phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(inference): enable routing of models with provider_data alone (#3928)

Browse source 
This PR enables routing of fully qualified model IDs of the form
`provider_id/model_id` even when the models are not registered with the
Stack.

Here's the situation: assume a remote inference provider which works
only when users provide their own API keys via
`X-LlamaStack-Provider-Data` header. By definition, we cannot list
models and hence update our routing registry. But because we _require_ a
provider ID in the models now, we can identify which provider to route
to and let that provider decide.

Note that we still try to look up our registry since it may have a
pre-registered alias. Just that we don't outright fail when we are not
able to look it up.

Also, updated inference router so that the responses have the _exact_
model that the request had.

## Test Plan

Added an integration test

Closes #3929

---------

Co-authored-by: ehhuang <ehhuang@users.noreply.github.com>
This commit is contained in:
Ashwin Bharambe 2025-10-28 11:16:37 -07:00 • committed by GitHub
parent 94b0592240
commit f88416ef87
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 216 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/integration/inference/test_openai_embeddings.py
View file

@ -161,8 +161,7 @@ def test_openai_embeddings_single_string(compat_client, client_with_models, embe
assert response.object == "list"
# Handle provider-scoped model identifiers (e.g., sentence-transformers/nomic-ai/nomic-embed-text-v1.5)
assert response.model == embedding_model_id or response.model.endswith(f"/{embedding_model_id}")
assert response.model == embedding_model_id
assert len(response.data) == 1
assert response.data[0].object == "embedding"
assert response.data[0].index == 0
@ -186,8 +185,7 @@ def test_openai_embeddings_multiple_strings(compat_client, client_with_models, e
assert response.object == "list"
# Handle provider-scoped model identifiers (e.g., sentence-transformers/nomic-ai/nomic-embed-text-v1.5)
assert response.model == embedding_model_id or response.model.endswith(f"/{embedding_model_id}")
assert response.model == embedding_model_id
assert len(response.data) == len(input_texts)
for i, embedding_data in enumerate(response.data):
@ -365,8 +363,7 @@ def test_openai_embeddings_base64_batch_processing(compat_client, client_with_mo
# Validate response structure
assert response.object == "list"
# Handle provider-scoped model identifiers (e.g., sentence-transformers/nomic-ai/nomic-embed-text-v1.5)
assert response.model == embedding_model_id or response.model.endswith(f"/{embedding_model_id}")
assert response.model == embedding_model_id
assert len(response.data) == len(input_texts)
# Validate each embedding in the batch