Update app.py

app.py

@@ -60,6 +60,25 @@ def get_text_embedding(text):
 
     return embeddings.embed_query(text)
 
+reader = PdfReader("/resource/NGAP 01042024.pdf")
+
+text = []
+for p in np.arange(0, len(reader.pages), 1):
+    page = reader.pages[int(p)]
+
+    # extracting text from page
+    text.append(page.extract_text())
+
+    text = ' '.join(text)
+
+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)
+
 
 def extract_text(file):
 
@@ -77,15 +96,9 @@ def extract_text(file):
 
     return text
 
-def qa(text, question):
-
-    chunks = [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]
+def qa(question):
 
-    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)])
 
@@ -104,16 +117,18 @@ def qa(text, question):
     
     return prompt
 
+def test_func(text):
+    return len(text_embeddings)
+
 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")
     
+    question_input = gr.Textbox(label="Question")
+    qa_button = gr.Button("Click to qa")
+        
     promp_output = gr.Textbox(label="prompt")
 
     
-    file_input.upload(extract_text, inputs=file_input, outputs=text_output)
-    text_output.change(qa,[text_output,question_input],promp_output)
+    qa_button.click(test_func, question_input, promp_output)