Spaces:
Sleeping
Sleeping
File size: 8,204 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 |
{
"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 TextRequestsWrapper\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
}
|