Pr 3003 ci branch (#3007)

* change ChatCompletionChunk to align with "OpenAI Chat Completions streaming API"

Moving after tool_calls2

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

add in Buffering..

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

fix: handle usage outside of stream state and add tests

Simplifying everything quite a bit.

Remove the unused model_dump.

Clippy.

Clippy ?

Ruff.

Uppgrade the flake for latest transformers.

Upgrade after rebase.

Remove potential footgun.

Fix completion test.

* Clippy.

* Tweak for multi prompt.

* Ruff.

* Update the snapshot a bit.

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

Author: drbh

flake.lock

@@ -8,6 +8,7 @@
 from openai.types.chat.chat_completion_chunk import (
     ChatCompletionChunk as OAIChatCompletionChunk,
 )
+from openai.types.completion import Completion as OAICompletion
 import requests
 
 
@@ -39,7 +40,6 @@ def request(self, *args, **kwargs):
 from aiohttp import ClientConnectorError, ClientOSError, ServerDisconnectedError
 from docker.errors import NotFound
 from syrupy.extensions.json import JSONSnapshotExtension
-
 from text_generation import AsyncClient
 from text_generation.types import (
     BestOfSequence,
@@ -133,6 +133,7 @@ def _serialize(
             or isinstance(data, ChatCompletionComplete)
             or isinstance(data, Completion)
             or isinstance(data, OAIChatCompletionChunk)
+            or isinstance(data, OAICompletion)
         ):
             data = data.model_dump()
         elif isinstance(data, ChatCompletionStreamOutput) or isinstance(

integration-tests/conftest.py

@@ -0,0 +1,62 @@
+[
+  {
+    "choices": [
+      {
+        "delta": {
+          "content": "OK",
+          "role": "assistant",
+          "tool_calls": null
+        },
+        "finish_reason": null,
+        "index": 0,
+        "logprobs": null
+      }
+    ],
+    "created": 1741265520,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": null
+  },
+  {
+    "choices": [
+      {
+        "delta": {
+          "content": "!",
+          "role": "assistant",
+          "tool_calls": null
+        },
+        "finish_reason": null,
+        "index": 0,
+        "logprobs": null
+      }
+    ],
+    "created": 1741265520,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": null
+  },
+  {
+    "choices": [
+      {
+        "delta": {
+          "content": "",
+          "role": "assistant",
+          "tool_calls": null
+        },
+        "finish_reason": "stop",
+        "index": 0,
+        "logprobs": null
+      }
+    ],
+    "created": 1741265520,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": null
+  }
+]

integration-tests/models/__snapshots__/test_completion_prompts/test_chat_hfhub_nousage.json

@@ -0,0 +1,75 @@
+[
+  {
+    "choices": [
+      {
+        "delta": {
+          "content": "OK",
+          "role": "assistant",
+          "tool_calls": null
+        },
+        "finish_reason": null,
+        "index": 0,
+        "logprobs": null
+      }
+    ],
+    "created": 1741266005,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": null
+  },
+  {
+    "choices": [
+      {
+        "delta": {
+          "content": "!",
+          "role": "assistant",
+          "tool_calls": null
+        },
+        "finish_reason": null,
+        "index": 0,
+        "logprobs": null
+      }
+    ],
+    "created": 1741266005,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": null
+  },
+  {
+    "choices": [
+      {
+        "delta": {
+          "content": "",
+          "role": "assistant",
+          "tool_calls": null
+        },
+        "finish_reason": "stop",
+        "index": 0,
+        "logprobs": null
+      }
+    ],
+    "created": 1741266005,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": null
+  },
+  {
+    "choices": [],
+    "created": 1741266005,
+    "id": "",
+    "model": "meta-llama/Llama-3.1-8B-Instruct",
+    "object": "chat.completion.chunk",
+    "system_fingerprint": "3.1.2-dev0-native",
+    "usage": {
+      "completion_tokens": 3,
+      "prompt_tokens": 39,
+      "total_tokens": 42
+    }
+  }
+]