Updated chatbot app

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,33 +1,160 @@
 import streamlit as st
 import openai
 import os
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from openai import OpenAI
+import base64
+import requests
 
-# Set OpenAI API key
-openai.api_key = os.getenv("OPENAI_API_KEY")
+# Initialize clients
+client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+elevenlabs_key = os.getenv("ELEVENLABS_API_KEY")
+tavily_key = os.getenv("TAVILY_API_KEY")
 
-if not openai.api_key:
-    st.error("⚠️ OpenAI API key is missing! Please add it in Hugging Face secrets.")
-    st.stop()
+# Initialize session state
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+if "document_vectors" not in st.session_state:
+    st.session_state.document_vectors = None
 
 # App title
-st.title("🤖 Interactive Chatbot Assistant")
+st.title("🤖 SuperBot Pro")
+st.caption("An AI Assistant with Superpowers")
 
-# User input
-user_input = st.text_input("You:", "")
+# ===== Sidebar Settings =====
+with st.sidebar:
+    st.header("⚙️ Settings")
+    
+    # Personality and Mode
+    tone = st.selectbox("Personality:", ["Assistant", "Sarcastic", "Academic", "Shakespeare"])
+    mode = st.radio("Mode:", ["Chat", "Document Q&A", "Web Researcher"])
+    
+    # Advanced Features
+    web_access = st.checkbox("Enable Web Search", value=False)
+    voice_enabled = st.checkbox("Enable Voice Response", value=False)
+    
+    # File Uploaders
+    uploaded_file = st.file_uploader("Upload Document (PDF)", type=["pdf"])
+    uploaded_image = st.file_uploader("Upload Image", type=["jpg", "png"])
 
-if st.button("Send"):
-    if user_input:
+# ===== Document Processing =====
+if uploaded_file and mode == "Document Q&A":
+    with st.spinner("Processing document..."):
+        # Save and load PDF
+        with open(uploaded_file.name, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        loader = PyPDFLoader(uploaded_file.name)
+        pages = loader.load()
+        
+        # Split and embed
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        texts = text_splitter.split_documents(pages)
+        embeddings = OpenAIEmbeddings()
+        st.session_state.document_vectors = FAISS.from_documents(texts, embeddings)
+
+# ===== Chat Interface =====
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+        if "audio" in message:
+            st.audio(message["audio"], format="audio/mp3")
+
+# Input area
+if prompt := st.chat_input("Ask me anything..."):
+    # Add user message to history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    
+    with st.chat_message("user"):
+        st.markdown(prompt)
+    
+    # ===== Generate Response =====
+    with st.chat_message("assistant"):
+        response_placeholder = st.empty()
+        full_response = ""
+        
         try:
-            response = openai.chat.completions.create(
+            # ===== Content Moderation =====
+            moderation = client.moderations.create(input=prompt)
+            if moderation.results[0].flagged:
+                st.error("Content violates policies")
+                st.stop()
+            
+            # ===== System Prompt Engineering =====
+            system_prompt = f"You are a {tone} assistant. Respond concisely."
+            
+            if mode == "Document Q&A" and st.session_state.document_vectors:
+                docs = st.session_state.document_vectors.similarity_search(prompt, k=3)
+                system_prompt += f"\nDocument context: {[doc.page_content for doc in docs]}"
+            
+            if web_access and tavily_key:
+                search_response = requests.post(
+                    "https://api.tavily.com/search",
+                    json={"query": prompt, "api_key": tavily_key}
+                )
+                web_results = search_response.json()["results"]
+                system_prompt += f"\nWeb results: {web_results[:2]}"
+            
+            # ===== Generate with OpenAI =====
+            response = client.chat.completions.create(
                 model="gpt-4",
-                messages=[{"role": "user", "content": user_input}]
+                messages=[
+                    {"role": "system", "content": system_prompt},
+                    *st.session_state.messages
+                ],
+                stream=True
             )
-            st.text_area("Chatbot:", response.choices[0].message.content, height=200)
+            
+            # Stream response
+            for chunk in response:
+                if chunk.choices[0].delta.content:
+                    full_response += chunk.choices[0].delta.content
+                    response_placeholder.markdown(full_response + "▌")
+            
+            response_placeholder.markdown(full_response)
+            
+            # ===== Voice Output =====
+            if voice_enabled and elevenlabs_key:
+                audio_response = requests.post(
+                    "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM",
+                    headers={"xi-api-key": elevenlabs_key},
+                    json={"text": full_response}
+                )
+                st.audio(audio_response.content, format="audio/mp3")
+            
+            # Add to history
+            st.session_state.messages.append({
+                "role": "assistant", 
+                "content": full_response,
+                "audio": audio_response.content if voice_enabled else None
+            })
+            
         except Exception as e:
-            st.error(f"Error: {e}")
-    else:
-        st.warning("Please enter a message to chat.")
+            st.error(f"Error: {str(e)}")
 
-st.sidebar.subheader("Chatbot Settings")
-st.sidebar.write("Customize your chatbot experience!")
+# ===== Feedback Buttons =====
+col1, col2 = st.columns(2)
+with col1:
+    if st.button("👍 Good Response"):
+        st.toast("Thanks for your feedback!")
+with col2:
+    if st.button("👎 Needs Improvement"):
+        st.toast("We'll do better next time!")
 
+# ===== Image Processing =====
+if uploaded_image:
+    st.image(uploaded_image, caption="Uploaded Image")
+    with st.spinner("Analyzing image..."):
+        response = client.chat.completions.create(
+            model="gpt-4-vision-preview",
+            messages=[{
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Describe this image"},
+                    {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64.b64encode(uploaded_image.getvalue()).decode('utf-8')}"}}
+                ]
+            }]
+        )
+        st.write(response.choices[0].message.content)

requirements.txt

@@ -1,2 +1,9 @@
-streamlit
-openai
+streamlit>=1.28
+openai>=1.3
+python-dotenv>=1.0
+langchain>=0.0.340
+PyPDF2>=3.0
+faiss-cpu>=1.7
+elevenlabs>=0.2.12
+tavily-python>=0.2
+requests>=2.31