fixed imports

app.py

@@ -1,63 +1,70 @@
+import os
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFacePipeline
+from langchain_community.vectorstores import FAISS
+from langchain.chains import RetrievalQA
 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 spaces
+
+
+# Load TinyLlama model
+model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+
+# Create a text generation pipeline
+pipe = pipeline(
+    "text-generation",
+    model=model, 
+    tokenizer=tokenizer, 
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    repetition_penalty=1.1
 )
 
+# Wrap the pipeline in a LangChain HuggingFacePipeline
+llm = HuggingFacePipeline(pipeline=pipe)
+
+# Load embeddings
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+# Load the FAISS index
+db_FAISS = FAISS.load_local("/home/user/app/", embeddings, allow_dangerous_deserialization=True)
+
+# Create a RetrievalQA chain
+qa_chain = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=db_FAISS.as_retriever(search_kwargs={"k": 3}),
+    return_source_documents=True
+)
+
+print("fuck14")
+@spaces.GPU
+def query_documents(query):
+    result = qa_chain({"query": query})
+    answer = result['result']
+    sources = [doc.metadata for doc in result['source_documents']]
+    return answer, sources
+
+# Gradio interface
+def gradio_interface(query):
+    answer, sources = query_documents(query)
+    source_text = "\n\nSources:\n" + "\n".join([f"Source: {s.get('source', 'Unknown')}, Page: {s.get('page', 'Unknown')}" for s in sources])
+    return answer + source_text
+
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs="text",
+    outputs="text",
+    title="Document Q&A with TinyLlama",
+    description="Ask questions about your documents"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Hugging Face Spaces
+iface.launch()

requirements.txt

@@ -1 +1,8 @@
-huggingface_hub==0.22.2
+huggingface_hub
+langchain
+sentence-transformers
+langchain-community
+transformers
+torch
+faiss-gpu
+langchain_huggingface