Spaces:
Sleeping
Sleeping
File size: 3,249 Bytes
2642249 0864cdf 2642249 0864cdf 2642249 0864cdf 2642249 babe37e b817db2 babe37e b817db2 babe37e 0864cdf 2642249 0864cdf 2642249 ad7c9e5 0864cdf 2642249 0864cdf 2642249 0864cdf 2642249 0864cdf 2642249 0864cdf 2642249 0864cdf 2642249 2d626a9 0864cdf 2642249 0864cdf d073b51 2642249 d073b51 94e7992 2642249 94e7992 ec4c7d2 94e7992 ec4c7d2 94e7992 ec4c7d2 94e7992 ec4c7d2 94e7992 2642249 0864cdf b817db2 |
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 |
import json
import gradio as gr
from sentence_transformers import SentenceTransformer
import faiss
import numpy as np
from huggingface_hub import InferenceClient
# 🔹 Load JSON Data with Colorado Food Stamp Information
DATA_FILE = "colorado_foodstamps.json"
def load_json_data():
try:
with open(DATA_FILE, "r", encoding="utf-8") as f:
data = json.load(f)
# Ensure data is a dictionary, not a list
if isinstance(data, list):
data = {str(i): str(entry) for i, entry in enumerate(data)}
# Convert all values to strings
data = {key: str(value) for key, value in data.items()}
return data
except (FileNotFoundError, ValueError) as e:
return {"error": f"Data loading issue: {e}"}
data = load_json_data()
# 🔹 Initialize FAISS for Searching Relevant Answers
model = SentenceTransformer("multi-qa-mpnet-base-dot-v1") # slower with great accuracy
def create_faiss_index(data):
texts = list(data.values())
embeddings = np.array([model.encode(text) for text in texts])
index = faiss.IndexFlatL2(embeddings.shape[1])
index.add(embeddings)
return index, texts
index, texts = create_faiss_index(data)
# 🔹 Function to Search FAISS for Relevant Answers
def search_faiss(query, top_k=1):
query_embedding = model.encode(query).reshape(1, -1)
distances, indices = index.search(query_embedding, top_k)
return texts[indices[0][0]] if indices[0][0] < len(texts) else "No relevant information found."
# 🔹 Hugging Face API for Additional Responses
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
def get_huggingface_response(query):
messages = [{"role": "system", "content": "Provide accurate food stamp information for Colorado."},
{"role": "user", "content": query}]
response = ""
for message in client.chat_completion(messages, max_tokens=1024, stream=True, temperature=0.7, top_p=0.95):
response += message.choices[0].delta.content
return response
# 🔹 Main Chatbot Function
def chatbot_response(message, history):
relevant_info = search_faiss(message, top_k=1) # Retrieve 1 most relevant sections
if "No relevant information found." not in relevant_info:
user_query_with_context = f"""
You are an expert in Colorado SNAP (food stamp) policies. The user is asking:
**User Question:** {message}
### **Relevant Policy Information Retrieved (Multiple Sources)**
{relevant_info}
### **Task:**
- **Summarize all retrieved policy information** and provide a clear, concise answer.
- **Use bullet points** for clarity.
- **If a rule applies, state it explicitly.**
- **If multiple sources provide different information, clarify the distinctions.**
- **If the policy does not fully answer the question, provide general guidance and suggest relevant keywords to search.**
"""
return get_huggingface_response(user_query_with_context)
return get_huggingface_response(message)
# 🔹 Gradio Chat Interface
demo = gr.ChatInterface(chatbot_response, textbox=gr.Textbox(placeholder="Ask about Colorado food stamps..."))
demo.launch()
|