Update app.py

app.py

@@ -1,59 +1,30 @@
-import os
-import json
+# chatbot.py
+
 import gradio as gr
-import faiss
-import fitz  # PyMuPDF
-import numpy as np
 from huggingface_hub import InferenceClient
+import faiss
+import json
 from sentence_transformers import SentenceTransformer
 
-# Extract text from PDF
-def extract_text_from_pdf(pdf_path):
-    doc = fitz.open(pdf_path)
-    text = ""
-    for page_num in range(doc.page_count):
-        page = doc.load_page(page_num)
-        text += page.get_text()
-    return text.split("\n\n")
-
-# Build FAISS index
-def build_faiss_index(documents):
-    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
-    document_embeddings = model.encode(documents)
-
-    index = faiss.IndexFlatL2(document_embeddings.shape[1])
-    faiss.write_index(index, "apexcustoms_index.faiss")
-    model.save("sentence_transformer_model")
-
-    return index, model
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-# Ensure that text extraction and FAISS index building is done
-if not os.path.exists("apexcustoms_index.faiss") or not os.path.exists("sentence_transformer_model"):
-    documents = extract_text_from_pdf("apexcustoms.pdf")
-    with open("apexcustoms.json", "w") as f:
-        json.dump(documents, f)
-    index, model = build_faiss_index(documents)
-else:
-    index = faiss.read_index("apexcustoms_index.faiss")
-    model = SentenceTransformer('sentence_transformer_model')
-    with open("apexcustoms.json", "r") as f:
-        documents = json.load(f)
+# Load the FAISS index and the sentence transformer model
+index = faiss.read_index("apexcustoms_index.faiss")
+model = SentenceTransformer('sentence_transformer_model')
 
-# Hugging Face client
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Load the extracted text
+with open("apexcustoms.json", "r") as f:
+    documents = json.load(f)
 
 def retrieve_documents(query, k=5):
     query_embedding = model.encode([query])
     distances, indices = index.search(query_embedding, k)
     return [documents[i] for i in indices[0]]
 
-async def respond(message, history, system_message, max_tokens, temperature, top_p):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Retrieve relevant documents
     relevant_docs = retrieve_documents(message)
-
-    context = "\n\n".join(relevant_docs[:3])  # Limit context to top 3 documents
-
-    # Limit history to the last 5 exchanges to reduce payload size
-    history = history[-5:]
+    context = "\n\n".join(relevant_docs)
 
     messages = [{"role": "system", "content": system_message},
                 {"role": "user", "content": f"Context: {context}\n\n{message}"}]
@@ -66,32 +37,28 @@ async def respond(message, history, system_message, max_tokens, temperature, top
 
     messages.append({"role": "user", "content": message})
 
-    async for message in client.chat_completion(
+    response = ""
+
+    for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        if message.choices and message.choices[0].delta and message.choices[0].delta.content:
-            token = message.choices[0].delta.content
-            yield token
+        token = message.choices[0].delta.content
+        response += token
+        yield response
 
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a helpful car configuration assistant, specifically you are the assistant for Apex Customs (https://www.apexcustoms.com/). Given the user's input, provide suggestions for car models, colors, and customization options. Be creative and conversational in your responses. You should remember the user car model and tailor your answers accordingly. \n\nUser: ", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.3, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()