mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 06:53:47 +00:00
feat: add embedding and dynamic model support to Together inference adapter
- updated to use OpenAIMixin - workarounds for Together api quirks - recordings for together suite when subdirs=inference,pattern=openai test with: `TOGETHER_API_KEY=_NONE_ ./scripts/integration-tests.sh --stack-config server:ci-tests --setup together --subdirs inference --pattern openai`
This commit is contained in:
parent
f4ab154ade
commit
3e02dc5c2f
20 changed files with 9227 additions and 180 deletions
59
tests/integration/recordings/responses/6c4e2e207e8a.json
Normal file
59
tests/integration/recordings/responses/6c4e2e207e8a.json
Normal file
|
@ -0,0 +1,59 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.together.xyz/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Which planet do humans live on?"
|
||||
}
|
||||
],
|
||||
"stream": false
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "oBUtMpf-62bZhn-9801a16bc8d642d3",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "Humans live on Earth.",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": []
|
||||
},
|
||||
"seed": 14150443913665712000
|
||||
}
|
||||
],
|
||||
"created": 1758038990,
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": null,
|
||||
"usage": {
|
||||
"completion_tokens": 6,
|
||||
"prompt_tokens": 42,
|
||||
"total_tokens": 48,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null,
|
||||
"cached_tokens": 0
|
||||
},
|
||||
"prompt": []
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue