featu: support passing "extra body" throught to providers

# What does this PR do?
Allows passing through extra_body parameters to inference providers.


closes #2720

## Test Plan
CI and added new test
This commit is contained in:
Eric Huang 2025-10-10 16:00:30 -07:00
parent 80d58ab519
commit c4dbaa9d4c
41 changed files with 3145 additions and 200 deletions

View file

@ -0,0 +1,44 @@
{
"test_id": "tests/integration/batches/test_batches.py::TestBatchesIntegration::test_batch_e2e_completions[txt=ollama/llama3.2:3b-instruct-fp16]",
"request": {
"method": "POST",
"url": "http://0.0.0.0:11434/v1/v1/completions",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"prompt": "Say completions",
"max_tokens": 20
},
"endpoint": "/v1/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.completion.Completion",
"__data__": {
"id": "rec-92d49675c903",
"choices": [
{
"finish_reason": "length",
"index": 0,
"logprobs": null,
"text": "What would you like me to say completion about? Would you like me to complete a thought, finish"
}
],
"created": 0,
"model": "llama3.2:3b-instruct-fp16",
"object": "text_completion",
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 20,
"prompt_tokens": 28,
"total_tokens": 48,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
},
"id_normalization_mapping": {}
}