Create app.py

app.py

@@ -0,0 +1,104 @@
+import gradio as gr
+import chromadb
+from chromadb.config import Settings
+from sentence_transformers import SentenceTransformer
+import json
+from pathlib import Path
+
+# Initialize ChromaDB and model
+chroma_client = chromadb.Client(Settings(
+    chroma_db_impl="duckdb+parquet",
+    persist_directory="db"
+))
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def initialize_database():
+    # Load documents from JSON file
+    docs_path = Path("documents.json")
+    with open(docs_path) as f:
+        documents = json.load(f)
+    
+    # Create or get collection
+    collection_name = "knowledge_base"
+    try:
+        collection = chroma_client.get_collection(collection_name)
+    except:
+        collection = chroma_client.create_collection(name=collection_name)
+        
+        # Add documents to collection
+        texts = [doc["content"] for doc in documents]
+        metadata = [{"title": doc["title"], "source": doc.get("source", ""), "section": doc.get("section", "")} 
+                   for doc in documents]
+        embeddings = model.encode(texts).tolist()
+        ids = [str(i) for i in range(len(texts))]
+        
+        collection.add(
+            documents=texts,
+            embeddings=embeddings,
+            metadatas=metadata,
+            ids=ids
+        )
+    
+    return collection
+
+# Initialize database
+collection = initialize_database()
+
+def search_documents(query, top_k=5):
+    if not query.strip():
+        return "Please enter a query"
+        
+    # Generate embedding for query
+    query_embedding = model.encode(query).tolist()
+    
+    # Query the collection
+    results = collection.query(
+        query_embeddings=[query_embedding],
+        n_results=top_k,
+        include=["documents", "metadatas", "distances"]
+    )
+    
+    # Format results
+    output = ""
+    for doc, metadata, distance in zip(
+        results["documents"][0],
+        results["metadatas"][0],
+        results["distances"][0]
+    ):
+        relevance = round((1 - (distance / 2)) * 100)
+        output += f"\n\n📚 {metadata['title']}\n"
+        output += f"📍 {metadata['source']} • {metadata['section']} • Relevance: {relevance}%\n"
+        output += f"───────────────────\n{doc}\n"
+        
+    return output
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=search_documents,
+    inputs=[
+        gr.Textbox(
+            lines=2,
+            placeholder="Enter your question here...",
+            label="Question"
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=10,
+            value=5,
+            step=1,
+            label="Number of results"
+        )
+    ],
+    outputs=gr.Textbox(
+        label="Search Results",
+        lines=20
+    ),
+    title="Knowledge Base Search",
+    description="Ask questions about your documents and get relevant answers.",
+    theme="default",
+    allow_flagging="never"
+)
+
+# Launch the app
+if __name__ == "__main__":
+    interface.launch()