kauabh

same even for me - Even with this dummy code from openai import AzureOpenAI from pydantic import BaseModel client = instructor.patch(AzureOpenAI( api_version="", azure_endpoint="", azure_deployment="" )) class UserDetail(BaseModel): name: str age:...

+ 1

@w352chen Is this branch contain working EVAL Gen code? I am trying to use from main branch but it is not working. If yes, can you please advice on how...

Hey @xflashxx I believe dynamic instruction are supported. Check below examples Example 1 ``` from pydantic_ai import Agent user_is_logged_in = False instructions = [ "Reply with user Name John "...

Hmmm, I see your point. Personally, managing all dependencies in one place sounds cleaner to me, but your example does raise some important points.

I believe you must have seen this example earlier from documentation (just sharing for the sake of completness ) https://ai.pydantic.dev/api/agent/#pydantic_ai.agent.Agent.instructions but yeah it still require defining deps ``` from pydantic_ai...

I think it is disabled by default, check these docs: https://github.com/NVIDIA/NeMo-Guardrails/blob/main/docs/user_guides/advanced/embedding-search-providers.md Try explicitly defining these variables

cool, ideally I think it should not try to create cache when explicitly disabled

any help on above trying to install macos14.5

Hi @nikithakriz have you checked this doc from langchain on using session id https://github.com/langchain-ai/langchain/blob/master/docs/docs/integrations/memory/mongodb_chat_message_history.ipynb . chat_history for session_id requires "session_id": ``` chain_with_history = RunnableWithMessageHistory( chain, lambda session_id: MongoDBChatMessageHistory( session_id=session_id, connection_string="mongodb://mongo_user:password123@mongo:27017",...