Skip to content

fix: enhance llm-katan OpenAI API compatibility for issue #241 #354

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Oct 7, 2025
Merged

fix: enhance llm-katan OpenAI API compatibility for issue #241 #354

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a6b308c
fix: enhance llm-katan OpenAI API compatibility for issue #241
yossiovadia Oct 6, 2025
415346a
bump llm-katan version to 0.1.9 for PyPI release
yossiovadia Oct 6, 2025
29ffb27
chore: trigger CI re-run to check pre-commit status
yossiovadia Oct 6, 2025
d3dcf38
trigger pre-commit formatting fix
yossiovadia Oct 7, 2025
6886362
fix: apply black formatting to llm-katan Python files
yossiovadia Oct 7, 2025
c5968f0
fix: apply black formatting to llm-katan Python files for CI compliance
yossiovadia Oct 7, 2025
528bc6d
Merge branch 'main' into fix/llm-katan-openai-compatibility-241
yossiovadia Oct 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 41 additions & 2 deletions e2e-tests/llm-katan/llm_katan/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,20 +136,27 @@ async def generate(
"object": "chat.completion",
"created": int(time.time()),
"model": self.config.served_model_name,
"system_fingerprint": "llm-katan-transformers",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": generated_text},
"logprobs": None,
"finish_reason": "stop",
}
],
"usage": {
"prompt_tokens": prompt_tokens,
"completion_tokens": completion_tokens,
"total_tokens": total_tokens,
"prompt_tokens_details": {"cached_tokens": 0},
"completion_tokens_details": {"reasoning_tokens": 0},
},
}

# Add token_usage as alias for better SDK compatibility
response_data["token_usage"] = response_data["usage"]

if stream:
# For streaming, yield chunks
words = generated_text.split()
Expand All @@ -159,12 +166,14 @@ async def generate(
"object": "chat.completion.chunk",
"created": response_data["created"],
"model": self.config.served_model_name,
"system_fingerprint": "llm-katan-transformers",
"choices": [
{
"index": 0,
"delta": {
"content": word + " " if i < len(words) - 1 else word
},
"logprobs": None,
"finish_reason": None,
}
],
Expand All @@ -178,7 +187,17 @@ async def generate(
"object": "chat.completion.chunk",
"created": response_data["created"],
"model": self.config.served_model_name,
"choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
"system_fingerprint": "llm-katan-transformers",
"choices": [
{"index": 0, "delta": {}, "logprobs": None, "finish_reason": "stop"}
],
"usage": {
"prompt_tokens": prompt_tokens,
"completion_tokens": completion_tokens,
"total_tokens": total_tokens,
"prompt_tokens_details": {"cached_tokens": 0},
"completion_tokens_details": {"reasoning_tokens": 0},
},
}
yield final_chunk
else:
Expand Down Expand Up @@ -295,10 +314,12 @@ async def generate(
"object": "chat.completion",
"created": int(time.time()),
"model": self.config.served_model_name,
"system_fingerprint": "llm-katan-vllm",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": generated_text},
"logprobs": None,
"finish_reason": "stop",
}
],
Expand All @@ -307,9 +328,14 @@ async def generate(
"completion_tokens": len(output.outputs[0].token_ids),
"total_tokens": len(output.prompt_token_ids)
+ len(output.outputs[0].token_ids),
"prompt_tokens_details": {"cached_tokens": 0},
"completion_tokens_details": {"reasoning_tokens": 0},
},
}

# Add token_usage as alias for better SDK compatibility
response_data["token_usage"] = response_data["usage"]

if stream:
# For streaming, yield chunks (simplified for now)
words = generated_text.split()
Expand All @@ -319,12 +345,14 @@ async def generate(
"object": "chat.completion.chunk",
"created": response_data["created"],
"model": self.config.served_model_name,
"system_fingerprint": "llm-katan-vllm",
"choices": [
{
"index": 0,
"delta": {
"content": word + " " if i < len(words) - 1 else word
},
"logprobs": None,
"finish_reason": None,
}
],
Expand All @@ -338,7 +366,18 @@ async def generate(
"object": "chat.completion.chunk",
"created": response_data["created"],
"model": self.config.served_model_name,
"choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
"system_fingerprint": "llm-katan-vllm",
"choices": [
{"index": 0, "delta": {}, "logprobs": None, "finish_reason": "stop"}
],
"usage": {
"prompt_tokens": len(output.prompt_token_ids),
"completion_tokens": len(output.outputs[0].token_ids),
"total_tokens": len(output.prompt_token_ids)
+ len(output.outputs[0].token_ids),
"prompt_tokens_details": {"cached_tokens": 0},
"completion_tokens_details": {"reasoning_tokens": 0},
},
}
yield final_chunk
else:
Expand Down
9 changes: 7 additions & 2 deletions e2e-tests/llm-katan/llm_katan/server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,8 +181,13 @@ async def generate_stream():

return StreamingResponse(
generate_stream(),
media_type="text/plain",
headers={"Cache-Control": "no-cache", "Connection": "keep-alive"},
media_type="text/event-stream",
headers={
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Access-Control-Allow-Origin": "*",
"Access-Control-Allow-Headers": "Content-Type",
},
)
else:
# Non-streaming response
Expand Down
2 changes: 1 addition & 1 deletion e2e-tests/llm-katan/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

[project]
name = "llm-katan"
version = "0.1.8"
version = "0.1.9"
description = "LLM Katan - Lightweight LLM Server for Testing - Real tiny models with FastAPI and HuggingFace"
readme = "README.md"
authors = [
Expand Down
Loading