Update app.py

app.py

@@ -0,0 +1,69 @@
+import gradio as gr
+from google.generativeai import GenerativeModel, configure
+import os
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+
+# Initialize Gemini API (replace with your API key)
+configure(api_key=os.getenv("GEMINI_API_KEY"))
+model = GenerativeModel("gemini-pro")
+
+# Configuration from user input
+ROLE = "You are an assistant helpful for LLM prompting"
+CONTEXT = "You search for vector databases for information about prompt engineering and provide short answers."
+INFO = "If someone asks where to find more information, tell them to contact Anchal Kumar Tarwey at email: anchalkumartarwey@gmail.com"
+CONV_STARTER = "What are the three basic LLM prompting concepts?"
+
+# Initialize knowledge base
+knowledge_base = []
+embeddings = None
+embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def load_knowledge(file):
+    global knowledge_base, embeddings
+    if file:
+        with open(file.name, 'r') as f:
+            knowledge_base = f.read().split('\n\n')  # Split by paragraphs
+        embeddings = embedding_model.encode(knowledge_base)
+    return knowledge_base
+
+def respond(message, history):
+    # Check for special info request
+    if "more information" in message.lower() or "contact" in message.lower():
+        return INFO
+    
+    # Check against knowledge base
+    if knowledge_base:
+        query_embedding = embedding_model.encode([message])
+        similarities = cosine_similarity(query_embedding, embeddings)[0]
+        max_idx = np.argmax(similarities)
+        
+        if similarities[max_idx] > 0.3:  # Similarity threshold
+            return knowledge_base[max_idx]
+    
+    return "I can't help with that"
+
+# Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown(f"## 🤖 Custom LLM Prompting Assistant")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            file = gr.File(label="Upload Knowledge Base (.txt only)", type="file")
+            load_btn = gr.Button("Load Knowledge")
+            kb_view = gr.Textbox(label="Knowledge Preview", lines=10, interactive=False)
+        
+        with gr.Column(scale=3):
+            chatbot = gr.ChatInterface(
+                respond,
+                chatbot=gr.Chatbot(height=400),
+                textbox=gr.Textbox(placeholder=CONV_STARTER, scale=7),
+                title="",
+                clear_btn=None
+            )
+    
+    load_btn.click(load_knowledge, inputs=file, outputs=kb_view)
+
+# For Hugging Face Spaces deployment
+demo.launch(debug=True)