task is to decide which of the tools is relevant for answering question at hand.
|
||||
For complex questions, you can break the question down into sub questions and use tools to answers the sub questions.
|
||||
"""
|
||||
@ -0,0 +1,89 @@
|
||||
"""Toolkit for interacting with a vector store."""
|
||||
from typing import List
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from langchain.agents.agent_toolkits.base import BaseToolkit
|
||||
from langchain.llms.base import BaseLLM
|
||||
from langchain.llms.openai import OpenAI
|
||||
from langchain.tools import BaseTool
|
||||
from langchain.tools.vectorstore.tool import (
|
||||
VectorStoreQATool,
|
||||
VectorStoreQAWithSourcesTool,
|
||||
)
|
||||
from langchain.vectorstores.base import VectorStore
|
||||
|
||||
|
||||
class VectorStoreInfo(BaseModel):
|
||||
"""Information about a vectorstore."""
|
||||
|
||||
vectorstore: VectorStore = Field(exclude=True)
|
||||
name: str
|
||||
description: str
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
|
||||
class VectorStoreToolkit(BaseToolkit):
|
||||
"""Toolkit for interacting with a vector store."""
|
||||
|
||||
vectorstore_info: VectorStoreInfo = Field(exclude=True)
|
||||
llm: BaseLLM = Field(default_factory=lambda: OpenAI(temperature=0))
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
description = VectorStoreQATool.get_description(
|
||||
self.vectorstore_info.name, self.vectorstore_info.description
|
||||
)
|
||||
qa_tool = VectorStoreQATool(
|
||||
name=self.vectorstore_info.name,
|
||||
description=description,
|
||||
vectorstore=self.vectorstore_info.vectorstore,
|
||||
llm=self.llm,
|
||||
)
|
||||
description = VectorStoreQAWithSourcesTool.get_description(
|
||||
self.vectorstore_info.name, self.vectorstore_info.description
|
||||
)
|
||||
qa_with_sources_tool = VectorStoreQAWithSourcesTool(
|
||||
name=f"{self.vectorstore_info.name}_with_sources",
|
||||
description=description,
|
||||
vectorstore=self.vectorstore_info.vectorstore,
|
||||
llm=self.llm,
|
||||
)
|
||||
return [qa_tool, qa_with_sources_tool]
|
||||
|
||||
|
||||
class VectorStoreRouterToolkit(BaseToolkit):
|
||||
"""Toolkit for routing between vectorstores."""
|
||||
|
||||
vectorstores: List[VectorStoreInfo] = Field(exclude=True)
|
||||
llm: BaseLLM = Field(default_factory=lambda: OpenAI(temperature=0))
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
tools: List[BaseTool] = []
|
||||
for vectorstore_info in self.vectorstores:
|
||||
description = VectorStoreQATool.get_description(
|
||||
vectorstore_info.name, vectorstore_info.description
|
||||
)
|
||||
qa_tool = VectorStoreQATool(
|
||||
name=vectorstore_info.name,
|
||||
description=description,
|
||||
vectorstore=vectorstore_info.vectorstore,
|
||||
llm=self.llm,
|
||||
)
|
||||
tools.append(qa_tool)
|
||||
return tools
|
||||
@ -1,15 +1,73 @@
|
||||
"""Lightweight wrapper around request library."""
|
||||
from typing import Optional
|
||||
"""Lightweight wrapper around requests library, with async support."""
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import aiohttp
|
||||
import requests
|
||||
from pydantic import BaseModel
|
||||
from pydantic import BaseModel, Extra
|
||||
|
||||
|
||||
class RequestsWrapper(BaseModel):
|
||||
"""Lightweight wrapper to partial out everything except the url to hit."""
|
||||
"""Lightweight wrapper around requests library."""
|
||||
|
||||
headers: Optional[dict] = None
|
||||
headers: Optional[Dict[str, str]] = None
|
||||
aiosession: Optional[aiohttp.ClientSession] = None
|
||||
|
||||
def run(self, url: str) -> str:
|
||||
"""Hit the URL and return the text."""
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
extra = Extra.forbid
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
def get(self, url: str) -> str:
|
||||
"""GET the URL and return the text."""
|
||||
return requests.get(url, headers=self.headers).text
|
||||
|
||||
def post(self, url: str, data: Dict[str, Any]) -> str:
|
||||
"""POST to the URL and return the text."""
|
||||
return requests.post(url, json=data, headers=self.headers).text
|
||||
|
||||
def patch(self, url: str, data: Dict[str, Any]) -> str:
|
||||
"""PATCH the URL and return the text."""
|
||||
return requests.patch(url, json=data, headers=self.headers).text
|
||||
|
||||
def put(self, url: str, data: Dict[str, Any]) -> str:
|
||||
"""PUT the URL and return the text."""
|
||||
return requests.put(url, json=data, headers=self.headers).text
|
||||
|
||||
def delete(self, url: str) -> str:
|
||||
"""DELETE the URL and return the text."""
|
||||
return requests.delete(url, headers=self.headers).text
|
||||
|
||||
async def _arequest(self, method: str, url: str, **kwargs: Any) -> str:
|
||||
"""Make an async request."""
|
||||
if not self.aiosession:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.request(
|
||||
method, url, headers=self.headers, **kwargs
|
||||
) as response:
|
||||
return await response.text()
|
||||
else:
|
||||
async with self.aiosession.request(
|
||||
method, url, headers=self.headers, **kwargs
|
||||
) as response:
|
||||
return await response.text()
|
||||
|
||||
async def aget(self, url: str) -> str:
|
||||
"""GET the URL and return the text asynchronously."""
|
||||
return await self._arequest("GET", url)
|
||||
|
||||
async def apost(self, url: str, data: Dict[str, Any]) -> str:
|
||||
"""POST to the URL and return the text asynchronously."""
|
||||
return await self._arequest("POST", url, json=data)
|
||||
|
||||
async def apatch(self, url: str, data: Dict[str, Any]) -> str:
|
||||
"""PATCH the URL and return the text asynchronously."""
|
||||
return await self._arequest("PATCH", url, json=data)
|
||||
|
||||
async def aput(self, url: str, data: Dict[str, Any]) -> str:
|
||||
"""PUT the URL and return the text asynchronously."""
|
||||
return await self._arequest("PUT", url, json=data)
|
||||
|
||||
async def adelete(self, url: str) -> str:
|
||||
"""DELETE the URL and return the text asynchronously."""
|
||||
return await self._arequest("DELETE", url)
|
||||
|
||||
@ -1,26 +0,0 @@
|
||||
"""Tool for the Bing search API."""
|
||||
|
||||
from typing import List
|
||||
|
||||
from langchain.tools.base import BaseTool, BaseToolkit
|
||||
from langchain.tools.bing_search.tool import BingSearchRun
|
||||
from langchain.utilities.bing_search import BingSearchAPIWrapper
|
||||
|
||||
|
||||
class BingSearchToolkit(BaseToolkit):
|
||||
"""Tool that adds the capability to query the Bing search API."""
|
||||
|
||||
bing_subscription_key: str
|
||||
bing_search_url: str
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
wrapper = BingSearchAPIWrapper(
|
||||
bing_subscription_key=self.bing_subscription_key,
|
||||
bing_search_url=self.bing_search_url,
|
||||
)
|
||||
return [
|
||||
BingSearchRun(
|
||||
api_wrapper=wrapper,
|
||||
)
|
||||
]
|
||||
@ -1,26 +0,0 @@
|
||||
"""Tool for the Google search API."""
|
||||
|
||||
from typing import List
|
||||
|
||||
from langchain.tools.base import BaseTool, BaseToolkit
|
||||
from langchain.tools.google_search.tool import GoogleSearchRun
|
||||
from langchain.utilities.google_search import GoogleSearchAPIWrapper
|
||||
|
||||
|
||||
class GoogleSearchToolkit(BaseToolkit):
|
||||
"""Tool that adds the capability to query the Google search API."""
|
||||
|
||||
google_subscription_key: str
|
||||
google_search_url: str
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
wrapper = GoogleSearchAPIWrapper(
|
||||
google_api_key=self.google_subscription_key,
|
||||
google_search_url=self.google_search_url,
|
||||
)
|
||||
return [
|
||||
GoogleSearchRun(
|
||||
api_wrapper=wrapper,
|
||||
)
|
||||
]
|
||||
@ -0,0 +1 @@
|
||||
"""Tools for interacting with a JSON file."""
|
||||
@ -0,0 +1,113 @@
|
||||
# flake8: noqa
|
||||
"""Tools for working with JSON specs."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from langchain.tools.base import BaseTool
|
||||
|
||||
|
||||
def _parse_input(text: str) -> List[Union[str, int]]:
|
||||
"""Parse input of the form data["key1"][0]["key2"] into a list of keys."""
|
||||
_res = re.findall(r"\[.*?]", text)
|
||||
# strip the brackets and quotes, convert to int if possible
|
||||
res = [i[1:-1].replace('"', "") for i in _res]
|
||||
res = [int(i) if i.isdigit() else i for i in res]
|
||||
return res
|
||||
|
||||
|
||||
class JsonSpec(BaseModel):
|
||||
"""Base class for JSON spec."""
|
||||
|
||||
dict_: Dict
|
||||
max_value_length: int = 200
|
||||
|
||||
@classmethod
|
||||
def from_file(cls, path: Path) -> JsonSpec:
|
||||
"""Create a JsonSpec from a file."""
|
||||
if not path.exists():
|
||||
raise FileNotFoundError(f"File not found: {path}")
|
||||
dict_ = json.loads(path.read_text())
|
||||
return cls(dict_=dict_)
|
||||
|
||||
def keys(self, text: str) -> str:
|
||||
"""Return the keys of the dict at the given path.
|
||||
|
||||
Args:
|
||||
text: Python representation of the path to the dict (e.g. data["key1"][0]["key2"]).
|
||||
"""
|
||||
try:
|
||||
items = _parse_input(text)
|
||||
val = self.dict_
|
||||
for i in items:
|
||||
if i:
|
||||
val = val[i]
|
||||
if not isinstance(val, dict):
|
||||
raise ValueError(
|
||||
f"Value at path `{text}` is not a dict, get the value directly."
|
||||
)
|
||||
return str(list(val.keys()))
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
def value(self, text: str) -> str:
|
||||
"""Return the value of the dict at the given path.
|
||||
|
||||
Args:
|
||||
text: Python representation of the path to the dict (e.g. data["key1"][0]["key2"]).
|
||||
"""
|
||||
try:
|
||||
items = _parse_input(text)
|
||||
val = self.dict_
|
||||
for i in items:
|
||||
val = val[i]
|
||||
|
||||
if isinstance(val, dict) and len(str(val)) > self.max_value_length:
|
||||
return "Value is a large dictionary, should explore its keys directly"
|
||||
str_val = str(val)
|
||||
if len(str_val) > self.max_value_length:
|
||||
str_val = str_val[: self.max_value_length] + "..."
|
||||
return str_val
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
|
||||
class JsonListKeysTool(BaseTool):
|
||||
"""Tool for listing keys in a JSON spec."""
|
||||
|
||||
name = "json_spec_list_keys"
|
||||
description = """
|
||||
Can be used to list all keys at a given path.
|
||||
Before calling this you should be SURE that the path to this exists.
|
||||
The input is a text representation of the path to the dict in Python syntax (e.g. data["key1"][0]["key2"]).
|
||||
"""
|
||||
spec: JsonSpec
|
||||
|
||||
def _run(self, tool_input: str) -> str:
|
||||
return self.spec.keys(tool_input)
|
||||
|
||||
async def _arun(self, tool_input: str) -> str:
|
||||
return self._run(tool_input)
|
||||
|
||||
|
||||
class JsonGetValueTool(BaseTool):
|
||||
"""Tool for getting a value in a JSON spec."""
|
||||
|
||||
name = "json_spec_get_value"
|
||||
description = """
|
||||
Can be used to see value in string format at a given path.
|
||||
Before calling this you should be SURE that the path to this exists.
|
||||
The input is a text representation of the path to the dict in Python syntax (e.g. data["key1"][0]["key2"]).
|
||||
"""
|
||||
spec: JsonSpec
|
||||
|
||||
def _run(self, tool_input: str) -> str:
|
||||
return self.spec.value(tool_input)
|
||||
|
||||
async def _arun(self, tool_input: str) -> str:
|
||||
return self._run(tool_input)
|
||||
@ -0,0 +1,30 @@
|
||||
"""A tool for running python code in a REPL."""
|
||||
|
||||
from pydantic import Field
|
||||
|
||||
from langchain.python import PythonREPL
|
||||
from langchain.tools.base import BaseTool
|
||||
|
||||
|
||||
def _get_default_python_repl() -> PythonREPL:
|
||||
return PythonREPL(_globals=globals(), _locals=None)
|
||||
|
||||
|
||||
class PythonREPLTool(BaseTool):
|
||||
"""A tool for running python code in a REPL."""
|
||||
|
||||
name = "Python REPL"
|
||||
description = (
|
||||
"A Python shell. Use this to execute python commands. "
|
||||
"Input should be a valid python command. "
|
||||
"If you expect output it should be printed out."
|
||||
)
|
||||
python_repl: PythonREPL = Field(default_factory=_get_default_python_repl)
|
||||
|
||||
def _run(self, query: str) -> str:
|
||||
"""Use the tool."""
|
||||
return self.python_repl.run(query)
|
||||
|
||||
async def _arun(self, query: str) -> str:
|
||||
"""Use the tool asynchronously."""
|
||||
raise NotImplementedError("PythonReplTool does not support async")
|
||||
@ -0,0 +1 @@
|
||||
"""Tools for making requests to an API endpoint."""
|
||||
@ -0,0 +1,137 @@
|
||||
# flake8: noqa
|
||||
"""Tools for making requests to an API endpoint."""
|
||||
import json
|
||||
from typing import Any, Dict
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from langchain.requests import RequestsWrapper
|
||||
from langchain.tools.base import BaseTool
|
||||
|
||||
|
||||
def _parse_input(text: str) -> Dict[str, Any]:
|
||||
"""Parse the json string into a dict."""
|
||||
return json.loads(text)
|
||||
|
||||
|
||||
class BaseRequestsTool(BaseModel):
|
||||
"""Base class for requests tools."""
|
||||
|
||||
requests_wrapper: RequestsWrapper
|
||||
|
||||
|
||||
class RequestsGetTool(BaseRequestsTool, BaseTool):
|
||||
"""Tool for making a GET request to an API endpoint."""
|
||||
|
||||
name = "requests_get"
|
||||
description = "A portal to the internet. Use this when you need to get specific content from a website. Input should be a url (i.e. https://www.google.com). The output will be the text response of the GET request."
|
||||
|
||||
def _run(self, url: str) -> str:
|
||||
"""Run the tool."""
|
||||
return self.requests_wrapper.get(url)
|
||||
|
||||
async def _arun(self, url: str) -> str:
|
||||
"""Run the tool asynchronously."""
|
||||
return await self.requests_wrapper.aget(url)
|
||||
|
||||
|
||||
class RequestsPostTool(BaseRequestsTool, BaseTool):
|
||||
"""Tool for making a POST request to an API endpoint."""
|
||||
|
||||
name = "requests_post"
|
||||
description = """Use this when you want to POST to a website.
|
||||
Input should be a json string with two keys: "url" and "data".
|
||||
The value of "url" should be a string, and the value of "data" should be a dictionary of
|
||||
key-value pairs you want to POST to the url.
|
||||
Be careful to always use double quotes for strings in the json string
|
||||
The output will be the text response of the POST request.
|
||||
"""
|
||||
|
||||
def _run(self, text: str) -> str:
|
||||
"""Run the tool."""
|
||||
try:
|
||||
data = _parse_input(text)
|
||||
return self.requests_wrapper.post(data["url"], data["data"])
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
async def _arun(self, text: str) -> str:
|
||||
"""Run the tool asynchronously."""
|
||||
try:
|
||||
data = _parse_input(text)
|
||||
return await self.requests_wrapper.apost(data["url"], data["data"])
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
|
||||
class RequestsPatchTool(BaseRequestsTool, BaseTool):
|
||||
"""Tool for making a PATCH request to an API endpoint."""
|
||||
|
||||
name = "requests_patch"
|
||||
description = """Use this when you want to PATCH to a website.
|
||||
Input should be a json string with two keys: "url" and "data".
|
||||
The value of "url" should be a string, and the value of "data" should be a dictionary of
|
||||
key-value pairs you want to PATCH to the url.
|
||||
Be careful to always use double quotes for strings in the json string
|
||||
The output will be the text response of the PATCH request.
|
||||
"""
|
||||
|
||||
def _run(self, text: str) -> str:
|
||||
"""Run the tool."""
|
||||
try:
|
||||
data = _parse_input(text)
|
||||
return self.requests_wrapper.patch(data["url"], data["data"])
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
async def _arun(self, text: str) -> str:
|
||||
"""Run the tool asynchronously."""
|
||||
try:
|
||||
data = _parse_input(text)
|
||||
return await self.requests_wrapper.apatch(data["url"], data["data"])
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
|
||||
class RequestsPutTool(BaseRequestsTool, BaseTool):
|
||||
"""Tool for making a PUT request to an API endpoint."""
|
||||
|
||||
name = "requests_put"
|
||||
description = """Use this when you want to PUT to a website.
|
||||
Input should be a json string with two keys: "url" and "data".
|
||||
The value of "url" should be a string, and the value of "data" should be a dictionary of
|
||||
key-value pairs you want to PUT to the url.
|
||||
Be careful to always use double quotes for strings in the json string.
|
||||
The output will be the text response of the PUT request.
|
||||
"""
|
||||
|
||||
def _run(self, text: str) -> str:
|
||||
"""Run the tool."""
|
||||
try:
|
||||
data = _parse_input(text)
|
||||
return self.requests_wrapper.put(data["url"], data["data"])
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
async def _arun(self, text: str) -> str:
|
||||
"""Run the tool asynchronously."""
|
||||
try:
|
||||
data = _parse_input(text)
|
||||
return await self.requests_wrapper.aput(data["url"], data["data"])
|
||||
except Exception as e:
|
||||
return repr(e)
|
||||
|
||||
|
||||
class RequestsDeleteTool(BaseRequestsTool, BaseTool):
|
||||
"""Tool for making a DELETE request to an API endpoint."""
|
||||
|
||||
name = "requests_delete"
|
||||
description = "A portal to the internet. Use this when you need to make a DELETE request to a URL. Input should be a specific url, and the output will be the text response of the DELETE request."
|
||||
|
||||
def _run(self, url: str) -> str:
|
||||
"""Run the tool."""
|
||||
return self.requests_wrapper.delete(url)
|
||||
|
||||
async def _arun(self, url: str) -> str:
|
||||
"""Run the tool asynchronously."""
|
||||
return await self.requests_wrapper.adelete(url)
|
||||
@ -0,0 +1 @@
|
||||
"""Tools for interacting with a SQL database."""
|
||||
@ -0,0 +1,14 @@
|
||||
# flake8: noqa
|
||||
QUERY_CHECKER = """
|
||||
{query}
|
||||
Double check the {dialect} query above for common mistakes, including:
|
||||
- Using NOT IN with NULL values
|
||||
- Using UNION when UNION ALL should have been used
|
||||
- Using BETWEEN for exclusive ranges
|
||||
- Data type mismatch in predicates
|
||||
- Properly quoting identifiers
|
||||
- Using the correct number of arguments for functions
|
||||
- Casting to the correct data type
|
||||
- Using the proper columns for joins
|
||||
|
||||
If there are any of the above mistakes, rewrite the query. If there are no mistakes, just reproduce the original query."""
|
||||
@ -0,0 +1,111 @@
|
||||
# flake8: noqa
|
||||
"""Tools for interacting with a SQL database."""
|
||||
from pydantic import BaseModel, Extra, Field, validator
|
||||
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.llms.openai import OpenAI
|
||||
from langchain.prompts import PromptTemplate
|
||||
from langchain.sql_database import SQLDatabase
|
||||
from langchain.tools.base import BaseTool
|
||||
from langchain.tools.sql_database.prompt import QUERY_CHECKER
|
||||
|
||||
|
||||
class BaseSQLDatabaseTool(BaseModel):
|
||||
"""Base tool for interacting with a SQL database."""
|
||||
|
||||
db: SQLDatabase = Field(exclude=True)
|
||||
|
||||
# Override BaseTool.Config to appease mypy
|
||||
# See https://github.com/pydantic/pydantic/issues/4173
|
||||
class Config(BaseTool.Config):
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
extra = Extra.forbid
|
||||
|
||||
|
||||
class QuerySQLDataBaseTool(BaseSQLDatabaseTool, BaseTool):
|
||||
"""Tool for querying a SQL database."""
|
||||
|
||||
name = "query_sql_db"
|
||||
description = """
|
||||
Input to this tool is a detailed and correct SQL query, output is a result from the database.
|
||||
If the query is not correct, an error message will be returned.
|
||||
If an error is returned, rewrite the query, check the query, and try again.
|
||||
"""
|
||||
|
||||
def _run(self, query: str) -> str:
|
||||
"""Execute the query, return the results or an error message."""
|
||||
return self.db.run_no_throw(query)
|
||||
|
||||
async def _arun(self, query: str) -> str:
|
||||
raise NotImplementedError("QuerySqlDbTool does not support async")
|
||||
|
||||
|
||||
class InfoSQLDatabaseTool(BaseSQLDatabaseTool, BaseTool):
|
||||
"""Tool for getting metadata about a SQL database."""
|
||||
|
||||
name = "schema_sql_db"
|
||||
description = """
|
||||
Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.
|
||||
Be sure that the tables actually exist by calling list_tables_sql_db first!
|
||||
|
||||
Example Input: "table1, table2, table3"
|
||||
"""
|
||||
|
||||
def _run(self, table_names: str) -> str:
|
||||
"""Get the schema for tables in a comma-separated list."""
|
||||
return self.db.get_table_info_no_throw(table_names.split(", "))
|
||||
|
||||
async def _arun(self, table_name: str) -> str:
|
||||
raise NotImplementedError("SchemaSqlDbTool does not support async")
|
||||
|
||||
|
||||
class ListSQLDatabaseTool(BaseSQLDatabaseTool, BaseTool):
|
||||
"""Tool for getting tables names."""
|
||||
|
||||
name = "list_tables_sql_db"
|
||||
description = "Input is an empty string, output is a comma separated list of tables in the database."
|
||||
|
||||
def _run(self, tool_input: str = "") -> str:
|
||||
"""Get the schema for a specific table."""
|
||||
return ", ".join(self.db.get_table_names())
|
||||
|
||||
async def _arun(self, tool_input: str = "") -> str:
|
||||
raise NotImplementedError("ListTablesSqlDbTool does not support async")
|
||||
|
||||
|
||||
class QueryCheckerTool(BaseSQLDatabaseTool, BaseTool):
|
||||
"""Use an LLM to check if a query is correct.
|
||||
Adapted from https://www.patterns.app/blog/2023/01/18/crunchbot-sql-analyst-gpt/"""
|
||||
|
||||
template: str = QUERY_CHECKER
|
||||
llm_chain: LLMChain = Field(
|
||||
default_factory=lambda: LLMChain(
|
||||
llm=OpenAI(temperature=0),
|
||||
prompt=PromptTemplate(
|
||||
template=QUERY_CHECKER, input_variables=["query", "dialect"]
|
||||
),
|
||||
)
|
||||
)
|
||||
name = "query_checker_sql_db"
|
||||
description = """
|
||||
Use this tool to double check if your query is correct before executing it.
|
||||
Always use this tool before executing a query with query_sql_db!
|
||||
"""
|
||||
|
||||
@validator("llm_chain")
|
||||
def validate_llm_chain_input_variables(cls, llm_chain: LLMChain) -> LLMChain:
|
||||
"""Make sure the LLM chain has the correct input variables."""
|
||||
if llm_chain.prompt.input_variables != ["query", "dialect"]:
|
||||
raise ValueError(
|
||||
"LLM chain for QueryCheckerTool must have input variables ['query', 'dialect']"
|
||||
)
|
||||
return llm_chain
|
||||
|
||||
def _run(self, query: str) -> str:
|
||||
"""Use the LLM to check the query."""
|
||||
return self.llm_chain.predict(query=query, dialect=self.db.dialect)
|
||||
|
||||
async def _arun(self, query: str) -> str:
|
||||
return await self.llm_chain.apredict(query=query, dialect=self.db.dialect)
|
||||
@ -0,0 +1 @@
|
||||
"""Simple tool wrapper around VectorDBQA chain."""
|
||||
@ -0,0 +1,81 @@
|
||||
"""Tools for interacting with vectorstores."""
|
||||
|
||||
import json
|
||||
from typing import Any, Dict
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from langchain.chains.qa_with_sources.vector_db import VectorDBQAWithSourcesChain
|
||||
from langchain.chains.vector_db_qa.base import VectorDBQA
|
||||
from langchain.llms.base import BaseLLM
|
||||
from langchain.llms.openai import OpenAI
|
||||
from langchain.tools.base import BaseTool
|
||||
from langchain.vectorstores.base import VectorStore
|
||||
|
||||
|
||||
class BaseVectorStoreTool(BaseModel):
|
||||
"""Base class for tools that use a VectorStore."""
|
||||
|
||||
vectorstore: VectorStore = Field(exclude=True)
|
||||
llm: BaseLLM = Field(default_factory=lambda: OpenAI(temperature=0))
|
||||
|
||||
class Config(BaseTool.Config):
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
|
||||
def _create_description_from_template(values: Dict[str, Any]) -> Dict[str, Any]:
|
||||
values["description"] = values["template"].format(name=values["name"])
|
||||
return values
|
||||
|
||||
|
||||
class VectorStoreQATool(BaseVectorStoreTool, BaseTool):
|
||||
"""Tool for the VectorDBQA chain. To be initialized with name and chain."""
|
||||
|
||||
@staticmethod
|
||||
def get_description(name: str, description: str) -> str:
|
||||
template: str = (
|
||||
"Useful for when you need to answer questions about {name}. "
|
||||
"Whenever you need information about {description} "
|
||||
"you should ALWAYS use this. "
|
||||
"Input should be a fully formed question."
|
||||
)
|
||||
return template.format(name=name, description=description)
|
||||
|
||||
def _run(self, query: str) -> str:
|
||||
"""Use the tool."""
|
||||
chain = VectorDBQA.from_chain_type(self.llm, vectorstore=self.vectorstore)
|
||||
return chain.run(query)
|
||||
|
||||
async def _arun(self, query: str) -> str:
|
||||
"""Use the tool asynchronously."""
|
||||
raise NotImplementedError("VectorDBQATool does not support async")
|
||||
|
||||
|
||||
class VectorStoreQAWithSourcesTool(BaseVectorStoreTool, BaseTool):
|
||||
"""Tool for the VectorDBQAWithSources chain."""
|
||||
|
||||
@staticmethod
|
||||
def get_description(name: str, description: str) -> str:
|
||||
template: str = (
|
||||
"Useful for when you need to answer questions about {name} and the sources "
|
||||
"used to construct the answer. "
|
||||
"Whenever you need information about {description} "
|
||||
"you should ALWAYS use this. "
|
||||
" Input should be a fully formed question. "
|
||||
"Output is a json serialized dictionary with keys `answer` and `sources`. "
|
||||
"Only use this tool if the user explicitly asks for sources."
|
||||
)
|
||||
return template.format(name=name, description=description)
|
||||
|
||||
def _run(self, query: str) -> str:
|
||||
"""Use the tool."""
|
||||
chain = VectorDBQAWithSourcesChain.from_chain_type(
|
||||
self.llm, vectorstore=self.vectorstore
|
||||
)
|
||||
return json.dumps(chain({chain.question_key: query}, return_only_outputs=True))
|
||||
|
||||
async def _arun(self, query: str) -> str:
|
||||
"""Use the tool asynchronously."""
|
||||
raise NotImplementedError("VectorDBQATool does not support async")
|
||||
@ -1,22 +0,0 @@
|
||||
"""Toolkit for the Wolfram Alpha API."""
|
||||
|
||||
from typing import List
|
||||
|
||||
from langchain.tools.base import BaseTool, BaseToolkit
|
||||
from langchain.tools.wolfram_alpha.tool import WolframAlphaQueryRun
|
||||
from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
|
||||
|
||||
|
||||
class WolframAlphaToolkit(BaseToolkit):
|
||||
"""Tool that adds the capability to interact with Wolfram Alpha."""
|
||||
|
||||
wolfram_alpha_appid: str
|
||||
|
||||
def get_tools(self) -> List[BaseTool]:
|
||||
"""Get the tools in the toolkit."""
|
||||
wrapper = WolframAlphaAPIWrapper(wolfram_alpha_appid=self.wolfram_alpha_appid)
|
||||
return [
|
||||
WolframAlphaQueryRun(
|
||||
api_wrapper=wrapper,
|
||||
)
|
||||
]
|
||||
@ -0,0 +1 @@
|
||||
"""Test suite for the tools module."""
|
||||
@ -0,0 +1,49 @@
|
||||
"""Test functionality of JSON tools."""
|
||||
from pathlib import Path
|
||||
|
||||
from langchain.tools.json.tool import JsonSpec
|
||||
|
||||
|
||||
def test_json_spec_from_file(tmp_path: Path) -> None:
|
||||
"""Test JsonSpec can be constructed from a file."""
|
||||
path = tmp_path / "test.json"
|
||||
path.write_text('{"foo": "bar"}')
|
||||
spec = JsonSpec.from_file(path)
|
||||
assert spec.dict_ == {"foo": "bar"}
|
||||
|
||||
|
||||
def test_json_spec_keys() -> None:
|
||||
"""Test JsonSpec can return keys of a dict at given path."""
|
||||
spec = JsonSpec(dict_={"foo": "bar", "baz": {"test": {"foo": [1, 2, 3]}}})
|
||||
assert spec.keys("data") == "['foo', 'baz']"
|
||||
assert "ValueError" in spec.keys('data["foo"]')
|
||||
assert spec.keys('data["baz"]') == "['test']"
|
||||
assert spec.keys('data["baz"]["test"]') == "['foo']"
|
||||
assert "ValueError" in spec.keys('data["baz"]["test"]["foo"]')
|
||||
|
||||
|
||||
def test_json_spec_value() -> None:
|
||||
"""Test JsonSpec can return value of a dict at given path."""
|
||||
spec = JsonSpec(dict_={"foo": "bar", "baz": {"test": {"foo": [1, 2, 3]}}})
|
||||
assert spec.value("data") == "{'foo': 'bar', 'baz': {'test': {'foo': [1, 2, 3]}}}"
|
||||
assert spec.value('data["foo"]') == "bar"
|
||||
assert spec.value('data["baz"]') == "{'test': {'foo': [1, 2, 3]}}"
|
||||
assert spec.value('data["baz"]["test"]') == "{'foo': [1, 2, 3]}"
|
||||
assert spec.value('data["baz"]["test"]["foo"]') == "[1, 2, 3]"
|
||||
|
||||
|
||||
def test_json_spec_value_max_length() -> None:
|
||||
"""Test JsonSpec can return value of a dict at given path."""
|
||||
spec = JsonSpec(
|
||||
dict_={"foo": "bar", "baz": {"test": {"foo": [1, 2, 3]}}}, max_value_length=5
|
||||
)
|
||||
assert spec.value('data["foo"]') == "bar"
|
||||
assert (
|
||||
spec.value('data["baz"]')
|
||||
== "Value is a large dictionary, should explore its keys directly"
|
||||
)
|
||||
assert (
|
||||
spec.value('data["baz"]["test"]')
|
||||
== "Value is a large dictionary, should explore its keys directly"
|
||||
)
|
||||
assert spec.value('data["baz"]["test"]["foo"]') == "[1, 2..."
|
||||
Loading…
Reference in New Issue