mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
79bed44b04
Propagate test IDs from client to server via HTTP headers to maintain proper test isolation when running with server-based stack configs. Without this, recorded/replayed inference requests in server mode would leak across tests. Changes: - Patch client _prepare_request to inject test ID into provider data header - Sync test context from provider data on server side before storage operations - Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config - Configure console width for cleaner log output in CI - Add SQLITE_STORE_DIR temp directory for test data isolation
54 lines
1.4 KiB
JSON
54 lines
1.4 KiB
JSON
{
|
|
"test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-emb=ollama/all-minilm:l6-v2]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/embeddings",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "all-minilm:l6-v2",
|
|
"input": "Test dimensions parameter",
|
|
"encoding_format": "float",
|
|
"dimensions": 16
|
|
},
|
|
"endpoint": "/v1/embeddings",
|
|
"model": "all-minilm:l6-v2"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
|
|
"__data__": {
|
|
"data": [
|
|
{
|
|
"embedding": [
|
|
0.25369987,
|
|
0.016355688,
|
|
-0.29676768,
|
|
0.316427,
|
|
-0.18642858,
|
|
0.076206245,
|
|
-0.031503417,
|
|
0.29860005,
|
|
-0.496603,
|
|
-0.36621967,
|
|
0.25334543,
|
|
-0.333392,
|
|
0.005993569,
|
|
0.14079759,
|
|
-0.13775977,
|
|
-0.14680246
|
|
],
|
|
"index": 0,
|
|
"object": "embedding"
|
|
}
|
|
],
|
|
"model": "all-minilm:l6-v2",
|
|
"object": "list",
|
|
"usage": {
|
|
"prompt_tokens": 3,
|
|
"total_tokens": 3
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|