Update app.py

app.py

@@ -77,20 +77,44 @@ def extract_text(file):
 
     return text
 
-def summarise(text):
+def qa(text, question):
 
     chunks = [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]
 
     text_embeddings = np.array([get_text_embedding(chunk) for chunk in chunks])
+
+    d = text_embeddings.shape[1]
+    index = faiss.IndexFlatL2(d)
+    index.add(text_embeddings)
+
+    question_embeddings = np.array([get_text_embedding(question)])
+
+    D, I = index.search(question_embeddings, k=2) # distance, index
+    retrieved_chunk = [chunks[i] for i in I.tolist()[0]]
+
+    prompt = f"""
+        Context information is below.
+        ---------------------
+        {retrieved_chunk}
+        ---------------------
+        Given the context information and not prior knowledge, answer the query.
+        Query: {question}
+        Answer:
+        """
     
-    return len(text_embeddings)
+    return prompt
 
 with gr.Blocks() as demo:
     file_input = gr.File(label="Upload a PDF file")
+    question_input = gr.Textbox(label="Question")
     text_output = gr.Textbox(label="Extracted Text")
-    summary_output = gr.Textbox(label="Summary")
+    
+    promp_output = gr.Textbox(label="prompt")
+
+    
     file_input.upload(extract_text, inputs=file_input, outputs=text_output)
-    text_output.change(summarise,text_output,summary_output)
+    text_output.change(qa,[text_output,question_input],promp_output)
+    
     
 
 if __name__ == "__main__":