mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-12 05:54:38 +00:00
feat: Add /v1/embeddings endpoint to batches API (#3384)
# What does this PR do? This PR extends the Llama Stack Batches API to support the /v1/embeddings endpoint, enabling efficient batch processing of embedding requests alongside the existing /v1/chat/completions and /v1/completions support. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes: https://github.com/llamastack/llama-stack/issues/3145 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> ``` (stack-client) ➜ llama-stack git:(support/embeddings-api) conda activate stack-client && python -m pytest tests/unit/providers/batches/test_reference.py -v ============================================================================================================================================ test session starts ============================================================================================================================================= platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'xdist': '3.8.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, xdist-3.8.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 46 items tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_and_retrieve_batch_success PASSED [ 2%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_without_metadata PASSED [ 4%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_completion_window PASSED [ 6%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_endpoints[/v1/invalid/endpoint] PASSED [ 8%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_endpoints[] PASSED [ 10%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_metadata PASSED [ 13%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_retrieve_batch_not_found PASSED [ 15%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_success PASSED [ 17%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[failed] PASSED [ 19%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[expired] PASSED [ 21%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[completed] PASSED [ 23%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_not_found PASSED [ 26%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_empty PASSED [ 28%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_single_batch PASSED [ 30%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_multiple_batches PASSED [ 32%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_with_limit PASSED [ 34%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_with_pagination PASSED [ 36%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_invalid_after PASSED [ 39%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_kvstore_persistence PASSED [ 41%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_not_found PASSED [ 43%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_exists_empty_content PASSED [ 45%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_mixed_valid_invalid_json PASSED [ 47%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_model PASSED [ 50%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[custom_id-custom_id-missing_required_parameter-Missing required parameter: custom_id] PASSED [ 52%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[method-method-missing_required_parameter-Missing required parameter: method] PASSED [ 54%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[url-url-missing_required_parameter-Missing required parameter: url] PASSED [ 56%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[body-body-missing_required_parameter-Missing required parameter: body] PASSED [ 58%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[model-body.model-invalid_request-Model parameter is required] PASSED [ 60%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[messages-body.messages-invalid_request-Messages parameter is required] PASSED [ 63%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[custom_id-custom_id-missing_required_parameter-Missing required parameter: custom_id] PASSED [ 65%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[method-method-missing_required_parameter-Missing required parameter: method] PASSED [ 67%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[url-url-missing_required_parameter-Missing required parameter: url] PASSED [ 69%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[body-body-missing_required_parameter-Missing required parameter: body] PASSED [ 71%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[model-body.model-invalid_request-Model parameter is required] PASSED [ 73%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[prompt-body.prompt-invalid_request-Prompt parameter is required] PASSED [ 76%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_url_mismatch PASSED [ 78%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_multiple_errors_per_request PASSED [ 80%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_request_format PASSED [ 82%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[custom_id-custom_id-12345-Custom_id must be a string] PASSED [ 84%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[url-url-123-URL must be a string] PASSED [ 86%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[method-method-invalid_value2-Method must be a string] PASSED [ 89%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[body-body-invalid_value3-Body must be a JSON dictionary object] PASSED [ 91%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[model-body.model-123-Model must be a string] PASSED [ 93%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[messages-body.messages-invalid messages format-Messages must be an array] PASSED [ 95%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_max_concurrent_batches PASSED [ 97%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_embeddings_endpoint PASSED [100%] ``` --------- Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
Varsha
GitHub
parent
1394403360
commit
32fde8d9a8
7 changed files with 1755 additions and 28 deletions
|
|
@ -323,3 +323,92 @@ class TestBatchesIntegration:
|
|||
if final_batch.error_file_id is not None:
|
||||
deleted_error_file = openai_client.files.delete(final_batch.error_file_id)
|
||||
assert deleted_error_file.deleted
|
||||
|
||||
def test_batch_e2e_embeddings(self, openai_client, batch_helper, embedding_model_id):
|
||||
"""Run an end-to-end batch with embeddings requests including both string and list inputs."""
|
||||
batch_requests = [
|
||||
{
|
||||
"custom_id": "success-1",
|
||||
"method": "POST",
|
||||
"url": "/v1/embeddings",
|
||||
"body": {"model": embedding_model_id, "input": "Hello world", "encoding_format": "float"},
|
||||
},
|
||||
{
|
||||
"custom_id": "success-2",
|
||||
"method": "POST",
|
||||
"url": "/v1/embeddings",
|
||||
"body": {
|
||||
"model": embedding_model_id,
|
||||
"input": ["How are you?", "Good morning", "Have a great day"],
|
||||
"encoding_format": "float",
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
with batch_helper.create_file(batch_requests) as uploaded_file:
|
||||
batch = openai_client.batches.create(
|
||||
input_file_id=uploaded_file.id,
|
||||
endpoint="/v1/embeddings",
|
||||
completion_window="24h",
|
||||
metadata={"test": "e2e_embeddings_success"},
|
||||
)
|
||||
|
||||
final_batch = batch_helper.wait_for(
|
||||
batch.id,
|
||||
max_wait_time=3 * 60,
|
||||
expected_statuses={"completed"},
|
||||
timeout_action="skip",
|
||||
)
|
||||
|
||||
assert final_batch.status == "completed"
|
||||
assert final_batch.request_counts is not None
|
||||
assert final_batch.request_counts.total == 2
|
||||
assert final_batch.request_counts.completed == 2
|
||||
assert final_batch.output_file_id is not None
|
||||
|
||||
output_content = openai_client.files.content(final_batch.output_file_id)
|
||||
if isinstance(output_content, str):
|
||||
output_text = output_content
|
||||
else:
|
||||
output_text = output_content.content.decode("utf-8")
|
||||
|
||||
output_lines = output_text.strip().split("\n")
|
||||
assert len(output_lines) == 2
|
||||
|
||||
# Check first result (string input)
|
||||
result1 = json.loads(output_lines[0])
|
||||
assert result1["custom_id"] in ["success-1", "success-2"]
|
||||
assert "response" in result1
|
||||
assert result1["response"]["status_code"] == 200
|
||||
|
||||
# Verify the response body contains embeddings data
|
||||
response_body1 = json.loads(result1["response"]["body"])
|
||||
assert response_body1["object"] == "list"
|
||||
assert "data" in response_body1
|
||||
assert len(response_body1["data"]) == 1
|
||||
assert "embedding" in response_body1["data"][0]
|
||||
assert "index" in response_body1["data"][0]
|
||||
assert response_body1["data"][0]["index"] == 0
|
||||
|
||||
# Check second result (list input)
|
||||
result2 = json.loads(output_lines[1])
|
||||
assert result2["custom_id"] in ["success-1", "success-2"]
|
||||
assert "response" in result2
|
||||
assert result2["response"]["status_code"] == 200
|
||||
|
||||
# Verify the response body contains embeddings data for list input
|
||||
response_body2 = json.loads(result2["response"]["body"])
|
||||
assert response_body2["object"] == "list"
|
||||
assert "data" in response_body2
|
||||
assert len(response_body2["data"]) == 3 # Three strings in the list
|
||||
for i, embedding_data in enumerate(response_body2["data"]):
|
||||
assert "embedding" in embedding_data
|
||||
assert "index" in embedding_data
|
||||
assert embedding_data["index"] == i
|
||||
|
||||
deleted_output_file = openai_client.files.delete(final_batch.output_file_id)
|
||||
assert deleted_output_file.deleted
|
||||
|
||||
if final_batch.error_file_id is not None:
|
||||
deleted_error_file = openai_client.files.delete(final_batch.error_file_id)
|
||||
assert deleted_error_file.deleted
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue