Update app.py

app.py

@@ -6,7 +6,7 @@ from sentence_transformers import SentenceTransformer
 import faiss
 import numpy as np
 import pickle
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_community.llms import HuggingFaceEndpoint  # Might need update
 from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
 import gradio as gr
@@ -23,7 +23,7 @@ if not api_token:
     raise ValueError("HUGGINGFACEHUB_API_TOKEN environment variable is not set")
 print(f"API Token: {api_token[:5]}...")
 
-# Initialize the HuggingFace LLM
+# Initialize the HuggingFace LLM (Optional, comment out if not used)
 llm = HuggingFaceEndpoint(
     endpoint_url="https://api-inference.huggingface.co/models/gpt2",
     model_kwargs={"api_key": api_token}
@@ -61,8 +61,23 @@ def extract_text_from_docx(docx_path):
     return text
 
 
-def process_and_query(text):
-    # Process the text and update FAISS index (similar to the previous code)
+def process_and_query(text, file=None):
+    # Check if a file is uploaded
+    if file:
+        # Get the uploaded file content
+        content = file.read()
+        if file.filename.endswith('.pdf'):
+            with open("temp.pdf", "wb") as f:
+                f.write(content)
+            text = extract_text_from_pdf("temp.pdf")
+        elif file.filename.endswith('.docx'):
+            with open("temp.docx", "wb") as f:
+                f.write(content)
+            text = extract_text_from_docx("temp.docx")
+        else:
+            return {"error": "Unsupported file format"}
+
+    # Process the text and update FAISS index (similar to previous code)
     sentences = text.split("\n")
     embeddings = embedding_model.encode(sentences)
     index.add(np.array(embeddings))
@@ -76,23 +91,18 @@ def process_and_query(text):
         if idx != -1:  # Ensure that a valid index is found
             top_documents.append(f"Document {idx}")
 
-    # Generate response using LLM (optional)
+    # Generate response using LLM (optional, commented out)
     # You can replace this with your desired LLM interaction logic
-    response = llm.run(inputs=text, max_length=100, temperature=0.7)["generated_text"]
+    # response = llm.run(inputs=text, max_length=100, temperature=0.7)["generated_text"]
 
-    return {"top_documents": top_documents, "response": response}
+    return {"top_documents": top_documents, "response": None}  # Response from LLM (optional)
 
 
 # Define the Gradio interface
 interface = gr.Interface(
     fn=process_and_query,
-    inputs="textbox",
-    outputs=["list", "text"],
-    title="Chatbot with Text Processing and Retrieval",
-    description="Upload a document (PDF or Word) or enter text to process. The chatbot will retrieve relevant documents and generate a response (optional).",
-)
+    inputs={"text": gr.Textbox(label="Enter text or upload a file"),
+             "file": gr.FileUpload(label="Upload File (PDF or Word
 
-# Launch the Gradio interface
-interface.launch()