Create app.py

app.py

@@ -0,0 +1,136 @@
+import streamlit as st
+import os
+from llama_index.core.indices.vector_store.base import VectorStoreIndex
+from llama_index.vector_stores.qdrant import QdrantVectorStore
+from llama_index.embeddings.fastembed import FastEmbedEmbedding
+from langchain_google_genai import ChatGoogleGenerativeAI
+from llama_index.core import Settings
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext
+import qdrant_client
+from llama_index.core.indices.query.schema import QueryBundle
+from llama_index.llms.gemini import Gemini
+from llama_index.embeddings.gemini import GeminiEmbedding
+from llama_index.core.memory import ChatMemoryBuffer
+from llama_index.readers.web import FireCrawlWebReader
+from llama_index.core import SummaryIndex
+
+# Setup functions
+def embed_setup():
+    Settings.embed_model = GeminiEmbedding(api_key=os.getenv("GOOGLE_API_KEY"), model_name="models/embedding-001")
+    Settings.llm = Gemini(api_key=os.getenv("GOOGLE_API_KEY"), temperature=0.1, model_name="models/gemini-pro")
+
+def qdrant_setup():
+    client = qdrant_client.QdrantClient(
+      os.getenv('QDRANT_URL'),
+      api_key = os.getenv('QDRANT_API_KEY'),
+    )
+    return client
+
+def llm_setup():
+    llm = Gemini(api_key=os.getenv("GOOGLE_API_KEY"), temperature=0.1, model_name="models/gemini-pro")
+    return llm
+
+def query_index(index, similarity_top_k=3, streaming=True):
+    memory = ChatMemoryBuffer.from_defaults(token_limit=4000)
+    chat_engine = index.as_chat_engine(
+        chat_mode="context",
+        memory=memory,
+        system_prompt=(
+            """You are an AI assistant for developers, specializing in technical documentation. Your task is to provide accurate, concise, and helpful responses based on the given documentation context.
+                Context information is below:
+                {context_str}
+                Always answer based on the information in the context and general knowledge and be precise
+                Given this context, please respond to the following user query:
+                {query_str}
+                Your response should:
+
+                Directly address the query using information from the context
+                Include relevant code examples or direct quotes if applicable
+                Mention specific sections or pages of the documentation
+                Highlight any best practices or potential pitfalls related to the query
+
+                After your response, suggest 3 follow-up questions based on the context that the user might find helpful for deeper understanding.
+                Your response:"""
+        ),
+    )
+    return chat_engine
+
+# Document ingestion function
+def ingest_documents(url):
+    firecrawl_reader = FireCrawlWebReader(
+        api_key=os.getenv("FIRECRAWL_API_KEY"),
+        mode="crawl",
+    )
+    documents = firecrawl_reader.load_data(url=url)
+    return documents
+
+# Streamlit app
+st.title("Talk to Software Documentation")
+
+# Initialize session state
+if 'chat_engine' not in st.session_state:
+    st.session_state['chat_engine'] = None
+if 'documents' not in st.session_state:
+    st.session_state['documents'] = None
+if 'chat_history' not in st.session_state:
+    st.session_state['chat_history'] = []
+if 'last_response' not in st.session_state:
+    st.session_state['last_response'] = None
+
+
+# URL input for document ingestion
+url = st.text_input("Enter URL to crawl and ingest documents:")
+
+# Ingest documents button
+if st.button("Ingest Documents"):
+    if url:
+        with st.spinner("Crawling and ingesting documents..."):
+            st.session_state['documents'] = ingest_documents(url)
+        st.success(f"Documents ingested from {url}")
+    else:
+        st.error("Please enter a URL")
+
+# Setup button
+if st.button("Setup Query Engine"):
+    if st.session_state['documents'] is None:
+        st.error("Please ingest documents first")
+    else:
+        with st.spinner("Setting up query engine..."):
+            embed_setup()
+            client = qdrant_setup()
+            llm = llm_setup()
+            vector_store = QdrantVectorStore(client=client, collection_name=os.getenv("COLLECTION_NAME"))
+            index = VectorStoreIndex.from_documents(st.session_state['documents'], vector_store=vector_store)
+            st.session_state['chat_engine'] = query_index(index)
+        st.success("Query engine setup completed successfully!")
+
+# Query input
+query = st.text_input("Enter your query:")
+
+# Search button
+if st.button("Search"):
+    if st.session_state['chat_engine'] is None:
+        st.error("Please complete the setup first")
+    elif query:
+        with st.spinner("Searching..."):
+            response = st.session_state['chat_engine'].chat(query)
+        
+        # Add the query and response to chat history
+        st.session_state['chat_history'].append(("User", query))
+        st.session_state['chat_history'].append(("Assistant", str(response.response)))
+        
+        # Display the most recent response prominently
+        st.subheader("Assistant's Response:")
+        st.write(response.response)
+    else:
+        st.error("Please enter a query")
+
+if st.session_state['chat_history']:
+    st.subheader("Chat History")
+    for role, message in st.session_state['chat_history']:
+        st.text(f"{role}: {message}")
+
+# Clear chat history button
+if st.button("Clear Chat History"):
+    st.session_state['chat_history'] = []
+    st.success("Chat history cleared!")