Upload 2 files

app.py

@@ -0,0 +1,108 @@
+# =======================================
+# 📘 RAG App – Gemini + Local Embeddings
+# =======================================
+
+#!pip install google-generativeai sentence-transformers chromadb beautifulsoup4 PyPDF2 gradio
+
+import os, textwrap, re
+import google.generativeai as genai
+from sentence_transformers import SentenceTransformer
+from bs4 import BeautifulSoup
+import requests
+import chromadb
+from PyPDF2 import PdfReader
+import gradio as gr
+
+# ======================
+# 🔹 API Key Setup
+# ======================
+genai.configure(api_key="AIzaSyDr2X5N-hHt9EqUNy7JCm58aG1FpeGVpgs")  # apni key yahan daalo
+
+MODEL = 'gemini-2.5-flash'
+embedder = SentenceTransformer('all-MiniLM-L6-v2')  # local free embedding model
+chroma_client = chromadb.Client()
+collection = chroma_client.create_collection(name="rag_store")
+
+# ======================
+# 🔹 Helper Functions
+# ======================
+
+def chunk_text(text, size=1000, overlap=100):
+    chunks = []
+    for i in range(0, len(text), size - overlap):
+        chunks.append(text[i:i+size])
+    return chunks
+
+def clean_text(text):
+    text = re.sub(r'\s+', ' ', text)
+    return text.strip()
+
+def ingest_source(source, from_url=True):
+    """
+    ✅ Web URL ya PDF se text nikaalo aur Chroma me store karo
+    """
+    if from_url:
+        html = requests.get(source).text
+        soup = BeautifulSoup(html, "html.parser")
+        text = clean_text(soup.get_text())
+    else:
+        reader = PdfReader(source)
+        text = " ".join([page.extract_text() for page in reader.pages])
+
+    chunks = chunk_text(text)
+    embeddings = embedder.encode(chunks).tolist()
+    
+    for i, emb in enumerate(embeddings):
+        collection.add(ids=[f"doc_{i}"], embeddings=[emb], documents=[chunks[i]])
+    print(f"✅ Ingested {len(chunks)} chunks into Chroma DB")
+
+def rag_query(query):
+    """
+    ✅ Query kare aur best-matched chunks Gemini ko dekar answer banaye
+    """
+    q_emb = embedder.encode([query]).tolist()
+    results = collection.query(query_embeddings=q_emb, n_results=4)
+    context = " ".join(results['documents'][0])
+
+    prompt = f"""
+    You are an AI assistant. Use the context below to answer clearly:
+    Context: {context}
+    Question: {query}
+    Answer:
+    """
+    response = genai.GenerativeModel(MODEL).generate_content(prompt)
+    return textwrap.fill(response.text, width=100)
+
+# ======================
+# 🔹 Gradio UI
+# ======================
+def web_ingest_ui(url):
+    ingest_source(url, from_url=True)
+    return f"✅ Website data added: {url}"
+
+def pdf_ingest_ui(file):
+    ingest_source(file.name, from_url=False)
+    return f"✅ PDF data added: {file.name}"
+
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="teal")) as demo:
+    gr.Markdown("## 🤖 RAG App (Gemini + Local Embeddings)")
+    
+    with gr.Tab("🌐 Ingest Website"):
+        url_in = gr.Textbox(label="Enter Website URL")
+        url_btn = gr.Button("Ingest Website")
+        url_out = gr.Textbox(label="Status")
+        url_btn.click(fn=web_ingest_ui, inputs=url_in, outputs=url_out)
+
+    with gr.Tab("📄 Ingest PDF"):
+        pdf_in = gr.File(label="Upload PDF")
+        pdf_btn = gr.Button("Ingest PDF")
+        pdf_out = gr.Textbox(label="Status")
+        pdf_btn.click(fn=pdf_ingest_ui, inputs=pdf_in, outputs=pdf_out)
+
+    with gr.Tab("💬 Ask Questions"):
+        q_in = gr.Textbox(label="Ask anything from ingested sources")
+        q_btn = gr.Button("Ask")
+        q_out = gr.Markdown(label="Answer")  # ✅ Markdown shows multi-line output
+        q_btn.click(fn=rag_query, inputs=q_in, outputs=q_out)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,9 @@
+google-generativeai
+chromadb
+sentence-transformers
+beautifulsoup4
+PyPDF2
+gradio
+
+
+!pip install google-generativeai sentence-transformers chromadb beautifulsoup4 PyPDF2 gradio