Update app.py

app.py

@@ -6,7 +6,6 @@ from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_core.prompts import PromptTemplate
-from langchain_core.output_parsers import StrOutputParser
 from langchain_community.llms import HuggingFacePipeline
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
 
@@ -35,12 +34,9 @@ def process_pdf(pdf_files):
     splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
     texts = splitter.split_text(text)
 
-    # Convert to LangChain documents
-    docs = [doc for doc in texts]
-
     # Embeddings & vector store
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    db = FAISS.from_texts(docs, embeddings)
+    db = FAISS.from_texts(texts, embeddings)
 
     return db
 
@@ -64,20 +60,24 @@ def ask_question(pdf_files, question):
     response = llm.invoke(final_prompt)
     return response
 
+
 # ---------- Gradio UI ----------
 with gr.Blocks() as demo:
     gr.Markdown("## 📚 Multiple PDF Chatbot")
 
     with gr.Row():
-    pdf_input = gr.File(
-    file_types=[".pdf"],
-    type="file",
-    label="Upload PDFs",
-    file_types="file",
-    file_types_multiple=True
-)
-estion_input = gr.Textbox(label="Ask a Question")
-    output = gr.Textbox(label="Answer")
+        pdf_input = gr.File(
+            file_types=[".pdf"],
+            type="file",
+            label="Upload PDFs",
+            file_types_multiple=True
+        )
+
+    with gr.Row():
+        question_input = gr.Textbox(label="Ask a Question")
+
+    with gr.Row():
+        output = gr.Textbox(label="Answer")
 
     submit = gr.Button("Submit")
     submit.click(fn=ask_question, inputs=[pdf_input, question_input], outputs=output)