yumoqing
608413a5d5
- Add /v1/chat/completions endpoint (POST) with streaming support - Add /v1/models endpoint (GET) listing available models - Add /v1/completions endpoint (POST) legacy compatibility - Add llm_api.py module with OpenAI API proxy via aiohttp - Add llm_service_url, llm_api_key, available_models to config model - Update harnessed_agent_config_view CRUD to protect API key field - Register new functions in init.py (harnessed_llm_chat_completions etc.) - Add .gitignore for pycache files Endpoints available under module path: POST /harnessed_agent/v1/chat/completions GET /harnessed_agent/v1/models POST /harnessed_agent/v1/completions
47 lines
1.3 KiB
Plaintext
47 lines
1.3 KiB
Plaintext
"""
|
|
OpenAI-compatible /v1/chat/completions endpoint
|
|
Accepts POST with JSON body matching OpenAI API format.
|
|
"""
|
|
import json
|
|
|
|
async def main():
|
|
# Read request body
|
|
body = {}
|
|
try:
|
|
raw_body = await request.read()
|
|
if raw_body:
|
|
body = json.loads(raw_body)
|
|
except Exception as e:
|
|
result = {
|
|
'error': {
|
|
'message': f'Invalid JSON body: {str(e)}',
|
|
'type': 'invalid_request_error',
|
|
'code': 400,
|
|
}
|
|
}
|
|
return json.dumps(result, ensure_ascii=False)
|
|
|
|
# Pass the request object for streaming support
|
|
body['_request'] = request
|
|
|
|
# Call the LLM API handler
|
|
result = await harnessed_llm_chat_completions(body)
|
|
|
|
# Handle streaming response (StreamResponse)
|
|
from aiohttp.web_response import StreamResponse
|
|
if isinstance(result, StreamResponse):
|
|
return result
|
|
|
|
# Handle error response
|
|
if 'error' in result:
|
|
status_code = result.get('error', {}).get('code', 500)
|
|
resp = web.Response(
|
|
status=status_code,
|
|
body=json.dumps(result, ensure_ascii=False),
|
|
content_type='application/json'
|
|
)
|
|
return resp
|
|
|
|
# Return successful response
|
|
return json.dumps(result, ensure_ascii=False)
|