Iyeoluwads/ds_zagres_ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
Iyeoluwa Akinrinola
2025-05-12 16:30:35 +01:00
parent 7c61e98340
commit f00941cece
4 changed files with 180 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ai_service/api.py
+125 -2
View File
@@ -7,6 +7,8 @@ from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel, Field
from typing import List, Optional
import uuid
from datetime import datetime, timezone
from ai_service.models.model_service import model_service
from ai_service.models.chat_service import chat_service
@@ -120,7 +122,7 @@ async def test_ollama_connection():
try:
# Try to connect to Ollama API
response = requests.get(f"{config.OLLAMA_API_URL}/api/tags", timeout=5)
response = requests.get(f"{config.OLLAMA_API_URL}/api/tags", timeout=config.API_TIMEOUT)
response.raise_for_status()
# Return the models from Ollama
@@ -130,6 +132,106 @@ async def test_ollama_connection():
"ollama_url": config.OLLAMA_API_URL,
"models": response.json()
}
except requests.exceptions.Timeout as e:
return {
"status": "error",
"message": f"Timeout connecting to Ollama API: {str(e)}. The request exceeded the {config.API_TIMEOUT} second timeout.",
"ollama_url": config.OLLAMA_API_URL
}
except requests.exceptions.ConnectionError as e:
return {
"status": "error",
"message": f"Connection error to Ollama API: {str(e)}. Please check if Ollama is running at {config.OLLAMA_API_URL}.",
"ollama_url": config.OLLAMA_API_URL
}
except Exception as e:
return {
"status": "error",
"message": f"Failed to connect to Ollama API: {str(e)}",
"ollama_url": config.OLLAMA_API_URL
}
@app.post("/test-chat")
async def test_chat_completion():
"""
Test the chat completion with a simple prompt.
Returns:
Model response.
"""
try:
# Use the model service directly
response = model_service.generate_response(
model_id=config.DEFAULT_MODEL,
prompt="Hello, how are you?",
context=[],
use_rag=False
)
return {
"status": "success",
"model": config.DEFAULT_MODEL,
"response": response,
"ollama_url": config.OLLAMA_API_URL
}
except Exception as e:
return {
"status": "error",
"message": f"Failed to get chat completion: {str(e)}",
"ollama_url": config.OLLAMA_API_URL
}
@app.post("/test-ollama-direct")
async def test_ollama_direct():
"""
Test the Ollama API directly with a simple chat request.
Returns:
Raw Ollama API response.
"""
import requests
try:
# Prepare a simple chat request
request_json = {
"model": config.DEFAULT_MODEL,
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, how are you?"}
],
"stream": False
}
# Make the API call to Ollama
print(f"Sending direct request to Ollama API at: {config.OLLAMA_API_URL}/api/chat")
response = requests.post(
f"{config.OLLAMA_API_URL}/api/chat",
headers={"Content-Type": "application/json"},
json=request_json,
timeout=config.API_TIMEOUT
)
response.raise_for_status()
result = response.json()
return {
"status": "success",
"ollama_url": config.OLLAMA_API_URL,
"request": request_json,
"response": result
}
except requests.exceptions.Timeout as e:
return {
"status": "error",
"message": f"Timeout connecting to Ollama API: {str(e)}. The request exceeded the {config.API_TIMEOUT} second timeout.",
"ollama_url": config.OLLAMA_API_URL
}
except requests.exceptions.ConnectionError as e:
return {
"status": "error",
"message": f"Connection error to Ollama API: {str(e)}. Please check if Ollama is running at {config.OLLAMA_API_URL}.",
"ollama_url": config.OLLAMA_API_URL
}
except Exception as e:
return {
"status": "error",
@@ -151,6 +253,7 @@ async def get_config():
"openwebui_url": config.OPENWEBUI_URL,
"ollama_api_url": config.OLLAMA_API_URL,
"default_model": config.DEFAULT_MODEL,
"api_timeout": config.API_TIMEOUT,
"available_models": list(model_service.AVAILABLE_MODELS.keys())
}
@@ -251,6 +354,11 @@ async def send_message(chat_id: str, request: MessageRequest):
Bot response message.
"""
try:
print(f"Processing message for chat {chat_id} from user {request.user_id}")
print(f"Message: {request.message[:50]}...") # Print first 50 chars of message
print(f"Using RAG: {request.use_rag}")
print(f"Model parameters: temperature={request.temperature}, max_tokens={request.max_tokens}")
# Extract model parameters from the request
response = chat_service.get_chat_response(
chat_id=chat_id,
@@ -270,10 +378,25 @@ async def send_message(chat_id: str, request: MessageRequest):
function_calling=request.function_calling
)
print(f"Response received. Length: {len(response.get('content', ''))}")
return response
except ValueError as e:
raise HTTPException(status_code=404, detail=str(e))
error_msg = f"Chat not found: {str(e)}"
print(f"ERROR: {error_msg}")
raise HTTPException(status_code=404, detail=error_msg)
except Exception as e:
error_msg = f"Error processing message: {str(e)}"
print(f"ERROR: {error_msg}")
# Return an error message instead of raising an exception
# This ensures the client gets a proper response
return {
"id": str(uuid.uuid4()),
"content": f"Error processing message: {str(e)}",
"user_id": None,
"is_user_message": False,
"timestamp": datetime.now(timezone.utc).isoformat()
}
@app.post("/chats/{chat_id}/members/{user_id}")
async def add_team_member(chat_id: str, user_id: str):
ai_service/config.py
+1
View File
@@ -24,6 +24,7 @@ class Config:
# Ollama configuration
OLLAMA_API_URL = os.environ.get('OLLAMA_API_URL', 'http://127.0.0.1:11434')
DEFAULT_MODEL = os.environ.get('DEFAULT_MODEL', 'llama3.1')
API_TIMEOUT = int(os.environ.get('API_TIMEOUT', 300)) # Default timeout of 5 minutes (300 seconds)
# Document processing
CHUNK_SIZE = int(os.environ.get('CHUNK_SIZE', 1000))
ai_service/models/chat_service.py
+28 -14
View File
@@ -286,21 +286,35 @@ class ChatService:
# Get response from model
model_id = chat['model_id']
response_text = model_service.generate_response(
model_id=model_id,
prompt=message,
context=context,
use_rag=use_rag,
model_params=model_params
)
try:
print(f"Requesting response from model {model_id} for chat {chat_id}")
response_text = model_service.generate_response(
model_id=model_id,
prompt=message,
context=context,
use_rag=use_rag,
model_params=model_params
)
# Add bot response to chat
response_message = self.add_message(
chat_id=chat_id,
content=response_text,
user_id=user_id,
is_user_message=False
)
# Add bot response to chat
response_message = self.add_message(
chat_id=chat_id,
content=response_text,
user_id=user_id,
is_user_message=False
)
except Exception as e:
error_message = f"Error generating response: {str(e)}"
print(f"ERROR: {error_message}")
# Add error message to chat
response_message = self.add_message(
chat_id=chat_id,
content=error_message,
user_id=user_id,
is_user_message=False
)
return response_message
ai_service/models/model_service.py
+26 -5
View File
@@ -52,6 +52,7 @@ class ModelService:
self.ollama_api_url = config.OLLAMA_API_URL
self.openwebui_url = config.OPENWEBUI_URL
self.openwebui_api_key = config.OPENWEBUI_API_KEY
self.api_timeout = config.API_TIMEOUT
def get_available_models(self) -> List[Dict[str, Any]]:
"""
@@ -193,7 +194,7 @@ class ModelService:
f"{self.openwebui_url}/api/chat/completions",
headers=headers,
json=openwebui_request,
timeout=60 # Longer timeout for RAG
timeout=self.api_timeout
)
response.raise_for_status()
@@ -205,9 +206,19 @@ class ModelService:
else:
return "Error: Unexpected response format from OpenWebUI"
except requests.exceptions.Timeout as e:
error_msg = f"Timeout error connecting to OpenWebUI API: {str(e)}. The request exceeded the {self.api_timeout} second timeout."
print(f"ERROR: {error_msg}")
print("Falling back to direct Ollama call without RAG")
# Continue to the Ollama API call below
except requests.exceptions.ConnectionError as e:
error_msg = f"Connection error to OpenWebUI API: {str(e)}. Please check if OpenWebUI is running at {self.openwebui_url}."
print(f"ERROR: {error_msg}")
print("Falling back to direct Ollama call without RAG")
# Continue to the Ollama API call below
except Exception as e:
print(f"Error calling OpenWebUI API: {str(e)}")
# Fall back to direct Ollama call without RAG
error_msg = f"Error calling OpenWebUI API: {str(e)}"
print(f"ERROR: {error_msg}")
print("Falling back to direct Ollama call without RAG")
# Continue to the Ollama API call below
@@ -250,7 +261,7 @@ class ModelService:
f"{self.ollama_api_url}/api/chat",
headers={"Content-Type": "application/json"},
json=request_json,
timeout=60
timeout=self.api_timeout
)
response.raise_for_status()
@@ -263,8 +274,18 @@ class ModelService:
else:
return "Error: Unexpected response format from Ollama"
except requests.exceptions.Timeout as e:
error_msg = f"Timeout error connecting to Ollama API: {str(e)}. The request exceeded the {self.api_timeout} second timeout."
print(f"ERROR: {error_msg}")
return error_msg
except requests.exceptions.ConnectionError as e:
error_msg = f"Connection error to Ollama API: {str(e)}. Please check if Ollama is running at {self.ollama_api_url}."
print(f"ERROR: {error_msg}")
return error_msg
except Exception as e:
return f"Error generating response: {str(e)}"
error_msg = f"Error generating response: {str(e)}"
print(f"ERROR: {error_msg}")
return error_msg
# Create a singleton instance