Spaces:
Sleeping
Sleeping
File size: 2,675 Bytes
b181476 |
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 |
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import json
import logging
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
app = FastAPI()
# Define input model for validation
class CoachingInput(BaseModel):
role: str
project_id: str
milestones: str
reflection_log: str
# Load model and tokenizer
try:
model_path = "./fine_tuned_construction_llm"
model = AutoModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
logger.info("Model and tokenizer loaded successfully")
except Exception as e:
logger.error(f"Failed to load model or tokenizer: {str(e)}")
raise Exception(f"Model loading failed: {str(e)}")
@app.post("/generate_coaching")
async def generate_coaching(data: CoachingInput):
try:
# Prepare input text
input_text = (
f"Role: {data.role}, Project: {data.project_id}, "
f"Milestones: {data.milestones}, Reflection: {data.reflection_log}"
)
# Tokenize input
inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True)
# Generate output
outputs = model.generate(
inputs["input_ids"],
max_length=200,
num_return_sequences=1,
no_repeat_ngram_size=2,
do_sample=True,
temperature=0.7
)
# Decode and parse response
response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Simulate structured output (replace with actual parsing logic based on model output)
# This assumes the model outputs a JSON-like string; adjust based on fine-tuning
try:
response_json = json.loads(response_text)
except json.JSONDecodeError:
# Fallback: Construct a default response if parsing fails
response_json = {
"checklist": ["Inspect safety equipment", "Review milestone progress"],
"tips": ["Prioritize team communication", "Check weather updates"],
"quote": "Every step forward counts!"
}
logger.warning("Failed to parse model output as JSON, using default response")
return response_json
except Exception as e:
logger.error(f"Error generating coaching response: {str(e)}")
raise HTTPException(status_code=500, detail=f"Internal server error: {str(e)}")
@app.get("/health")
async def health_check():
return {"status": "healthy"} |