phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

docs(json_mode.md): add example of calling openai with pydantic model via litellm

Browse source
This commit is contained in:
Krrish Dholakia 2024-08-06 18:27:06 -07:00
parent 9cf3d5f568
commit 0c88cc4153
1 changed files with 6 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

39
docs/my-website/docs/completion/json_mode.md
View file

@ -71,12 +71,6 @@ response_format: { "type": "json_schema", "json_schema": … , "strict": true }
Works for OpenAI models Works for OpenAI models
:::info
Support for passing in a pydantic object to litellm sdk will be [coming soon](https://github.com/BerriAI/litellm/issues/5074#issuecomment-2272355842)
:::
<Tabs> <Tabs>
<TabItem value="sdk" label="SDK"> <TabItem value="sdk" label="SDK">
@ -89,36 +83,15 @@ os.environ["OPENAI_API_KEY"] = ""
messages = [{"role": "user", "content": "List 5 cookie recipes"}] messages = [{"role": "user", "content": "List 5 cookie recipes"}]
class CalendarEvent(BaseModel):
name: str
date: str
participants: list[str]
resp = completion( resp = completion(
model="gpt-4o-2024-08-06", model="gpt-4o-2024-08-06",
messages=messages, messages=messages,
response_format={ response_format=CalendarEvent
"type": "json_schema",
"json_schema": {
"name": "math_reasoning",
"schema": {
"type": "object",
"properties": {
"steps": {
"type": "array",
"items": {
"type": "object",
"properties": {
"explanation": { "type": "string" },
"output": { "type": "string" }
},
"required": ["explanation", "output"],
"additionalProperties": False
}
},
"final_answer": { "type": "string" }
},
"required": ["steps", "final_answer"],
"additionalProperties": False
},
"strict": True
},
}
) )
print("Received={}".format(resp)) print("Received={}".format(resp))