Update app.py

app.py

@@ -1,62 +1,128 @@
-
 import streamlit as st
+from typing import Generator
+from groq import Groq
 import os
-from langchain_groq import ChatGroq
-from langchain_community.document_loaders import WebBaseLoader
-from langchain_community.embeddings import OllamaEmbeddings
-from langchain.embeddings import OllamaEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.chains.combine_documents import create_stuff_documents_chain
-from langchain_core.prompts import ChatPromptTemplate
-from langchain.chains import create_retrieval_chain
-from langchain_community.vectorstores import FAISS
 import time
+from langchain_groq import ChatGroq
+st.set_page_config(page_icon="💬", layout="wide",
+                   page_title="Groq Goes Brrrrrrrr...")
 
 from dotenv import load_dotenv
+
 load_dotenv()
 
 ## load the Groq API key
 groq_api_key=os.environ['GROQ_API_KEY']
+def icon(emoji: str):
+    """Shows an emoji as a Notion-style page icon."""
+    st.write(
+        f'<span style="font-size: 78px; line-height: 1">{emoji}</span>',
+        unsafe_allow_html=True,
+    )
+
+
+icon("🏎️")
+
+st.subheader("Groq Chat Streamlit App", divider="rainbow", anchor=False)
+
+client = Groq(api_key=groq_api_key)
+
+
+# Initialize chat history and selected model
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+if "selected_model" not in st.session_state:
+    st.session_state.selected_model = None
+
+# Define model details
+models = {
+    "gemma-7b-it": {"name": "Gemma-7b-it", "tokens": 8192, "developer": "Google"},
+    "llama2-70b-4096": {"name": "LLaMA2-70b-chat", "tokens": 4096, "developer": "Meta"},
+    "llama3-70b-8192": {"name": "LLaMA3-70b-8192", "tokens": 8192, "developer": "Meta"},
+    "llama3-8b-8192": {"name": "LLaMA3-8b-8192", "tokens": 8192, "developer": "Meta"},
+    "mixtral-8x7b-32768": {"name": "Mixtral-8x7b-Instruct-v0.1", "tokens": 32768, "developer": "Mistral"},
+}
+
+# Layout for model selection and max_tokens slider
+col1, col2 = st.columns(2)
+
+with col1:
+    model_option = st.selectbox(
+        "Choose a model:",
+        options=list(models.keys()),
+        format_func=lambda x: models[x]["name"],
+        index=4  # Default to mixtral
+    )
+
+# Detect model change and clear chat history if model has changed
+if st.session_state.selected_model != model_option:
+    st.session_state.messages = []
+    st.session_state.selected_model = model_option
+
+max_tokens_range = models[model_option]["tokens"]
+
+with col2:
+    # Adjust max_tokens slider dynamically based on the selected model
+    max_tokens = st.slider(
+        "Max Tokens:",
+        min_value=512,  # Minimum value to allow some flexibility
+        max_value=max_tokens_range,
+        # Default value or max allowed if less
+        value=min(32768, max_tokens_range),
+        step=512,
+        help=f"Adjust the maximum number of tokens (words) for the model's response. Max for selected model: {max_tokens_range}"
+    )
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    avatar = '🤖' if message["role"] == "assistant" else '👨‍💻'
+    with st.chat_message(message["role"], avatar=avatar):
+        st.markdown(message["content"])
+
+
+def generate_chat_responses(chat_completion) -> Generator[str, None, None]:
+    """Yield chat response content from the Groq API response."""
+    for chunk in chat_completion:
+        if chunk.choices[0].delta.content:
+            yield chunk.choices[0].delta.content
+
+
+if prompt := st.chat_input("Enter your prompt here..."):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    with st.chat_message("user", avatar='👨‍💻'):
+        st.markdown(prompt)
+    # Fetch response from Groq API
+    try:
+        chat_completion = client.chat.completions.create(
+            model=model_option,
+            messages=[
+                {
+                    "role": m["role"],
+                    "content": m["content"]
+                }
+                for m in st.session_state.messages
+            ],
+            max_tokens=max_tokens,
+            stream=False
+        )
+        full_response = chat_completion.choices[0].message.content
+    
+        # Use the generator function with st.write_stream
+        with st.chat_message("assistant", avatar="🤖"):
+            st.write(full_response)
+            for chunk in chat_completion:
+                if chunk.choices[0].message.content:
+                    st.text(chunk.choices[0].message.content)
+    
 
-if "vector" not in st.session_state:
-    st.session_state.embeddings=OllamaEmbeddings()
-    st.session_state.loader=WebBaseLoader("https://docs.smith.langchain.com/")
-    st.session_state.docs=st.session_state.loader.load()
-
-    st.session_state.text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
-    st.session_state.final_documents=st.session_state.text_splitter.split_documents(st.session_state.docs[:50])
-    st.session_state.vectors=FAISS.from_documents(st.session_state.final_documents,st.session_state.embeddings)
-
-st.title("ChatGroq Demo")
-llm=ChatGroq(groq_api_key=groq_api_key,
-             model_name="mixtral-8x7b-32768")
-
-prompt=ChatPromptTemplate.from_template(
-"""
-Answer the questions based on the provided context only.
-Please provide the most accurate response based on the question
-<context>
-{context}
-<context>
-Questions:{input}
-
-"""
-)
-document_chain = create_stuff_documents_chain(llm, prompt)
-retriever = st.session_state.vectors.as_retriever()
-retrieval_chain = create_retrieval_chain(retriever, document_chain)
-
-prompt=st.text_input("Input you prompt here")
-
-if prompt:
-    start=time.process_time()
-    response=retrieval_chain.invoke({"input":prompt})
-    print("Response time :",time.process_time()-start)
-    st.write(response['answer'])
-
-    # With a streamlit expander
-    with st.expander("Document Similarity Search"):
-        # Find the relevant chunks
-        for i, doc in enumerate(response["context"]):
-            st.write(doc.page_content)
-            st.write("--------------------------------")
+            # Update message content dynamically using a loop with sleep
+        for i in range(1, len(full_response) // 100 + 1):
+          st.write(full_response[i * 100 : (i + 1) * 100])
+          time.sleep(0.1) 
+        
+    except Exception as e:
+        st.error(e, icon="🚨")
+        # Set full_response to a default value or handle the error accordingly
+        full_response = None