Spaces:
Sleeping
Sleeping
File size: 4,930 Bytes
3177683 1bc8c61 3177683 1bc8c61 3177683 fc90017 3177683 845b7b0 3177683 845b7b0 3177683 845b7b0 e453bf9 845b7b0 3177683 845b7b0 3177683 1bc8c61 3177683 d60f5f6 fc90017 3177683 1bc8c61 3177683 1bc8c61 3177683 2ec7684 | 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 | """
Text Feature Extraction — Hugging Face Inference Endpoint Handler
Extracts all 9 text features from conversation transcript:
t0_explicit_free, t1_explicit_busy, t2_avg_resp_len, t3_short_ratio,
t4_cognitive_load, t5_time_pressure, t6_deflection, t7_sentiment,
t8_coherence, t9_latency
Derived from: src/text_features.py
"""
# ──────────────────────────────────────────────────────────────────────── #
# Imports from standardized modules
# ──────────────────────────────────────────────────────────────────────── #
try:
from text_features import TextFeatureExtractor
except ImportError:
import sys
sys.path.append('.')
from text_features import TextFeatureExtractor
# Initialize global extractor
print("[INFO] Initializing Global TextFeatureExtractor...")
# Preload models to avoid first-request latency in the Space runtime.
extractor = TextFeatureExtractor(use_intent_model=True, preload=True)
# ──────────────────────────────────────────────────────────────────────── #
# FastAPI handler for deployment
# ──────────────────────────────────────────────────────────────────────── #
from fastapi import FastAPI, Request
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse
from pydantic import BaseModel
from typing import Optional, List, Dict
import traceback
import numpy as np
# ──────────────────────────────────────────────────────────────────────── #
# Constants & Defaults
# ──────────────────────────────────────────────────────────────────────── #
DEFAULT_TEXT_FEATURES = {
"t0_explicit_free": 0.0, "t1_explicit_busy": 0.0,
"t2_avg_resp_len": 0.0, "t3_short_ratio": 0.0,
"t4_cognitive_load": 0.0, "t5_time_pressure": 0.0,
"t6_deflection": 0.0, "t7_sentiment": 0.0,
"t8_coherence": 0.5, "t9_latency": 0.0,
}
app = FastAPI(title="Text Feature Extraction API", version="1.0.0")
app.add_middleware(
CORSMiddleware,
allow_origins=["*"], allow_credentials=True,
allow_methods=["*"], allow_headers=["*"],
)
@app.exception_handler(Exception)
async def global_exception_handler(request: Request, exc: Exception):
print(f"[GLOBAL ERROR] {request.url}: {exc}")
traceback.print_exc()
return JSONResponse(
status_code=200,
content={**DEFAULT_TEXT_FEATURES, "_error": str(exc), "_handler": "global"},
)
class TextRequest(BaseModel):
transcript: str = ""
# Optional list of extra utterances if available
utterances: List[str] = []
question: str = ""
events: Optional[List[Dict]] = None
@app.get("/")
async def root():
return {
"service": "Text Feature Extraction API",
"version": "1.0.0",
"endpoints": ["/health", "/extract-text-features"],
}
@app.get("/health")
async def health():
return {
"status": "healthy",
"intent_model_loaded": extractor.use_intent_model,
"models_preloaded": True,
}
@app.post("/extract-text-features")
async def extract_text_features(data: TextRequest):
"""Extract all 9 text features from transcript."""
# Prepare inputs for TextFeatureExtractor.extract_all
# It expects: transcript_list, full_transcript, question, events
transcript_list = data.utterances
if not transcript_list and data.transcript:
transcript_list = [data.transcript]
features = extractor.extract_all(
transcript_list=transcript_list,
full_transcript=data.transcript,
question=data.question,
events=data.events,
)
# Sanitize inputs to ensure floats
sanitized = {}
for k, v in features.items():
if isinstance(v, float):
sanitized[k] = 0.0 if np.isnan(v) or np.isinf(v) else v
else:
sanitized[k] = v
return sanitized
if __name__ == "__main__":
import uvicorn
import os
port = int(os.environ.get("PORT", 7860))
uvicorn.run(app, host="0.0.0.0", port=port)
|