Update app.py

app.py

@@ -1,30 +1,33 @@
+# chatbot.py
+
 import gradio as gr
 from huggingface_hub import InferenceClient
-from langchain_community.llms.huggingface_text_gen_inference import HuggingFaceTextGenInference
-from langchain_community.vectorstores.faiss import FAISS
-from langchain.chains import RetrievalQA
-
-# Load the vector store from the saved index files
-vector_store = FAISS.load_local("db.index", embeddings=None, allow_dangerous_deserialization=True)
+import faiss
+import json
+from sentence_transformers import SentenceTransformer
 
-# Load the model using InferenceClient
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-# Create an LLM object from the InferenceClient
-llm = HuggingFaceTextGenInference(client)
+# Load the FAISS index and the sentence transformer model
+index = faiss.read_index("apexcustoms_index.faiss")
+model = SentenceTransformer('sentence_transformer_model')
+
+# 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]]
 
-# Initialize the RetrievalQA chain
-qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=vector_store.as_retriever())
+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)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    messages = [{"role": "system", "content": system_message},
+                {"role": "user", "content": f"Context: {context}\n\n{message}"}]
 
     for val in history:
         if val[0]:
@@ -34,30 +37,28 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    result = qa({"input_documents": vector_store.texts, "question": message})
-    response = result["result"]
+    response = ""
 
-    history.append((message, response))
-    return response, history
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+        response += token
+        yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 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=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()