File size: 5,666 Bytes
87a12c6
 
 
 
 
 
 
9a9ec03
 
87a12c6
6348ce6
3297dba
9a9ec03
87a12c6
 
 
 
 
9a9ec03
87a12c6
9a9ec03
 
87a12c6
 
 
 
 
9a9ec03
87a12c6
9a9ec03
 
 
87a12c6
9a9ec03
 
a1c0774
9a9ec03
 
 
 
 
 
 
 
 
 
 
 
 
87a12c6
 
 
 
 
 
 
 
 
 
5c2acfd
 
87a12c6
9a9ec03
 
 
87a12c6
 
 
 
9a9ec03
 
87a12c6
 
 
 
 
 
 
 
 
 
 
9a9ec03
87a12c6
 
 
 
3297dba
87a12c6
 
9a9ec03
87a12c6
 
 
 
3297dba
 
87a12c6
3297dba
87a12c6
 
9a9ec03
87a12c6
9a9ec03
 
 
 
87a12c6
 
 
3297dba
 
 
 
 
 
87a12c6
 
 
 
 
 
 
 
 
 
 
3297dba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87a12c6
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
import os
import time
import importlib
from fastapi import FastAPI, HTTPException, Depends, Body
from typing import Optional
from pydantic import ValidationError

from app.models.huggingface_service import HuggingFaceTextGenerationService
from fastapi.middleware.cors import CORSMiddleware
from app.schemas.schemas import EnhancedDescriptionResponse
from app.auth.placeholder_auth import get_authenticated_user
# MCP imports removed

app = FastAPI(
    title="Modular Car Description Enhancer",
    description="AI-powered service for enhancing descriptions for multiple domains with Auth0 JWT authentication",
    version="2.0.0"
)

# CORS configuration
app.add_middleware(
    CORSMiddleware,
    allow_origins=[
        "http://localhost:5173",
        "http://localhost:5174",
        os.getenv("FRONTEND_URL", "http://localhost:5173")
    ],
    allow_credentials=True,
    allow_methods=["POST", "GET"],
    allow_headers=["*"],
)

# Global service initialization
MODEL_PATH_IN_CONTAINER = "/app/pretrain_model"
hf_service = HuggingFaceTextGenerationService(
    model_name_or_path=MODEL_PATH_IN_CONTAINER,
    device="cpu"
)

@app.on_event("startup")
async def startup_event():
    print("Starting up and initializing HuggingFace service...")
    try:
        await hf_service.initialize()
        print(f"HuggingFace service initialized successfully from {MODEL_PATH_IN_CONTAINER}.")
    except Exception as e:
        print(f"An unexpected error occurred during HuggingFace service initialization: {e}")
        raise

# --- Helper function to load domain logic ---
def get_domain_config(domain: str):
    try:
        module = importlib.import_module(f"app.domains.{domain}.config")
        return module.domain_config
    except (ImportError, AttributeError):
        raise HTTPException(status_code=404, detail=f"Domain '{domain}' not found or not configured correctly.")

# --- API Endpoints ---

@app.get("/")
async def read_root():
    return {"message": "Welcome to the Modular Description Enhancer API! Go to /docs for documentation."}

@app.get("/health")
async def health_check():
    return {
        "status": "ok",
        "model_initialized": hf_service.pipeline is not None,
    }

@app.post("/enhance-description", response_model=EnhancedDescriptionResponse)
async def enhance_description(
    domain: str = Body(..., embed=True),
    data: dict = Body(..., embed=True),
    user: Optional[dict] = Depends(get_authenticated_user)
):
    """
    Generate an enhanced description for a given domain and data.
    - **domain**: The name of the domain (e.g., 'cars').
    - **data**: A dictionary with the data for the description.
    """
    start_time = time.time()
    
    # --- 1. Load Domain Configuration ---
    domain_config = get_domain_config(domain)
    DomainSchema = domain_config["schema"]
    create_prompt = domain_config["create_prompt"]
    # mcp_rules removed

    # --- 2. Validate Input Data ---
    try:
        validated_data = DomainSchema(**data)
    except ValidationError as e:
        raise HTTPException(status_code=422, detail=f"Invalid data for domain '{domain}': {e}")

    # --- 3. Prompt Construction ---
    chat_messages = create_prompt(validated_data)

    # --- 4. Text Generation ---
    try:
        generated_description = await hf_service.generate_text(
            chat_template_messages=chat_messages,
            max_new_tokens=150,
            temperature=0.75,
            top_p=0.9,
        )
    except Exception as e:
        print(f"Unexpected error during text generation: {e}")
        raise HTTPException(status_code=500, detail=f"An unexpected error occurred during text generation: {str(e)}")

    # --- 5. MCP Guardrails & Post-processing removed ---
    # if not guardrails.check_compliance(generated_description, mcp_rules.get("guardrails", {})):
    #     raise HTTPException(status_code=400, detail="Generated description failed compliance checks.")

    # final_description = postprocessor.format_output(generated_description, mcp_rules.get("postprocessor", {}))
    final_description = generated_description # No post-processing here

    generation_time = time.time() - start_time
    user_email = user['email'] if user else "anonymous"

    return EnhancedDescriptionResponse(
        description=final_description,
        model_used="speakleash/Bielik-1.5B-v3.0-Instruct",
        generation_time=round(generation_time, 2),
        user_email=user_email
    )

@app.post("/generate")
async def generate_text_only(
    chat_template_messages: str = Body(..., embed=True),
    max_new_tokens: int = 150,
    temperature: float = 0.75,
    top_p: float = 0.9
):
    """
    Generates raw text based on provided chat template messages.
    This endpoint is intended for internal use by the MCP service.
    """
    try:
        generated_text = await hf_service.generate_text(
            chat_template_messages=chat_template_messages,
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            top_p=top_p,
        )
        return {"generated_text": generated_text}
    except Exception as e:
        print(f"Unexpected error during raw text generation: {e}")
        raise HTTPException(status_code=500, detail=f"An unexpected error occurred during text generation: {str(e)}")


@app.get("/user/me")
async def get_user_info(user: dict = Depends(get_authenticated_user)):
    """Get current authenticated user information"""
    if not user:
        raise HTTPException(status_code=401, detail="Not authenticated")
    return {
        "user_id": user['user_id'],
        "email": user['email'],
        "name": user.get('name', 'Unknown')
    }