mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
# What does this PR do? recorded for: ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup fireworks --subdirs inference --pattern openai ## Test Plan ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup fireworks --subdirs inference --pattern openai
56 lines
1.4 KiB
JSON
56 lines
1.4 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.fireworks.ai/inference/v1/v1/embeddings",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "accounts/fireworks/models/qwen3-embedding-8b",
|
|
"input": "Test dimensions parameter",
|
|
"encoding_format": "float",
|
|
"dimensions": 16
|
|
},
|
|
"endpoint": "/v1/embeddings",
|
|
"model": "accounts/fireworks/models/qwen3-embedding-8b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
|
|
"__data__": {
|
|
"data": [
|
|
{
|
|
"embedding": [
|
|
-0.9296875,
|
|
5.1875,
|
|
-2.140625,
|
|
0.171875,
|
|
-2.25,
|
|
-0.8359375,
|
|
-0.828125,
|
|
1.15625,
|
|
2.328125,
|
|
-1.0078125,
|
|
-3.0,
|
|
4.09375,
|
|
0.8359375,
|
|
0.1015625,
|
|
2.015625,
|
|
-1.0859375
|
|
],
|
|
"index": 0,
|
|
"object": "embedding",
|
|
"raw_output": null
|
|
}
|
|
],
|
|
"model": "accounts/fireworks/models/qwen3-embedding-8b",
|
|
"object": "list",
|
|
"usage": {
|
|
"prompt_tokens": 5,
|
|
"total_tokens": 5,
|
|
"completion_tokens": 0
|
|
},
|
|
"perf_metrics": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|