Create app.py

app.py

@@ -0,0 +1,111 @@
+import os
+import streamlit as st
+from crewai import Agent, Task, Crew
+from crewai_tools import LlamaIndexTool
+from langchain_groq import ChatGroq
+from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+import tempfile
+import requests
+
+# --- Streamlit UI Header ---
+st.title("Document Q&A Assistant with CrewAI")
+st.write("Upload a document, provide a link, or ask questions dynamically!")
+
+# --- Key Configuration from Secrets ---
+try:
+    GROQ_API_KEY = st.secrets["GROQ_API_KEY"]
+    TAVILY_API_KEY = st.secrets["TAVILY_API_KEY"]
+except KeyError as e:
+    st.error(f"Missing API key in secrets: {e}. Please add it to your environment.")
+    st.stop()
+
+# Check if all API keys are available
+if not GROQ_API_KEY or not TAVILY_API_KEY:
+    st.error("One or more required API keys are missing. Please check your configuration.")
+    st.stop()
+
+# Function to download PDF from URL
+def download_pdf_from_url(url, save_path):
+    response = requests.get(url)
+    if response.status_code == 200:
+        with open(save_path, 'wb') as f:
+            f.write(response.content)
+        return save_path
+    else:
+        st.error("Failed to download PDF from the provided URL.")
+        return None
+
+# --- User Inputs for File or Link ---
+document_source = st.radio("Choose input method:", ("Upload a PDF", "Provide PDF URL"))
+
+pdf_path = None
+if document_source == "Upload a PDF":
+    uploaded_file = st.file_uploader("Upload a PDF file", type=['pdf'])
+    if uploaded_file:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
+            temp_file.write(uploaded_file.getvalue())
+            pdf_path = temp_file.name
+        st.success("File uploaded successfully!")
+else:
+    pdf_url = st.text_input("Enter PDF URL")
+    if st.button("Download PDF") and pdf_url:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
+            saved_path = download_pdf_from_url(pdf_url, temp_file.name)
+            if saved_path:
+                pdf_path = saved_path
+
+# --- LLM Configuration ---
+llm = ChatGroq(groq_api_key=GROQ_API_KEY, model="groq/llama-3.3-70b-versatile")
+
+# Function to create Query Engine
+def create_query_engine(pdf_path, llm):
+    reader = SimpleDirectoryReader(input_files=[pdf_path])
+    docs = reader.load_data()
+    embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+    index = VectorStoreIndex.from_documents(docs, embed_model=embed_model)
+    return index.as_query_engine(similarity_top_k=5)
+
+# --- Streamlit Question Workflow ---
+if pdf_path:
+    st.success("PDF loaded successfully!")
+    query_engine = create_query_engine(pdf_path, llm)
+    query_tool = LlamaIndexTool.from_query_engine(
+        query_engine,
+        name="Document Query Tool",
+        description="Tool to analyze and retrieve information from the uploaded document."
+    )
+
+    # Define Agents and Tasks
+    researcher = Agent(
+        role="Document Analyst",
+        goal="Analyze documents and answer questions",
+        backstory="Expert at retrieving insights from documents.",
+        verbose=True,
+        allow_delegation=False,
+        tools=[query_tool],
+        llm=llm,
+    )
+
+    task = Task(
+        description="Answer user queries based on the uploaded document.",
+        expected_output="Clear and concise answers to user questions.",
+        agent=researcher,
+    )
+
+    crew = Crew(agents=[researcher], tasks=[task], verbose=True)
+
+    st.subheader("Ask a Question")
+    user_question = st.text_input("Enter your question")
+
+    if st.button("Get Answer"):
+        with st.spinner("Processing your request..."):
+            result = crew.kickoff(inputs={"question": user_question})
+            st.success("Here is the answer:")
+            st.write(result)
+else:
+    st.warning("Please upload a PDF or provide a valid URL to continue.")
+
+# --- Clean Up ---
+if pdf_path and os.path.exists(pdf_path):
+    os.remove(pdf_path)