Update app.py

app.py

@@ -1,63 +1,70 @@
+import bs4
+from langchain import hub
+from langchain_chroma import Chroma
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain_community.llms import HuggingFaceEndpoint
 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)",
-        ),
-    ],
+
+
+
+repo_id = "HuggingFaceH4/zephyr-7b-beta"
+
+llm = HuggingFaceEndpoint(
+    repo_id=repo_id, max_length=128, temperature=0.1
+)
+
+# Load, chunk and index the contents of the blog.
+loader = WebBaseLoader(
+    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
+    bs_kwargs=dict(
+        parse_only=bs4.SoupStrainer(
+            class_=("post-content", "post-title", "post-header")
+        )
+    ),
+)
+docs = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+splits = text_splitter.split_documents(docs)
+# vectorstore = Chroma.from_documents(documents=splits, embedding=HuggingFaceEmbeddings(model_name='BAAI/bge-base-en-v1.5'))
+vectorstore = FAISS.from_documents(documents=splits, embedding=HuggingFaceEmbeddings(model_name='BAAI/bge-base-en-v1.5'))
+
+# Retrieve and generate using the relevant snippets of the blog.
+retriever = vectorstore.as_retriever()
+prompt = hub.pull("rlm/rag-prompt")
+
+
+def format_docs(docs):
+    return "\n\n".join(doc.page_content for doc in docs)
+
+
+rag_chain = (
+    {"context": retriever | format_docs, "question": RunnablePassthrough()}
+    | prompt
+    | llm
+    | StrOutputParser()
 )
 
+# rag_chain.invoke("What is Task Decomposition?")
+
+# Function for the chatbot logic
+def rag_chatbot(user_input):
+    # context = document_store.retrieve(user_input)
+    # answer = retrieval_qa(context=context, question=user_input)
+    answer = rag_chain.invoke(user_input)
+    return answer
+
+iface = gr.Interface(
+    fn=rag_chatbot,
+    inputs="text",
+    outputs="text",
+    title="RAG Chatbot using Gradio and LangChain"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio interface
+iface.launch()