OpenAPI 工具包
我们可以构建代理来消费任意API，这里的API符合OpenAPI/Swagger规范。
# NOTE: In this example. We must set `allow_dangerous_request=True` to enable the OpenAPI Agent to automatically use the Request Tool.
# This can be dangerous for calling unwanted requests. Please make sure your custom OpenAPI spec (yaml) is safe.
ALLOW_DANGEROUS_REQUEST = True
第一个示例：分层规划代理
在这个例子中，我们将考虑一种称为分层规划的方法，这种方法在机器人技术中很常见，并且在最近的大语言模型（LLMs）与机器人技术结合的工作中出现。我们将看到，这是一种可行的方法，既可以开始处理庞大的API规范，也可以协助用户进行需要多个步骤的API查询。
这个想法很简单：为了在长时间的行为序列中获得一致的代理行为并节省令牌，我们将分离关注点：一个“规划器”将负责调用哪些端点，而一个“控制器”将负责如何调用它们。
在初始实现中，规划器是一个LLM链，它在上下文中为每个端点提供了名称和简短描述。控制器是一个LLM代理，它仅针对特定计划的端点实例化文档。要使这个系统非常稳健地工作，还有很多工作要做 :)
首先，让我们收集一些OpenAPI规范。
import os
import yaml
您将能够从这里获取OpenAPI规范：APIs-guru/openapi-directory
!wget https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml -O openai_openapi.yaml
!wget https://www.klarna.com/us/shopping/public/openai/v0/api-docs -O klarna_openapi.yaml
!wget https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/spotify.com/1.0.0/openapi.yaml -O spotify_openapi.yaml
--2023-03-31 15:45:56-- https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 122995 (120K) [text/plain]
Saving to: ‘openapi.yaml’
openapi.yaml 100%[===================>] 120.11K --.-KB/s in 0.01s
2023-03-31 15:45:56 (10.4 MB/s) - ‘openapi.yaml’ saved [122995/122995]
--2023-03-31 15:45:57-- https://www.klarna.com/us/shopping/public/openai/v0/api-docs
Resolving www.klarna.com (www.klarna.com)... 52.84.150.34, 52.84.150.46, 52.84.150.61, ...
Connecting to www.klarna.com (www.klarna.com)|52.84.150.34|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: unspecified [application/json]
Saving to: ‘api-docs’
api-docs [ <=> ] 1.87K --.-KB/s in 0s
2023-03-31 15:45:57 (261 MB/s) - ‘api-docs’ saved [1916]
--2023-03-31 15:45:57-- https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/spotify.com/1.0.0/openapi.yaml
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 286747 (280K) [text/plain]
Saving to: ‘openapi.yaml’
openapi.yaml 100%[===================>] 280.03K --.-KB/s in 0.02s
2023-03-31 15:45:58 (13.3 MB/s) - ‘openapi.yaml’ saved [286747/286747]
from langchain_community.agent_toolkits.openapi.spec import reduce_openapi_spec
API Reference:reduce_openapi_spec
with open("openai_openapi.yaml") as f:
raw_openai_api_spec = yaml.load(f, Loader=yaml.Loader)
openai_api_spec = reduce_openapi_spec(raw_openai_api_spec)
with open("klarna_openapi.yaml") as f:
raw_klarna_api_spec = yaml.load(f, Loader=yaml.Loader)
klarna_api_spec = reduce_openapi_spec(raw_klarna_api_spec)
with open("spotify_openapi.yaml") as f:
raw_spotify_api_spec = yaml.load(f, Loader=yaml.Loader)
spotify_api_spec = reduce_openapi_spec(raw_spotify_api_spec)
我们将以Spotify API为例，展示一个相对复杂的API。如果你想复制这个例子，需要进行一些与认证相关的设置。
- 你需要在Spotify开发者控制台中设置一个应用程序，文档这里，以获取凭证：
CLIENT_ID、CLIENT_SECRET和REDIRECT_URI。 - 要获取访问令牌（并保持其新鲜），您可以实现oauth流程，或者您可以使用
spotipy。如果您已将Spotify凭据设置为环境变量SPOTIPY_CLIENT_ID、SPOTIPY_CLIENT_SECRET和SPOTIPY_REDIRECT_URI，您可以使用以下辅助函数：
import spotipy.util as util
from langchain_community.utilities.requests import RequestsWrapper
def construct_spotify_auth_headers(raw_spec: dict):
scopes = list(
raw_spec["components"]["securitySchemes"]["oauth_2_0"]["flows"][
"authorizationCode"
]["scopes"].keys()
)
access_token = util.prompt_for_user_token(scope=",".join(scopes))
return {"Authorization": f"Bearer {access_token}"}
# Get API credentials.
headers = construct_spotify_auth_headers(raw_spotify_api_spec)
requests_wrapper = RequestsWrapper(headers=headers)
API Reference:RequestsWrapper
这个规范有多大？
endpoints = [
(route, operation)
for route, operations in raw_spotify_api_spec["paths"].items()
for operation in operations
if operation in ["get", "post"]
]
len(endpoints)
63
import tiktoken
enc = tiktoken.encoding_for_model("gpt-4")
def count_tokens(s):
return len(enc.encode(s))
count_tokens(yaml.dump(raw_spotify_api_spec))
80326
让我们看一些例子！
从GPT-4开始。（GPT-3系列正在进行一些稳健性迭代。）
from langchain_community.agent_toolkits.openapi import planner
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model_name="gpt-4", temperature=0.0)
API Reference:planner | ChatOpenAI
/Users/jeremywelborn/src/langchain/langchain/llms/openai.py:169: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: `from langchain_openai import ChatOpenAI`
warnings.warn(
/Users/jeremywelborn/src/langchain/langchain/llms/openai.py:608: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: `from langchain_openai import ChatOpenAI`
warnings.warn(
# NOTE: set allow_dangerous_requests manually for security concern https://python.langchain.com/docs/security
spotify_agent = planner.create_openapi_agent(
spotify_api_spec,
requests_wrapper,
llm,
allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,
)
user_query = (
"make me a playlist with the first song from kind of blue. call it machine blues."
)
spotify_agent.invoke(user_query)
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: api_planner
Action Input: I need to find the right API calls to create a playlist with the first song from Kind of Blue and name it Machine Blues[0m
Observation: [36;1m[1;3m1. GET /search to search for the album "Kind of Blue"
2. GET /albums/{id}/tracks to get the tracks from the "Kind of Blue" album
3. GET /me to get the current user's information
4. POST /users/{user_id}/playlists to create a new playlist named "Machine Blues" for the current user
5. POST /playlists/{playlist_id}/tracks to add the first song from "Kind of Blue" to the "Machine Blues" playlist[0m
Thought:[32;1m[1;3mI have the plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /search to search for the album "Kind of Blue"
2. GET /albums/{id}/tracks to get the tracks from the "Kind of Blue" album
3. GET /me to get the current user's information
4. POST /users/{user_id}/playlists to create a new playlist named "Machine Blues" for the current user
5. POST /playlists/{playlist_id}/tracks to add the first song from "Kind of Blue" to the "Machine Blues" playlist[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.spotify.com/v1/search?q=Kind%20of%20Blue&type=album", "output_instructions": "Extract the id of the first album in the search results"}[0m
Observation: [36;1m[1;3m1weenld61qoidwYuZ1GESA[0m
Thought:[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.spotify.com/v1/albums/1weenld61qoidwYuZ1GESA/tracks", "output_instructions": "Extract the id of the first track in the album"}[0m
Observation: [36;1m[1;3m7q3kkfAVpmcZ8g6JUThi3o[0m
Thought:[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.spotify.com/v1/me", "output_instructions": "Extract the id of the current user"}[0m
Observation: [36;1m[1;3m22rhrz4m4kvpxlsb5hezokzwi[0m
Thought:[32;1m[1;3mAction: requests_post
Action Input: {"url": "https://api.spotify.com/v1/users/22rhrz4m4kvpxlsb5hezokzwi/playlists", "data": {"name": "Machine Blues"}, "output_instructions": "Extract the id of the created playlist"}[0m
Observation: [33;1m[1;3m7lzoEi44WOISnFYlrAIqyX[0m
Thought:[32;1m[1;3mAction: requests_post
Action Input: {"url": "https://api.spotify.com/v1/playlists/7lzoEi44WOISnFYlrAIqyX/tracks", "data": {"uris": ["spotify:track:7q3kkfAVpmcZ8g6JUThi3o"]}, "output_instructions": "Confirm that the track was added to the playlist"}
[0m
Observation: [33;1m[1;3mThe track was added to the playlist, confirmed by the snapshot_id: MiwxODMxNTMxZTFlNzg3ZWFlZmMxYTlmYWQyMDFiYzUwNDEwMTAwZmE1.[0m
Thought:[32;1m[1;3mI am finished executing the plan.
Final Answer: The first song from the "Kind of Blue" album has been added to the "Machine Blues" playlist.[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mThe first song from the "Kind of Blue" album has been added to the "Machine Blues" playlist.[0m
Thought:[32;1m[1;3mI am finished executing the plan and have created the playlist with the first song from Kind of Blue.
Final Answer: I have created a playlist called "Machine Blues" with the first song from the "Kind of Blue" album.[0m
[1m> Finished chain.[0m
'I have created a playlist called "Machine Blues" with the first song from the "Kind of Blue" album.'
user_query = "give me a song I'd like, make it blues-ey"
spotify_agent.invoke(user_query)
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: api_planner
Action Input: I need to find the right API calls to get a blues song recommendation for the user[0m
Observation: [36;1m[1;3m1. GET /me to get the current user's information
2. GET /recommendations/available-genre-seeds to retrieve a list of available genres
3. GET /recommendations with the seed_genre parameter set to "blues" to get a blues song recommendation for the user[0m
Thought:[32;1m[1;3mI have the plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /me to get the current user's information
2. GET /recommendations/available-genre-seeds to retrieve a list of available genres
3. GET /recommendations with the seed_genre parameter set to "blues" to get a blues song recommendation for the user[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.spotify.com/v1/me", "output_instructions": "Extract the user's id and username"}[0m
Observation: [36;1m[1;3mID: 22rhrz4m4kvpxlsb5hezokzwi, Username: Jeremy Welborn[0m
Thought:[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.spotify.com/v1/recommendations/available-genre-seeds", "output_instructions": "Extract the list of available genres"}[0m
Observation: [36;1m[1;3macoustic, afrobeat, alt-rock, alternative, ambient, anime, black-metal, bluegrass, blues, bossanova, brazil, breakbeat, british, cantopop, chicago-house, children, chill, classical, club, comedy, country, dance, dancehall, death-metal, deep-house, detroit-techno, disco, disney, drum-and-bass, dub, dubstep, edm, electro, electronic, emo, folk, forro, french, funk, garage, german, gospel, goth, grindcore, groove, grunge, guitar, happy, hard-rock, hardcore, hardstyle, heavy-metal, hip-hop, holidays, honky-tonk, house, idm, indian, indie, indie-pop, industrial, iranian, j-dance, j-idol, j-pop, j-rock, jazz, k-pop, kids, latin, latino, malay, mandopop, metal, metal-misc, metalcore, minimal-techno, movies, mpb, new-age, new-release, opera, pagode, party, philippines-[0m
Thought:
``````output
Retrying langchain.llms.openai.completion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it raised RateLimitError: That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID 2167437a0072228238f3c0c5b3882764 in your message.).
``````output
[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.spotify.com/v1/recommendations?seed_genres=blues", "output_instructions": "Extract the list of recommended tracks with their ids and names"}[0m
Observation: [36;1m[1;3m[
{
id: '03lXHmokj9qsXspNsPoirR',
name: 'Get Away Jordan'
}
][0m
Thought:[32;1m[1;3mI am finished executing the plan.
Final Answer: The recommended blues song for user Jeremy Welborn (ID: 22rhrz4m4kvpxlsb5hezokzwi) is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mThe recommended blues song for user Jeremy Welborn (ID: 22rhrz4m4kvpxlsb5hezokzwi) is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.[0m
Thought:[32;1m[1;3mI am finished executing the plan and have the information the user asked for.
Final Answer: The recommended blues song for you is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.[0m
[1m> Finished chain.[0m
'The recommended blues song for you is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.'
尝试另一个API。
headers = {"Authorization": f"Bearer {os.getenv('OPENAI_API_KEY')}"}
openai_requests_wrapper = RequestsWrapper(headers=headers)
# Meta!
llm = ChatOpenAI(model_name="gpt-4", temperature=0.25)
openai_agent = planner.create_openapi_agent(
openai_api_spec, openai_requests_wrapper, llm
)
user_query = "generate a short piece of advice"
openai_agent.invoke(user_query)
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: api_planner
Action Input: I need to find the right API calls to generate a short piece of advice[0m
Observation: [36;1m[1;3m1. GET /engines to retrieve the list of available engines
2. POST /completions with the selected engine and a prompt for generating a short piece of advice[0m
Thought:[32;1m[1;3mI have the plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /engines to retrieve the list of available engines
2. POST /completions with the selected engine and a prompt for generating a short piece of advice[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.openai.com/v1/engines", "output_instructions": "Extract the ids of the engines"}[0m
Observation: [36;1m[1;3mbabbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-001, ada, babbage-code-search-text, babbage-similarity, whisper-1, code-search-babbage-text-001, text-curie-001, code-search-babbage-code-001, text-ada-001, text-embedding-ada-002, text-similarity-ada-001, curie-instruct-beta, ada-code-search-code, ada-similarity, text-davinci-003, code-search-ada-text-001, text-search-ada-query-001, davinci-search-document, ada-code-search-text, text-search-ada-doc-001, davinci-instruct-beta, text-similarity-curie-001, code-search-ada-code-001[0m
Thought:[32;1m[1;3mI will use the "davinci" engine to generate a short piece of advice.
Action: requests_post
Action Input: {"url": "https://api.openai.com/v1/completions", "data": {"engine": "davinci", "prompt": "Give me a short piece of advice on how to be more productive."}, "output_instructions": "Extract the text from the first choice"}[0m
Observation: [33;1m[1;3m"you must provide a model parameter"[0m
Thought:!! Could not _extract_tool_and_input from "I cannot finish executing the plan without knowing how to provide the model parameter correctly." in _get_next_action
[32;1m[1;3mI cannot finish executing the plan without knowing how to provide the model parameter correctly.[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mI need more information on how to provide the model parameter correctly in the POST request to generate a short piece of advice.[0m
Thought:[32;1m[1;3mI need to adjust my plan to include the model parameter in the POST request.
Action: api_planner
Action Input: I need to find the right API calls to generate a short piece of advice, including the model parameter in the POST request[0m
Observation: [36;1m[1;3m1. GET /models to retrieve the list of available models
2. Choose a suitable model from the list
3. POST /completions with the chosen model as a parameter to generate a short piece of advice[0m
Thought:[32;1m[1;3mI have an updated plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /models to retrieve the list of available models
2. Choose a suitable model from the list
3. POST /completions with the chosen model as a parameter to generate a short piece of advice[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.openai.com/v1/models", "output_instructions": "Extract the ids of the available models"}[0m
Observation: [36;1m[1;3mbabbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-edit-001, ada[0m
Thought:[32;1m[1;3mAction: requests_post
Action Input: {"url": "https://api.openai.com/v1/completions", "data": {"model": "davinci", "prompt": "Give me a short piece of advice on how to improve communication skills."}, "output_instructions": "Extract the text from the first choice"}[0m
Observation: [33;1m[1;3m"I'd like to broaden my horizon.\n\nI was trying to"[0m
Thought:[32;1m[1;3mI cannot finish executing the plan without knowing some other information.
Final Answer: The generated text is not a piece of advice on improving communication skills. I would need to retry the API call with a different prompt or model to get a more relevant response.[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mThe generated text is not a piece of advice on improving communication skills. I would need to retry the API call with a different prompt or model to get a more relevant response.[0m
Thought:[32;1m[1;3mI need to adjust my plan to include a more specific prompt for generating a short piece of advice on improving communication skills.
Action: api_planner
Action Input: I need to find the right API calls to generate a short piece of advice on improving communication skills, including the model parameter in the POST request[0m
Observation: [36;1m[1;3m1. GET /models to retrieve the list of available models
2. Choose a suitable model for generating text (e.g., text-davinci-002)
3. POST /completions with the chosen model and a prompt related to improving communication skills to generate a short piece of advice[0m
Thought:[32;1m[1;3mI have an updated plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /models to retrieve the list of available models
2. Choose a suitable model for generating text (e.g., text-davinci-002)
3. POST /completions with the chosen model and a prompt related to improving communication skills to generate a short piece of advice[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: requests_get
Action Input: {"url": "https://api.openai.com/v1/models", "output_instructions": "Extract the names of the models"}[0m
Observation: [36;1m[1;3mbabbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-edit-001, ada[0m
Thought:[32;1m[1;3mAction: requests_post
Action Input: {"url": "https://api.openai.com/v1/completions", "data": {"model": "text-davinci-002", "prompt": "Give a short piece of advice on how to improve communication skills"}, "output_instructions": "Extract the text from the first choice"}[0m
Observation: [33;1m[1;3m"Some basic advice for improving communication skills would be to make sure to listen"[0m
Thought:[32;1m[1;3mI am finished executing the plan.
Final Answer: Some basic advice for improving communication skills would be to make sure to listen.[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mSome basic advice for improving communication skills would be to make sure to listen.[0m
Thought:[32;1m[1;3mI am finished executing the plan and have the information the user asked for.
Final Answer: A short piece of advice for improving communication skills is to make sure to listen.[0m
[1m> Finished chain.[0m
'A short piece of advice for improving communication skills is to make sure to listen.'
到达那里需要一些时间！
第二个示例："json explorer" 代理
这里有一个不是特别实用，但很整洁的代理！该代理可以访问2个工具包。一个包含与json交互的工具：一个工具用于列出json对象的键，另一个工具用于获取给定键的值。另一个工具包包含requests包装器，用于发送GET和POST请求。这个代理消耗了大量的语言模型调用，但做得相当不错。
from langchain_community.agent_toolkits import OpenAPIToolkit, create_openapi_agent
from langchain_community.tools.json.tool import JsonSpec
from langchain_openai import OpenAI
with open("openai_openapi.yaml") as f:
data = yaml.load(f, Loader=yaml.FullLoader)
json_spec = JsonSpec(dict_=data, max_value_length=4000)
openapi_toolkit = OpenAPIToolkit.from_llm(
OpenAI(temperature=0), json_spec, openai_requests_wrapper, verbose=True
)
openapi_agent_executor = create_openapi_agent(
llm=OpenAI(temperature=0),
toolkit=openapi_toolkit,
allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,
verbose=True,
)
openapi_agent_executor.run(
"Make a post request to openai /completions. The prompt should be 'tell me a joke.'"
)
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: json_explorer
Action Input: What is the base url for the API?[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: json_spec_list_keys
Action Input: data[0m
Observation: [36;1m[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta'][0m
Thought:[32;1m[1;3m I should look at the servers key to see what the base url is
Action: json_spec_list_keys
Action Input: data["servers"][0][0m
Observation: [36;1m[1;3mValueError('Value at path `data["servers"][0]` is not a dict, get the value directly.')[0m
Thought:[32;1m[1;3m I should get the value of the servers key
Action: json_spec_get_value
Action Input: data["servers"][0][0m
Observation: [33;1m[1;3m{'url': 'https://api.openai.com/v1'}[0m
Thought:[32;1m[1;3m I now know the base url for the API
Final Answer: The base url for the API is https://api.openai.com/v1[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mThe base url for the API is https://api.openai.com/v1[0m
Thought:[32;1m[1;3m I should find the path for the /completions endpoint.
Action: json_explorer
Action Input: What is the path for the /completions endpoint?[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: json_spec_list_keys
Action Input: data[0m
Observation: [36;1m[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta'][0m
Thought:[32;1m[1;3m I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"][0m
Observation: [36;1m[1;3m['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/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'][0m
Thought:[32;1m[1;3m I now know the path for the /completions endpoint
Final Answer: The path for the /completions endpoint is data["paths"][2][0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mThe path for the /completions endpoint is data["paths"][2][0m
Thought:[32;1m[1;3m I should find the required parameters for the POST request.
Action: json_explorer
Action Input: What are the required parameters for a POST request to the /completions endpoint?[0m
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: json_spec_list_keys
Action Input: data[0m
Observation: [36;1m[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta'][0m
Thought:[32;1m[1;3m I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"][0m
Observation: [36;1m[1;3m['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/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'][0m
Thought:[32;1m[1;3m I should look at the /completions endpoint to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"][0m
Observation: [36;1m[1;3m['post'][0m
Thought:[32;1m[1;3m I should look at the post key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"][0m
Observation: [36;1m[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta'][0m
Thought:[32;1m[1;3m I should look at the requestBody key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"][0m
Observation: [36;1m[1;3m['required', 'content'][0m
Thought:[32;1m[1;3m I should look at the content key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"][0m
Observation: [36;1m[1;3m['application/json'][0m
Thought:[32;1m[1;3m I should look at the application/json key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"][0m
Observation: [36;1m[1;3m['schema'][0m
Thought:[32;1m[1;3m I should look at the schema key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"][0m
Observation: [36;1m[1;3m['$ref'][0m
Thought:[32;1m[1;3m I should look at the $ref key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"][0m
Observation: [36;1m[1;3mValueError('Value at path `data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"]` is not a dict, get the value directly.')[0m
Thought:[32;1m[1;3m I should look at the $ref key to get the value directly
Action: json_spec_get_value
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"][0m
Observation: [33;1m[1;3m#/components/schemas/CreateCompletionRequest[0m
Thought:[32;1m[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required
Action: json_spec_list_keys
Action Input: data["components"]["schemas"]["CreateCompletionRequest"][0m
Observation: [36;1m[1;3m['type', 'properties', 'required'][0m
Thought:[32;1m[1;3m I should look at the required key to see what parameters are required
Action: json_spec_get_value
Action Input: data["components"]["schemas"]["CreateCompletionRequest"]["required"][0m
Observation: [33;1m[1;3m['model'][0m
Thought:[32;1m[1;3m I now know the final answer
Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.[0m
[1m> Finished chain.[0m
Observation: [33;1m[1;3mThe required parameters for a POST request to the /completions endpoint are 'model'.[0m
Thought:[32;1m[1;3m I now know the parameters needed to make the request.
Action: requests_post
Action Input: { "url": "https://api.openai.com/v1/completions", "data": { "model": "davinci", "prompt": "tell me a joke" } }[0m
Observation: [33;1m[1;3m{"id":"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv","object":"text_completion","created":1680307139,"model":"davinci","choices":[{"text":" with mummy not there”\n\nYou dig deep and come up with,","index":0,"logprobs":null,"finish_reason":"length"}],"usage":{"prompt_tokens":4,"completion_tokens":16,"total_tokens":20}}
[0m
Thought:[32;1m[1;3m I now know the final answer.
Final Answer: The response of the POST request is {"id":"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv","object":"text_completion","created":1680307139,"model":"davinci","choices":[{"text":" with mummy not there”\n\nYou dig deep and come up with,","index":0,"logprobs":null,"finish_reason":"length"}],"usage":{"prompt_tokens":4,"completion_tokens":16,"total_tokens":20}}[0m
[1m> Finished chain.[0m
'The response of the POST request is {"id":"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv","object":"text_completion","created":1680307139,"model":"davinci","choices":[{"text":" with mummy not there”\\n\\nYou dig deep and come up with,","index":0,"logprobs":null,"finish_reason":"length"}],"usage":{"prompt_tokens":4,"completion_tokens":16,"total_tokens":20}}'