Update app.py

app.py

@@ -1,64 +1,40 @@
 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)",
-        ),
-    ],
-)
-
-
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import TextLoader
+from langchain_community.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.prompts import PromptTemplate
+from transformers import AutoModelForSeq2SeqLM, pipeline, AutoTokenizer
+
+# Load data
+loader = TextLoader("about_me.txt")
+docs = loader.load()
+
+# Split documents
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50)
+split_docs = text_splitter.split_documents(docs)
+
+# Embeddings and DB
+embedding_model = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+db = FAISS.from_documents(split_docs, embedding_model)
+
+# Load model
+model_id = "google/flan-t5-large"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer, max_length=512, truncation=True)
+llm = HuggingFacePipeline(pipeline=pipe)
+
+# RetrievalQA chain
+custom_prompt = PromptTemplate(template="Context: {context}\nQ: {question}\nA:", input_variables=["context", "question"])
+qa_chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=db.as_retriever(search_kwargs={"k": 2}), chain_type_kwargs={"prompt": custom_prompt})
+
+def ask_bot_alternative(question):
+    return qa_chain.invoke({"query": question})["result"]
+
+# Gradio interface
+iface = gr.Interface(fn=ask_bot_alternative, inputs="text", outputs="text", title="Portfolio Chatbot")
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()