Marco Fiocco
Marco Fiocco
Looks like if I listen to http://*:8000 it works, instead of http:/0.0.0.0:8000
Same issue here
@rbren yes, I cannot set LLM_API_KEY because we need to setup the token_provider as seen above which in turn requires TENANT_ID, CLIENT_ID, CLIENT_SECRET
@enyst Yes I can make it work in a standalone script, without litellm. The updated code is: ``` from openai import AzureOpenAI from azure.identity import EnvironmentCredential, get_bearer_token_provider # Provide a...
I don't have a fixed API key, I have to use a token provider. it would be great if you can add support for `azure_ad_token_provider` parameter in `AzureChatOpenAI`. I use...
Yes, I agree with @jonascsantos . I've found that if a subagent of deepagent calls Copilotkit frontend actions, Copilotkit does not seem to receive any action call, as if the...
I'll try if I get the traces... But if you want to replicate, just do this: ``` agent = create_deep_agent( tools=[internet_search], model="openai:gpt-5", instructions=research_instructions, subagents=[critique_sub_agent, research_sub_agent], ).with_config({"recursion_limit": 1000}) ``` and ask...
I have a similar issue. I have noticed that If I stop and start the backend, the conversation history can be reloaded.
@NathanTarbert there will be a way to list the IDs of the existing threads? And how to store the title of the thread (not just the id)?
What if I use Langgraph chat persistence with Sqlite/Postgres?