feat(api)!: support extra_body to embeddings and vector_stores APIs (#3794)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 0s
Python Package Build Test / build (3.12) (push) Failing after 1s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 10s
UI Tests / ui-tests (22) (push) Successful in 40s
Pre-commit / pre-commit (push) Successful in 1m23s

Applies the same pattern from
https://github.com/llamastack/llama-stack/pull/3777 to embeddings and
vector_stores.create() endpoints.

This should _not_ be a breaking change since (a) our tests were already
using the `extra_body` parameter when passing in to the backend (b) but
the backend probably wasn't extracting the parameters correctly. This PR
will fix that.

Updated APIs: `openai_embeddings(), openai_create_vector_store(),
openai_create_vector_store_file_batch()`
This commit is contained in:
Ashwin Bharambe 2025-10-12 19:01:52 -07:00 committed by GitHub
parent 3bb6ef351b
commit ecc8a554d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 451 additions and 426 deletions

View file

@ -13,7 +13,10 @@ from unittest.mock import AsyncMock, MagicMock
import numpy as np
import pytest
from llama_stack.apis.inference.inference import OpenAIEmbeddingData
from llama_stack.apis.inference.inference import (
OpenAIEmbeddingData,
OpenAIEmbeddingsRequestWithExtraBody,
)
from llama_stack.apis.tools import RAGDocument
from llama_stack.apis.vector_io import Chunk
from llama_stack.providers.utils.memory.vector_store import (
@ -226,9 +229,14 @@ class TestVectorDBWithIndex:
await vector_db_with_index.insert_chunks(chunks)
mock_inference_api.openai_embeddings.assert_called_once_with(
"test-model without embeddings", ["Test 1", "Test 2"]
)
# Verify openai_embeddings was called with correct params
mock_inference_api.openai_embeddings.assert_called_once()
call_args = mock_inference_api.openai_embeddings.call_args[0]
assert len(call_args) == 1
params = call_args[0]
assert isinstance(params, OpenAIEmbeddingsRequestWithExtraBody)
assert params.model == "test-model without embeddings"
assert params.input == ["Test 1", "Test 2"]
mock_index.add_chunks.assert_called_once()
args = mock_index.add_chunks.call_args[0]
assert args[0] == chunks
@ -321,9 +329,14 @@ class TestVectorDBWithIndex:
await vector_db_with_index.insert_chunks(chunks)
mock_inference_api.openai_embeddings.assert_called_once_with(
"test-model with partial embeddings", ["Test 1", "Test 3"]
)
# Verify openai_embeddings was called with correct params
mock_inference_api.openai_embeddings.assert_called_once()
call_args = mock_inference_api.openai_embeddings.call_args[0]
assert len(call_args) == 1
params = call_args[0]
assert isinstance(params, OpenAIEmbeddingsRequestWithExtraBody)
assert params.model == "test-model with partial embeddings"
assert params.input == ["Test 1", "Test 3"]
mock_index.add_chunks.assert_called_once()
args = mock_index.add_chunks.call_args[0]
assert len(args[0]) == 3