Fix issues
This commit is contained in:
Iyeoluwa Akinrinola
+51
-1
@@ -11,6 +11,7 @@ from typing import List, Optional
|
||||
from ai_service.models.model_service import model_service
|
||||
from ai_service.models.chat_service import chat_service
|
||||
from ai_service.openwebui_api import router as openwebui_router
|
||||
from ai_service.config import config
|
||||
|
||||
# Create FastAPI app
|
||||
app = FastAPI(
|
||||
@@ -107,6 +108,52 @@ async def health_check():
|
||||
"""
|
||||
return {"status": "healthy"}
|
||||
|
||||
@app.get("/test-ollama")
|
||||
async def test_ollama_connection():
|
||||
"""
|
||||
Test the connection to the Ollama API.
|
||||
|
||||
Returns:
|
||||
Connection status and available models from Ollama.
|
||||
"""
|
||||
import requests
|
||||
|
||||
try:
|
||||
# Try to connect to Ollama API
|
||||
response = requests.get(f"{config.OLLAMA_API_URL}/api/tags", timeout=5)
|
||||
response.raise_for_status()
|
||||
|
||||
# Return the models from Ollama
|
||||
return {
|
||||
"status": "success",
|
||||
"message": "Successfully connected to Ollama API",
|
||||
"ollama_url": config.OLLAMA_API_URL,
|
||||
"models": response.json()
|
||||
}
|
||||
except Exception as e:
|
||||
return {
|
||||
"status": "error",
|
||||
"message": f"Failed to connect to Ollama API: {str(e)}",
|
||||
"ollama_url": config.OLLAMA_API_URL
|
||||
}
|
||||
|
||||
@app.get("/config")
|
||||
async def get_config():
|
||||
"""
|
||||
Get the current configuration.
|
||||
|
||||
Returns:
|
||||
Current configuration settings.
|
||||
"""
|
||||
return {
|
||||
"api_host": config.API_HOST,
|
||||
"api_port": config.API_PORT,
|
||||
"openwebui_url": config.OPENWEBUI_URL,
|
||||
"ollama_api_url": config.OLLAMA_API_URL,
|
||||
"default_model": config.DEFAULT_MODEL,
|
||||
"available_models": list(model_service.AVAILABLE_MODELS.keys())
|
||||
}
|
||||
|
||||
|
||||
|
||||
# Model endpoints
|
||||
@@ -118,7 +165,10 @@ async def get_available_models():
|
||||
Returns:
|
||||
List of model information.
|
||||
"""
|
||||
return model_service.get_available_models()
|
||||
models = model_service.get_available_models()
|
||||
# Debug log
|
||||
print(f"API models: {models}")
|
||||
return models
|
||||
|
||||
@app.get("/models/{model_id}", response_model=ModelInfo)
|
||||
async def get_model_info(model_id: str):
|
||||
|
||||
@@ -22,7 +22,7 @@ class Config:
|
||||
OPENWEBUI_API_KEY = os.environ.get('OPENWEBUI_API_KEY', '')
|
||||
|
||||
# Ollama configuration
|
||||
OLLAMA_API_URL = os.environ.get('OLLAMA_API_URL', 'http://104.225.217.215:11434')
|
||||
OLLAMA_API_URL = os.environ.get('OLLAMA_API_URL', 'http://127.0.0.1:11434')
|
||||
DEFAULT_MODEL = os.environ.get('DEFAULT_MODEL', 'llama3.1')
|
||||
|
||||
# Document processing
|
||||
|
||||
@@ -3,6 +3,7 @@ Service for model management and interaction.
|
||||
"""
|
||||
|
||||
import requests
|
||||
import json
|
||||
from typing import List, Dict, Any, Optional
|
||||
|
||||
from ai_service.config import config
|
||||
@@ -68,6 +69,21 @@ class ModelService:
|
||||
}
|
||||
models.append(model_data)
|
||||
|
||||
# Debug log
|
||||
print(f"Model service models: {models}")
|
||||
|
||||
# Ensure we're returning a non-empty list
|
||||
if not models:
|
||||
# Return a default model if none are found
|
||||
return [{
|
||||
'id': 'llama3.1',
|
||||
'name': 'Llama 3 (8B)',
|
||||
'description': 'Meta Llama 3 8B model via Ollama',
|
||||
'provider': 'ollama',
|
||||
'max_tokens': 8192,
|
||||
'is_default': True
|
||||
}]
|
||||
|
||||
return models
|
||||
|
||||
def get_model_info(self, model_id: str) -> Optional[Dict[str, Any]]:
|
||||
@@ -106,8 +122,17 @@ class ModelService:
|
||||
Returns:
|
||||
Generated response.
|
||||
"""
|
||||
# Debug configuration information
|
||||
print(f"ModelService configuration:")
|
||||
print(f" - Ollama API URL: {self.ollama_api_url}")
|
||||
print(f" - OpenWebUI URL: {self.openwebui_url}")
|
||||
print(f" - Default model: {self.default_model}")
|
||||
print(f" - Requested model: {model_id}")
|
||||
print(f" - Using RAG: {use_rag}")
|
||||
|
||||
if model_id not in self.AVAILABLE_MODELS:
|
||||
model_id = self.default_model
|
||||
print(f" - Model not found, using default: {model_id}")
|
||||
|
||||
# Ensure we're using a valid model
|
||||
# (model_id is already validated above)
|
||||
@@ -158,6 +183,11 @@ class ModelService:
|
||||
if self.openwebui_api_key:
|
||||
headers["Authorization"] = f"Bearer {self.openwebui_api_key}"
|
||||
|
||||
# Debug logs
|
||||
print(f"Sending RAG request to OpenWebUI at: {self.openwebui_url}/api/chat/completions")
|
||||
print(f"OpenWebUI request: {json.dumps(openwebui_request, indent=2)}")
|
||||
print(f"Headers: {headers}")
|
||||
|
||||
# OpenWebUI API endpoint is /api/chat/completions
|
||||
response = requests.post(
|
||||
f"{self.openwebui_url}/api/chat/completions",
|
||||
@@ -213,6 +243,9 @@ class ModelService:
|
||||
headers = {"Content-Type": "application/json"}
|
||||
|
||||
# Direct Ollama API call
|
||||
print(f"Sending request to Ollama API at: {self.ollama_api_url}/api/chat")
|
||||
print(f"Request JSON: {json.dumps(request_json, indent=2)}")
|
||||
|
||||
response = requests.post(
|
||||
f"{self.ollama_api_url}/api/chat",
|
||||
headers={"Content-Type": "application/json"},
|
||||
|
||||
+37
-21
@@ -23,7 +23,7 @@ async def get_models():
|
||||
Get available models in OpenWebUI-compatible format.
|
||||
"""
|
||||
models = model_service.get_available_models()
|
||||
|
||||
|
||||
# Convert to OpenWebUI format
|
||||
openwebui_models = []
|
||||
for model in models:
|
||||
@@ -36,7 +36,23 @@ async def get_models():
|
||||
"root": model["id"],
|
||||
"parent": None
|
||||
})
|
||||
|
||||
|
||||
# Debug log
|
||||
print(f"OpenWebUI models: {json.dumps(openwebui_models, indent=2)}")
|
||||
|
||||
# Ensure we're returning a properly formatted list
|
||||
if not openwebui_models:
|
||||
# Return at least one default model if none are found
|
||||
return [{
|
||||
"id": "llama3.1",
|
||||
"object": "model",
|
||||
"created": int(time.time()),
|
||||
"owned_by": "user",
|
||||
"permission": [],
|
||||
"root": "llama3.1",
|
||||
"parent": None
|
||||
}]
|
||||
|
||||
return openwebui_models
|
||||
|
||||
# Chat completions endpoint (OpenAI-compatible)
|
||||
@@ -47,7 +63,7 @@ async def chat_completions(request: Request):
|
||||
"""
|
||||
# Parse request body
|
||||
body = await request.json()
|
||||
|
||||
|
||||
# Extract parameters
|
||||
model_id = body.get("model", "llama3.1")
|
||||
messages = body.get("messages", [])
|
||||
@@ -58,26 +74,26 @@ async def chat_completions(request: Request):
|
||||
frequency_penalty = body.get("frequency_penalty")
|
||||
presence_penalty = body.get("presence_penalty")
|
||||
stop = body.get("stop")
|
||||
|
||||
|
||||
# Create a unique chat ID
|
||||
chat_id = str(uuid.uuid4())
|
||||
|
||||
|
||||
# Create a user ID (in a real implementation, this would come from authentication)
|
||||
user_id = "openwebui-user"
|
||||
|
||||
|
||||
# Create a new chat
|
||||
chat_service.create_chat(user_id=user_id, title="API Chat", model_id=model_id)
|
||||
|
||||
|
||||
# Extract the user's message (last user message in the array)
|
||||
user_message = None
|
||||
for msg in reversed(messages):
|
||||
if msg.get("role") == "user":
|
||||
user_message = msg.get("content")
|
||||
break
|
||||
|
||||
|
||||
if not user_message:
|
||||
raise HTTPException(status_code=400, detail="No user message found")
|
||||
|
||||
|
||||
# Get chat response
|
||||
response = chat_service.get_chat_response(
|
||||
chat_id=chat_id,
|
||||
@@ -90,10 +106,10 @@ async def chat_completions(request: Request):
|
||||
presence_penalty=presence_penalty,
|
||||
stop_sequences=stop if isinstance(stop, list) else [stop] if stop else None
|
||||
)
|
||||
|
||||
|
||||
# Format response in OpenAI-compatible format
|
||||
completion_id = f"chatcmpl-{str(uuid.uuid4())[:8]}"
|
||||
|
||||
|
||||
openai_response = {
|
||||
"id": completion_id,
|
||||
"object": "chat.completion",
|
||||
@@ -115,16 +131,16 @@ async def chat_completions(request: Request):
|
||||
"total_tokens": -1
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
# Handle streaming if requested
|
||||
if stream:
|
||||
async def generate_stream():
|
||||
# Yield the response in the SSE format
|
||||
yield f"data: {json.dumps(openai_response)}\n\n"
|
||||
yield "data: [DONE]\n\n"
|
||||
|
||||
|
||||
return StreamingResponse(generate_stream(), media_type="text/event-stream")
|
||||
|
||||
|
||||
return openai_response
|
||||
|
||||
# Health check endpoint
|
||||
@@ -143,27 +159,27 @@ async def ollama_generate(request: Request):
|
||||
"""
|
||||
# Parse request body
|
||||
body = await request.json()
|
||||
|
||||
|
||||
# Extract parameters
|
||||
model_id = body.get("model", "llama3.1")
|
||||
prompt = body.get("prompt", "")
|
||||
|
||||
|
||||
# Create a unique chat ID
|
||||
chat_id = str(uuid.uuid4())
|
||||
|
||||
|
||||
# Create a user ID (in a real implementation, this would come from authentication)
|
||||
user_id = "openwebui-user"
|
||||
|
||||
|
||||
# Create a new chat
|
||||
chat_service.create_chat(user_id=user_id, title="API Chat", model_id=model_id)
|
||||
|
||||
|
||||
# Get chat response
|
||||
response = chat_service.get_chat_response(
|
||||
chat_id=chat_id,
|
||||
message=prompt,
|
||||
user_id=user_id
|
||||
)
|
||||
|
||||
|
||||
# Format response in Ollama-compatible format
|
||||
ollama_response = {
|
||||
"model": model_id,
|
||||
@@ -171,5 +187,5 @@ async def ollama_generate(request: Request):
|
||||
"response": response.get("content", ""),
|
||||
"done": True
|
||||
}
|
||||
|
||||
|
||||
return ollama_response
|
||||
|
||||
Reference in New Issue
Block a user