litellm/docs/extras/integrations/toolkits/openapi.ipynb

OpenAPI agents

We can construct agents to consume arbitrary APIs, here APIs conformant to the OpenAPI/Swagger specification.

1st example: hierarchical planning agent

In this example, we'll consider an approach called hierarchical planning, common in robotics and appearing in recent works for LLMs X robotics. We'll see it's a viable approach to start working with a massive API spec AND to assist with user queries that require multiple steps against the API.

The idea is simple: to get coherent agent behavior over long sequences behavior & to save on tokens, we'll separate concerns: a "planner" will be responsible for what endpoints to call and a "controller" will be responsible for how to call them.

In the initial implementation, the planner is an LLM chain that has the name and a short description for each endpoint in context. The controller is an LLM agent that is instantiated with documentation for only the endpoints for a particular plan. There's a lot left to get this working very robustly :)

---

To start, let's collect some OpenAPI specs.

In [1]:

import os, yaml

In [2]:

!wget https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
!mv openapi.yaml openai_openapi.yaml
!wget https://www.klarna.com/us/shopping/public/openai/v0/api-docs
!mv api-docs klarna_openapi.yaml
!wget https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/spotify.com/1.0.0/openapi.yaml
!mv openapi.yaml 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]

In [3]:

from langchain.agents.agent_toolkits.openapi.spec import reduce_openapi_spec

In [4]:

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)

---

We'll work with the Spotify API as one of the examples of a somewhat complex API. There's a bit of auth-related setup to do if you want to replicate this.

• You'll have to set up an application in the Spotify developer console, documented here, to get credentials: CLIENT_ID, CLIENT_SECRET, and REDIRECT_URI.
• To get an access tokens (and keep them fresh), you can implement the oauth flows, or you can use spotipy. If you've set your Spotify creedentials as environment variables SPOTIPY_CLIENT_ID, SPOTIPY_CLIENT_SECRET, and SPOTIPY_REDIRECT_URI, you can use the helper functions below:

In [5]:

import spotipy.util as util
from langchain.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)

How big is this spec?

In [6]:

endpoints = [
    (route, operation)
    for route, operations in raw_spotify_api_spec["paths"].items()
    for operation in operations
    if operation in ["get", "post"]
]
len(endpoints)

Out [6]:

63

In [7]:

import tiktoken

enc = tiktoken.encoding_for_model("text-davinci-003")


def count_tokens(s):
    return len(enc.encode(s))


count_tokens(yaml.dump(raw_spotify_api_spec))

Out [7]:

80326

Let's see some examples!

Starting with GPT-4. (Some robustness iterations under way for GPT-3 family.)

In [8]:

from langchain.llms.openai import OpenAI
from langchain.agents.agent_toolkits.openapi import planner

llm = OpenAI(model_name="gpt-4", temperature=0.0)

/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.chat_models 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.chat_models import ChatOpenAI`
  warnings.warn(

In [9]:

spotify_agent = planner.create_openapi_agent(spotify_api_spec, requests_wrapper, llm)
user_query = (
    "make me a playlist with the first song from kind of blue. call it machine blues."
)
spotify_agent.run(user_query)

Out [9]:

> Entering new AgentExecutor chain...
Action: 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
Observation: 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
Thought:I 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

> Entering new AgentExecutor chain...
Action: 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"}
Observation: 1weenld61qoidwYuZ1GESA
Thought:Action: 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"}
Observation: 7q3kkfAVpmcZ8g6JUThi3o
Thought:Action: requests_get
Action Input: {"url": "https://api.spotify.com/v1/me", "output_instructions": "Extract the id of the current user"}
Observation: 22rhrz4m4kvpxlsb5hezokzwi
Thought:Action: 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"}
Observation: 7lzoEi44WOISnFYlrAIqyX
Thought:Action: 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"}

Observation: The track was added to the playlist, confirmed by the snapshot_id: MiwxODMxNTMxZTFlNzg3ZWFlZmMxYTlmYWQyMDFiYzUwNDEwMTAwZmE1.
Thought:I am finished executing the plan.
Final Answer: The first song from the "Kind of Blue" album has been added to the "Machine Blues" playlist.

> Finished chain.

Observation: The first song from the "Kind of Blue" album has been added to the "Machine Blues" playlist.
Thought:I 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.

> Finished chain.

'I have created a playlist called "Machine Blues" with the first song from the "Kind of Blue" album.'

In [12]:

user_query = "give me a song I'd like, make it blues-ey"
spotify_agent.run(user_query)

Out [12]:

> Entering new AgentExecutor chain...
Action: api_planner
Action Input: I need to find the right API calls to get a blues song recommendation for the user
Observation: 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
Thought:I 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

> Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.spotify.com/v1/me", "output_instructions": "Extract the user's id and username"}
Observation: ID: 22rhrz4m4kvpxlsb5hezokzwi, Username: Jeremy Welborn
Thought:Action: requests_get
Action Input: {"url": "https://api.spotify.com/v1/recommendations/available-genre-seeds", "output_instructions": "Extract the list of available genres"}
Observation: acoustic, 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-
Thought:

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.).

Action: 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"}
Observation: [
  {
    id: '03lXHmokj9qsXspNsPoirR',
    name: 'Get Away Jordan'
  }
]
Thought:I 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.

> Finished chain.

Observation: The recommended blues song for user Jeremy Welborn (ID: 22rhrz4m4kvpxlsb5hezokzwi) is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.
Thought:I 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.

> Finished chain.

'The recommended blues song for you is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.'

Try another API.

In [23]:

headers = {"Authorization": f"Bearer {os.getenv('OPENAI_API_KEY')}"}
openai_requests_wrapper = RequestsWrapper(headers=headers)

In [28]:

# Meta!
llm = OpenAI(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.run(user_query)

Out [28]:

> Entering new AgentExecutor chain...
Action: api_planner
Action Input: I need to find the right API calls to generate a short piece of advice
Observation: 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
Thought:I 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

> Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.openai.com/v1/engines", "output_instructions": "Extract the ids of the engines"}
Observation: babbage, 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
Thought:I 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"}
Observation: "you must provide a model parameter"
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
I cannot finish executing the plan without knowing how to provide the model parameter correctly.

> Finished chain.

Observation: I need more information on how to provide the model parameter correctly in the POST request to generate a short piece of advice.
Thought:I 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
Observation: 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
Thought:I 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

> Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.openai.com/v1/models", "output_instructions": "Extract the ids of the available models"}
Observation: babbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-edit-001, ada
Thought:Action: 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"}
Observation: "I'd like to broaden my horizon.\n\nI was trying to"
Thought:I 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.

> Finished chain.

Observation: 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.
Thought:I 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
Observation: 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
Thought:I 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

> Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.openai.com/v1/models", "output_instructions": "Extract the names of the models"}
Observation: babbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-edit-001, ada
Thought:Action: 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"}
Observation: "Some basic advice for improving communication skills would be to make sure to listen"
Thought:I am finished executing the plan.

Final Answer: Some basic advice for improving communication skills would be to make sure to listen.

> Finished chain.

Observation: Some basic advice for improving communication skills would be to make sure to listen.
Thought:I 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.

> Finished chain.

'A short piece of advice for improving communication skills is to make sure to listen.'

Takes awhile to get there!

2nd example: "json explorer" agent

Here's an agent that's not particularly practical, but neat! The agent has access to 2 toolkits. One comprises tools to interact with json: one tool to list the keys of a json object and another tool to get the value for a given key. The other toolkit comprises requests wrappers to send GET and POST requests. This agent consumes a lot calls to the language model, but does a surprisingly decent job.

In [29]:

from langchain.agents import create_openapi_agent
from langchain.agents.agent_toolkits import OpenAPIToolkit
from langchain.llms.openai import OpenAI
from langchain.requests import TextRequestsWrapper
from langchain.tools.json.tool import JsonSpec

In [32]:

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, verbose=True
)

In [33]:

openapi_agent_executor.run(
    "Make a post request to openai /completions. The prompt should be 'tell me a joke.'"
)

Out [33]:

> Entering new AgentExecutor chain...
Action: json_explorer
Action Input: What is the base url for the API?

> Entering new AgentExecutor chain...
Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
Thought: I should look at the servers key to see what the base url is
Action: json_spec_list_keys
Action Input: data["servers"][0]
Observation: ValueError('Value at path `data["servers"][0]` is not a dict, get the value directly.')
Thought: I should get the value of the servers key
Action: json_spec_get_value
Action Input: data["servers"][0]
Observation: {'url': 'https://api.openai.com/v1'}
Thought: I now know the base url for the API
Final Answer: The base url for the API is https://api.openai.com/v1

> Finished chain.

Observation: The base url for the API is https://api.openai.com/v1
Thought: I should find the path for the /completions endpoint.
Action: json_explorer
Action Input: What is the path for the /completions endpoint?

> Entering new AgentExecutor chain...
Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
Thought: I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/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']
Thought: I now know the path for the /completions endpoint
Final Answer: The path for the /completions endpoint is data["paths"][2]

> Finished chain.

Observation: The path for the /completions endpoint is data["paths"][2]
Thought: 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?

> Entering new AgentExecutor chain...
Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
Thought: I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/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']
Thought: I should look at the /completions endpoint to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]
Observation: ['post']
Thought: I should look at the post key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]
Observation: ['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']
Thought: 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"]
Observation: ['required', 'content']
Thought: 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"]
Observation: ['application/json']
Thought: 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"]
Observation: ['schema']
Thought: 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"]
Observation: ['$ref']
Thought: 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"]
Observation: ValueError('Value at path `data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"]` is not a dict, get the value directly.')
Thought: 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"]
Observation: #/components/schemas/CreateCompletionRequest
Thought: I should look at the CreateCompletionRequest schema to see what parameters are required
Action: json_spec_list_keys
Action Input: data["components"]["schemas"]["CreateCompletionRequest"]
Observation: ['type', 'properties', 'required']
Thought: 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"]
Observation: ['model']
Thought: I now know the final answer
Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.

> Finished chain.

Observation: The required parameters for a POST request to the /completions endpoint are 'model'.
Thought: 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" } }
Observation: {"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}}

Thought: 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}}

> Finished chain.

'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}}'