Merge branch 'main' of github.com:datastax/astra-assistants-api

README.md

@@ -178,9 +178,7 @@ you need to pull the model you want to ollama before using it
 
     curl http://localhost:11434/api/pull -d '{ "name": "deepseek-coder-v2" }'
 
-your assistants client should route to the ollama container by passing the llm-param-base-url header:
-
-    client = patch(OpenAI(default_headers={"LLM-PARAM-base-url": "http://ollama:11434"}))
+your assistants client should route to the ollama container setting OLLAMA_API_BASE_URL. OLLAMA_API_BASE_URL should be set to http://ollama:11434 if you are using docker-compose. If you are using ollama on your localhost you can set it to http://localhost:11434
 
 
 ## Feedback / Help

examples/python/agency-swarm/local_open_source_models.py

@@ -6,9 +6,8 @@
 load_dotenv("./.env")
 load_dotenv("../../../.env")
 
-client = patch(OpenAI(default_headers={"LLM-PARAM-base-url": "http://localhost:11434"}))
-# if using docker-compose, pass custom header to point to the ollama container instead of localhost
-# client = patch(OpenAI(default_headers={"LLM-PARAM-base-url": "http://ollama:11434"}))
+# remember to set OLLAMA_API_BASE_URL="http://ollama:11434" and base_url="http://localhost:8000/v1" in your env
+client = patch(OpenAI())
 
 set_openai_client(client)
 
@@ -25,4 +24,4 @@
 print(assistant)
 
 completion = agency.get_completion("What's something interesting about language models?")
-print(completion)
+print(completion)