phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: Fix incorrect vector_db_id usage in RAG tutorial

Browse source 
The detailed RAG tutorial was using a client-generated `vector_db_id`.
Recent versions of Llama-Stack ignore this ID and assign a new
server-side ID, causing the `rag_tool.insert` call to fail with a
`400 Bad Request` error.

This commit updates the code to capture the authoritative ID from the
`.identifier` attribute of the `register()` method's response object. A
concise comment is also added to explain why this is necessary.

This ensures the tutorial code runs successfully and reflects the current
API behavior related to the deprecation of VectorDB.
This commit is contained in:
Adam Young 2025-09-14 15:10:01 -05:00
parent 6787755c0c
commit 1039c8e7cf
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/source/getting_started/detailed_tutorial.md
View file

@ -460,10 +460,12 @@ client = LlamaStackClient(base_url="http://localhost:8321")
embed_lm = next(m for m in client.models.list() if m.model_type == "embedding") embed_lm = next(m for m in client.models.list() if m.model_type == "embedding")
embedding_model = embed_lm.identifier embedding_model = embed_lm.identifier
vector_db_id = f"v{uuid.uuid4().hex}" vector_db_id = f"v{uuid.uuid4().hex}"
client.vector_dbs.register( # The VectorDB API is deprecated; the server now returns its own authoritative ID.
# We capture the correct ID from the response's .identifier attribute.
vector_db_id = client.vector_dbs.register(
vector_db_id=vector_db_id, vector_db_id=vector_db_id,
embedding_model=embedding_model, embedding_model=embedding_model,
) ).identifier
# Create Documents # Create Documents
urls = [ urls = [