update app.py

app.py

@@ -1,63 +1,102 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    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 friendly Chatbot.", 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)",
-        ),
-    ],
+# import fitz  # PyMuPDF for extracting text from PDFs
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.docstore.document import Document
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+from transformers import AutoConfig, AutoTokenizer, pipeline, AutoModelForCausalLM
+import torch
+import re
+import transformers
+from torch import bfloat16
+from langchain_community.document_loaders import DirectoryLoader
+
+# Initialize embeddings and ChromaDB
+model_name = "sentence-transformers/all-mpnet-base-v2"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model_kwargs = {"device": device}
+embeddings = HuggingFaceEmbeddings(model_name=model_name, model_kwargs=model_kwargs)
+
+loader = DirectoryLoader('./example', glob="**/*.pdf", recursive=True, use_multithreading=True)
+docs = loader.load()
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+all_splits = text_splitter.split_documents(docs)
+vectordb = Chroma.from_documents(documents=all_splits, embedding=embeddings, persist_directory="example_chroma_companies")
+books_db = Chroma(persist_directory="./example_chroma_companies", embedding_function=embeddings)
+
+books_db_client = books_db.as_retriever()
+
+# Initialize the model and tokenizer
+model_name = "stabilityai/stablelm-zephyr-3b"
+
+bnb_config = transformers.BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type='nf4',
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+model_config = transformers.AutoConfig.from_pretrained(model_name, max_new_tokens=1024)
+model = transformers.AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    config=model_config,
+    quantization_config=bnb_config,
+    device_map=device,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+query_pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    return_full_text=True,
+    torch_dtype=torch.float16,
+    device_map=device,
+    temperature=0.7,
+    top_p=0.9,
+    top_k=50,
+    max_new_tokens=256
+)
+
+llm = HuggingFacePipeline(pipeline=query_pipeline)
+
+books_db_client_retriever = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=books_db_client,
+    verbose=True
 )
 
+# Function to retrieve answer using the RAG system
+def test_rag(query):
+    books_retriever = books_db_client_retriever.run(query)
+    
+    # Extract the relevant answer using regex
+    corrected_text_match = re.search(r"Helpful Answer:(.*)", books_retriever, re.DOTALL)
+    
+    if corrected_text_match:
+        corrected_text_books = corrected_text_match.group(1).strip()
+    else:
+        corrected_text_books = "No helpful answer found."
+    
+    return corrected_text_books
+
+# Define the Gradio interface
+def chat(query, history=[]):
+    answer = test_rag(query)
+    history.append((query, answer))
+    return history, history
+
+# Gradio interface
+interface = gr.Interface(
+    fn=chat,
+    inputs=[gr.Textbox(label="Enter your question"), gr.State()],
+    outputs=[gr.Chatbot(label="Chat History"), gr.State()],
+    live=True
+)
 
-if __name__ == "__main__":
-    demo.launch()
+interface.launch()