Spaces:
Running
Running
File size: 4,519 Bytes
0e95308 018c04e 0e95308 018c04e 0e95308 7f8d2fb 84f2063 787aea7 ca1fb1d 2978c6a 84f2063 2978c6a 85be5b5 2978c6a ca1fb1d 2978c6a ca1fb1d 84f2063 |
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 |
import json
from sentence_transformers import SentenceTransformer, util
from groq import Groq
import datetime
import requests
from io import BytesIO
from PIL import Image, ImageDraw, ImageFont
import numpy as np
from dotenv import load_dotenv
import os
# Load environment variables
load_dotenv()
# Initialize Groq client
groq_client = Groq(api_key=os.getenv("GROQ_API_KEY"))
# Load models and dataset
similarity_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
# Configuration
HF_DATASET_REPO = "midrees2806/unmatched_queries" # Your dataset repo
HF_TOKEN = os.getenv("HF_TOKEN") # From Space secrets
# Load dataset (automatically using the path)
with open('dataset.json', 'r') as f:
dataset = json.load(f)
# Precompute embeddings
dataset_questions = [item.get("input", "").lower().strip() for item in dataset]
dataset_answers = [item.get("response", "") for item in dataset]
dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tensor=True)
# --- Unmatched Queries Handler ---
def manage_unmatched_queries(query: str):
"""Save unmatched queries to HF Dataset with error handling"""
try:
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# Load existing dataset or create new
try:
ds = load_dataset(HF_DATASET_REPO, token=HF_TOKEN)
df = ds["train"].to_pandas()
except:
df = pd.DataFrame(columns=["Query", "Timestamp", "Processed"])
# Append new query (avoid duplicates)
if query not in df["Query"].values:
new_entry = {"Query": query, "Timestamp": timestamp, "Processed": False}
df = pd.concat([df, pd.DataFrame([new_entry])], ignore_index=True)
# Push to Hub
updated_ds = Dataset.from_pandas(df)
updated_ds.push_to_hub(HF_DATASET_REPO, token=HF_TOKEN)
except Exception as e:
print(f"Failed to save query: {e}")
# --- Enhanced LLM Query ---
def query_groq_llm(prompt, model_name="llama3-70b-8192"):
try:
chat_completion = groq_client.chat.completions.create(
messages=[{
"role": "user",
"content": prompt
}],
model=model_name,
temperature=0.7,
max_tokens=500
)
return chat_completion.choices[0].message.content.strip()
except Exception as e:
print(f"Error querying Groq API: {e}")
return ""
def get_best_answer(user_input):
user_input_lower = user_input.lower().strip()
# 👉 Check if question is about fee
if any(keyword in user_input_lower for keyword in ["fee", "fees", "charges", "semester fee"]):
return (
"💰 For complete and up-to-date fee details for this program, we recommend visiting the official University of Education fee structure page.\n"
"You’ll find comprehensive information regarding tuition, admission charges, and other applicable fees there.\n"
"🔗 https://ue.edu.pk/allfeestructure.php"
)
# 🔁 Continue with normal similarity-based logic
user_embedding = similarity_model.encode(user_input_lower, convert_to_tensor=True)
similarities = util.pytorch_cos_sim(user_embedding, dataset_embeddings)[0]
best_match_idx = similarities.argmax().item()
best_score = similarities[best_match_idx].item()
if best_score >= 0.65:
original_answer = dataset_answers[best_match_idx]
prompt = f"""As an official assistant for University of Education Lahore, provide a clear response:
Question: {user_input}
Original Answer: {original_answer}
Improved Answer:"""
else:
prompt = f"""As an official assistant for University of Education Lahore, provide a helpful response:
Include relevant details about university policies.
If unsure, direct to official channels.
Question: {user_input}
Official Answer:"""
llm_response = query_groq_llm(prompt)
if llm_response:
for marker in ["Improved Answer:", "Official Answer:"]:
if marker in llm_response:
response = llm_response.split(marker)[-1].strip()
break
else:
response = llm_response
else:
response = dataset_answers[best_match_idx] if best_score >= 0.65 else """For official information:
📞 +92-42-99262231-33
✉️ [email protected]
🌐 ue.edu.pk"""
return response
|