Create app.py

app.py

@@ -0,0 +1,132 @@
+import streamlit as st
+import re
+from langchain_groq import ChatGroq
+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 sentence_transformers import SentenceTransformer
+import bs4
+import torch
+import os
+
+# Sidebar Style with Multicolored Background
+sidebar_bg_style = """
+    <style>
+        [data-testid="stSidebar"] {
+            background: linear-gradient(135deg, #ffafbd, #ffc3a0, #2193b0, #6dd5ed);
+        }
+    </style>
+"""
+st.markdown(sidebar_bg_style, unsafe_allow_html=True)
+
+# Sidebar: Input for URL and API keys
+st.sidebar.title("Settings")
+
+# Input field for entering URL dynamically with placeholder and help text
+url_input = st.sidebar.text_input("Enter Blog Post URL", placeholder="e.g., https://example.com/blog", help="Paste the full URL of the blog post you want to retrieve data from")
+
+# Validate the URL and show a success message when correct
+if url_input:
+    if re.match(r"https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+", url_input):
+        st.sidebar.markdown('<p style="color:green; font-weight:bold;">URL is correctly entered</p>', unsafe_allow_html=True)
+    else:
+        st.sidebar.markdown('<p style="color:red; font-weight:bold;">Invalid URL, please enter a valid one</p>', unsafe_allow_html=True)
+
+# Input fields for API keys with placeholders and helper text
+api_key_1 = st.sidebar.text_input("Enter LangChain API Key", type="password", placeholder="Enter your LangChain API Key", help="Please enter a valid LangChain API key here")
+api_key_2 = st.sidebar.text_input("Enter Groq API Key", type="password", placeholder="Enter your Groq API Key", help="Please enter your Groq API key here")
+
+# Submit button for API keys with a success/warning message
+if st.sidebar.button("Submit API Keys"):
+    if api_key_1 and api_key_2:
+        os.environ["LANGCHAIN_API_KEY"] = api_key_1
+        os.environ["GROQ_API_KEY"] = api_key_2
+        st.sidebar.markdown('<p style="color:green; font-weight:bold;">Both API keys are entered</p>', unsafe_allow_html=True)
+    else:
+        st.sidebar.markdown('<p style="color:red; font-weight:bold;">Please fill in both API keys</p>', unsafe_allow_html=True)
+
+# Main Section with Multicolored Background and Chatbot Title
+main_bg_style = """
+    <style>
+        body {
+            background: linear-gradient(135deg, #ff9a9e, #fad0c4, #fbc2eb, #a18cd1);
+        }
+    </style>
+"""
+st.markdown(main_bg_style, unsafe_allow_html=True)
+
+# Title of the chatbot
+st.markdown('<h1 style="color:#4CAF50; font-weight:bold;">🤖 Chatbot with URL-based Document Retrieval</h1>', unsafe_allow_html=True)
+
+# Chat query input field with placeholder and help text
+query = st.text_input("Ask a question based on the blog post", placeholder="Type your question here...", help="Enter a question related to the content of the blog post")
+
+# Placeholder to display responses
+if 'chat_history' not in st.session_state:
+    st.session_state['chat_history'] = []
+
+# Submit button for chat
+if st.button("Submit Query"):
+    if query and url_input:
+        # Blog loading logic based on user input URL
+        loader = WebBaseLoader(
+            web_paths=(url_input,),  # Use the user-input URL
+            bs_kwargs=dict(
+                parse_only=bs4.SoupStrainer()  # Adjust based on the user's URL structure
+            ),
+        )
+        docs = loader.load()
+
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        splits = text_splitter.split_documents(docs)
+
+        # Define the embedding class
+        class SentenceTransformerEmbedding:
+            def __init__(self, model_name):
+                self.model = SentenceTransformer(model_name)
+
+            def embed_documents(self, texts):
+                embeddings = self.model.encode(texts, convert_to_tensor=True)
+                if isinstance(embeddings, torch.Tensor):
+                    return embeddings.cpu().detach().numpy().tolist()  # Convert tensor to list
+                return embeddings
+
+            def embed_query(self, query):
+                embedding = self.model.encode([query], convert_to_tensor=True)
+                if isinstance(embedding, torch.Tensor):
+                    return embedding.cpu().detach().numpy().tolist()[0]  # Convert tensor to list
+                return embedding[0]
+
+        # Initialize the embedding model
+        embedding_model = SentenceTransformerEmbedding('all-MiniLM-L6-v2')
+
+        # Initialize Chroma with the embedding class
+        vectorstore = Chroma.from_documents(documents=splits, embedding=embedding_model)
+
+        # 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
+            | ChatGroq(model="llama3-8b-8192")  # Replace `llm` with an appropriate language model
+            | StrOutputParser()
+        )
+
+        # Generate the answer using the user's query
+        result = rag_chain.invoke(query)
+
+        # Store query and response in session for chat history
+        st.session_state['chat_history'].append((query, result))
+
+# Display chat history
+for q, r in st.session_state['chat_history']:
+    st.write(f"**User:** {q}")
+    st.write(f"**Bot:** {r}")