Update app.py

app.py

@@ -1,49 +1,82 @@
 import os
 from embedchain import App
 import streamlit as st
-import ollama
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.document_loaders import WebBaseLoader
-from langchain_community.vectorstores import Chroma
-from langchain_community.embeddings import OllamaEmbeddings
-
-
-#with st.sidebar:
-    #huggingface_access_token = st.text_input("Hugging face Token", key="chatbot_api_key", type="password")
-    #"[Get Hugging Face Access Token](https://huggingface.co/settings/tokens)"
-    #"[View the source code](https://github.com/embedchain/examples/mistral-streamlit)"
-
-st.title("Chat with webpage")
-st.caption("This app allows you to chat with a webpage using local llama3 and RAG")
-#webpage_url = st.text_input("Enter web page URL", type = "default")
-webpage_url = "https://en.wikipedia.org/wiki/Indian_Premier_League"
-if webpage_url:
-    loader = WebBaseLoader(webpage_url)
-    docs = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size = 500, chunk_overlap = 10)
-    splits = text_splitter.split_documents(docs)
-    
-    embeddings = OllamaEmbeddings(base_url='http://localhost:11434',model="llama2")
-    vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
-
-    def ollama_llm(question, context):
-        formatted_prompt = f"Question: {question}\n\nContext: {context}"
-        response = ollama.chat(model = "llama3", messages=[{'role':'user','content': formatted_prompt}])
-        return response['message']['content']
 
-    retriever = vectorstore.as_retriever()
-    def combine_docs(docs):
-        return "\n\n".join(doc.page_content for doc in docs)
+with st.sidebar:
+    huggingface_access_token = st.text_input("Hugging face Token", key="chatbot_api_key", type="password")
+    "[Get Hugging Face Access Token](https://huggingface.co/settings/tokens)"
+    "[View the source code](https://github.com/embedchain/examples/mistral-streamlit)"
     
-    def rag_chain(question):
-        retrieved_docs = retriever.invoke(question)
-        formatted_context = combine_docs(retrieved_docs)
-        return ollama_llm(question, formatted_context)
     
-    st.success(f"Loaded {webpage_url} successfully")
+config = {
+  'llm': {
+    'provider': 'huggingface',
+    'config': {
+      'model': 'mistralai/Mistral-7B-Instruct-v0.2',
+      'top_p': 0.5
+    }
+  },
+  'embedder': {
+    'provider': 'huggingface',
+    'config': {
+      'model': 'sentence-transformers/all-mpnet-base-v2'
+    }
+  }
+}
+
+
+st.title("💬 Chatbot")
+st.caption("🚀 An Embedchain app powered by Mistral!")
+if "messages" not in st.session_state:
+    st.session_state.messages = [
+        {
+            "role": "assistant",
+            "content": """
+        Hi! I'm a chatbot. I can answer questions and learn new things!\n
+        Ask me anything and if you want me to learn something do `/add <source>`.\n
+        I can learn mostly everything. :)
+        """,
+        }
+    ]
+
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+if prompt := st.chat_input("Ask me anything!"):
+    if not st.session_state.chatbot_api_key:
+        st.error("Please enter your Hugging Face Access Token")
+        st.stop()
+
+    os.environ["HUGGINGFACE_ACCESS_TOKEN"] = st.session_state.chatbot_api_key
+    app = App.from_config(config = config)
+    app.add("https://en.wikipedia.org/wiki/Indian_Premier_League")
+
+    if prompt.startswith("/add"):
+        with st.chat_message("user"):
+            st.markdown(prompt)
+            st.session_state.messages.append({"role": "user", "content": prompt})
+        prompt = prompt.replace("/add", "").strip()
+        with st.chat_message("assistant"):
+            message_placeholder = st.empty()
+            message_placeholder.markdown("Adding to knowledge base...")
+            app.add(prompt)
+            message_placeholder.markdown(f"Added {prompt} to knowledge base!")
+            st.session_state.messages.append({"role": "assistant", "content": f"Added {prompt} to knowledge base!"})
+            st.stop()
+
+    with st.chat_message("user"):
+        st.markdown(prompt)
+        st.session_state.messages.append({"role": "user", "content": prompt})
+
+    with st.chat_message("assistant"):
+        msg_placeholder = st.empty()
+        msg_placeholder.markdown("Thinking...")
+        full_response = ""
 
-    prompt = st.text_input("Ask any question about the webpage")
+        for response in app.chat(prompt):
+            msg_placeholder.empty()
+            full_response += response
 
-    if prompt:
-        result = rag_chain(prompt)
-        st.write(result)
+        msg_placeholder.markdown(full_response)
+        st.session_state.messages.append({"role": "assistant", "content": full_response})