Update app.py

app.py

@@ -4,14 +4,17 @@ from pdfminer.high_level import extract_text
 from sentence_transformers import SentenceTransformer
 import faiss
 from ctransformers import AutoModelForCausalLM
-from transformers import AutoTokenizer
 
-# Embeddings
+# Embeddings Model
 embedder = SentenceTransformer("all-MiniLM-L6-v2")
 
-# Load model
-llm = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-GGUF", model_type="mistral")
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+# FREE, non-gated GGUF model
+llm = AutoModelForCausalLM.from_pretrained(
+    "TheBloke/OpenHermes-2.5-Mistral-7B-GGUF",
+    model_file="openhermes-2.5-mistral-7b.Q4_K_M.gguf",
+    model_type="mistral",
+    gpu_layers=0
+)
 
 doc_chunks, index = [], None
 
@@ -64,11 +67,12 @@ def chat_with_pdf(message):
     prompt = build_prompt(message, chunks)
     return llm_answer(prompt)
 
+# Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("## Chat with your PDF (No Langchain!)")
+    gr.Markdown("## 🧠 Chat with your PDF (Open Source, No Login!)")
     file_input = gr.File(label="Upload PDF")
     upload_btn = gr.Button("Process PDF")
-    chatbot = gr.ChatInterface(fn=chat_with_pdf, textbox=gr.Textbox(placeholder="Ask something...", lines=2))
+    chatbot = gr.ChatInterface(fn=chat_with_pdf, textbox=gr.Textbox(placeholder="Ask something from your PDF..."))
 
     upload_btn.click(fn=process_pdf, inputs=[file_input], outputs=[chatbot.textbox])