Update app.py

app.py

@@ -1,47 +1,62 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.prompts import PromptTemplate
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import CTransformers
+from langchain.chains import RetrievalQA
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+DB_FAISS_PATH = 'vectorstore/db_faiss'
 
+custom_prompt_template = """Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+Context: {context}
+Question: {question}
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""
 
-    messages.append({"role": "user", "content": message})
+def set_custom_prompt():
+    prompt = PromptTemplate(template=custom_prompt_template,
+                            input_variables=['context', 'question'])
+    return prompt
 
-    response = ""
+def retrieval_qa_chain(llm, prompt, db):
+    qa_chain = RetrievalQA.from_chain_type(llm=llm,
+                                           chain_type='stuff',
+                                           retriever=db.as_retriever(search_kwargs={'k': 2}),
+                                           return_source_documents=True,
+                                           chain_type_kwargs={'prompt': prompt}
+                                          )
+    return qa_chain
 
-    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
+def load_llm():
+    llm = CTransformers(
+        model="TheBloke/Llama-2-7B-Chat-GGML",
+        model_type="llama",
+        max_new_tokens=512,
+        temperature=0.5
+    )
+    return llm
 
-        response += token
-        yield response
+def qa_bot():
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
+                                       model_kwargs={'device': 'cpu'})
+    db = FAISS.load_local(DB_FAISS_PATH, embeddings)
+    llm = load_llm()
+    qa_prompt = set_custom_prompt()
+    qa = retrieval_qa_chain(llm, qa_prompt, db)
+    return qa
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Define a function to respond to messages using your QA model
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    qa_result = qa_bot()
+    response = qa_result({'query': message})
+    return response
+
+# Create a Gradio interface using the respond function
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +73,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()