mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
# What does this PR do? add/enable the Databricks inference adapter Databricks inference adapter was broken, closes #3486 - remove deprecated completion / chat_completion endpoints - enable dynamic model listing w/o refresh, listing is not async - use SecretStr instead of str for token - backward incompatible change: for consistency with databricks docs, env DATABRICKS_URL -> DATABRICKS_HOST and DATABRICKS_API_TOKEN -> DATABRICKS_TOKEN - databricks urls are custom per user/org, add special recorder handling for databricks urls - add integration test --setup databricks - enable chat completions tests - enable embeddings tests - disable n > 1 tests - disable embeddings base64 tests - disable embeddings dimensions tests note: reasoning models, e.g. gpt oss, fail because databricks has a custom, incompatible response format ## Test Plan ci and ``` ./scripts/integration-tests.sh --stack-config server:ci-tests --setup databricks --subdirs inference --pattern openai ``` note: databricks needs to be manually added to the ci-tests distro for replay testing
83 lines
2.3 KiB
JSON
83 lines
2.3 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "__databricks__/serving-endpoints/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "databricks-meta-llama-3-3-70b-instruct",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather in Tokyo? Use the get_weather function to get the weather."
|
|
}
|
|
],
|
|
"stream": false,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "get_weather",
|
|
"description": "Get the weather in a given city",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"city": {
|
|
"type": "string",
|
|
"description": "The city to get the weather for"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "databricks-meta-llama-3-3-70b-instruct"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl_e54eaa97-ace3-4af6-b3a2-b1627bc77488",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [
|
|
{
|
|
"id": "call_9c7f9e5f-c6eb-4c3c-a7b3-e9fe0e786b50",
|
|
"function": {
|
|
"arguments": "{ \"city\": \"Tokyo\" }",
|
|
"name": "get_weather"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"created": 1758326507,
|
|
"model": "meta-llama-3.3-70b-instruct-121024",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 15,
|
|
"prompt_tokens": 682,
|
|
"total_tokens": 697,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|