Spaces:
Running
Running
File size: 3,752 Bytes
d825c91 |
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 |
from fastapi import APIRouter, HTTPException, Depends
from typing import List, Dict, Any
from loguru import logger
from pydantic import BaseModel
from services.ai_service import ai_service
router = APIRouter()
class ModelConfig(BaseModel):
provider: str
model: str
max_tokens: int = 1000
temperature: float = 0.7
class BenchmarkRequest(BaseModel):
prompt: str
models: List[ModelConfig]
@router.post("/generate")
async def generate_response(
prompt: str,
provider: str = "openai",
model: str = "gpt-3.5-turbo",
max_tokens: int = 1000,
temperature: float = 0.7
) -> Dict[str, Any]:
"""
Generate response using specified AI model.
Parameters:
- prompt: The input prompt
- provider: AI provider to use (openai, local, openrouter)
- model: Model to use
- max_tokens: Maximum tokens in response
- temperature: Response temperature
"""
try:
response = await ai_service.generate_response(
prompt=prompt,
provider=provider,
model=model,
max_tokens=max_tokens,
temperature=temperature
)
return response
except Exception as e:
logger.error(f"Error generating response: {str(e)}")
raise HTTPException(status_code=500, detail=str(e))
@router.post("/benchmark")
async def benchmark_models(request: BenchmarkRequest) -> List[Dict[str, Any]]:
"""
Benchmark multiple models with the same prompt.
Parameters:
- request: Benchmark request containing prompt and model configurations
"""
try:
results = await ai_service.benchmark_models(
prompt=request.prompt,
models=[model.dict() for model in request.models]
)
return results
except Exception as e:
logger.error(f"Error benchmarking models: {str(e)}")
raise HTTPException(status_code=500, detail=str(e))
@router.get("/available-models")
async def get_available_models() -> Dict[str, List[str]]:
"""Get list of available models for each provider."""
return {
"openai": [
"gpt-3.5-turbo",
"gpt-4",
"gpt-4-turbo"
],
"openrouter": [
"anthropic/claude-2",
"google/palm-2",
"meta-llama/llama-2-70b"
],
"local": [
"llama-2-7b",
"llama-2-13b",
"llama-2-70b"
]
}
@router.post("/validate-response")
async def validate_response(
prompt: str,
response: str,
provider: str = "openai",
model: str = "gpt-3.5-turbo"
) -> Dict[str, Any]:
"""
Validate AI response against the prompt.
Parameters:
- prompt: Original prompt
- response: AI-generated response
- provider: AI provider used
- model: Model used
"""
try:
validation_prompt = f"""
Validate if the following response adequately addresses the prompt:
Prompt:
{prompt}
Response:
{response}
Provide:
1. Relevance score (0-1)
2. Completeness score (0-1)
3. Specific feedback
"""
validation = await ai_service.generate_response(
prompt=validation_prompt,
provider=provider,
model=model
)
return {
"status": "success",
"validation": validation["response"]
}
except Exception as e:
logger.error(f"Error validating response: {str(e)}")
raise HTTPException(status_code=500, detail=str(e)) |