Update app.py

app.py

@@ -11,6 +11,7 @@ from langchain.schema import Document
 from sentence_transformers import SentenceTransformer,util
 from streamlit_image_select import image_select
 import os
+import fitz
 import PyPDF2
 import requests 
 from streamlit_navigation_bar import st_navbar
@@ -32,7 +33,7 @@ def consume_llm_api(prompt):
     """
     Sends a prompt to the LLM API and processes the streamed response.
     """
-    url = "https://hot-eyes-shop.loca.lt/api/llm-response"
+    url = "https://wise-eagles-send.loca.lt/api/llm-response"
     headers = {"Content-Type": "application/json"}
     payload = {"prompt": prompt}
 
@@ -477,7 +478,39 @@ with column1:
     negative_prompt="the black masked area"
 
     # run=st.button("run_experiment")
+if bg_doc:
+    if len(dictionary['every_prompt_with_val'])==0:
+        query_embedding = model.encode(["something"])
+    else:
+
+        query_embedding = model.encode([dictionary['every_prompt_with_val'][-1][0]])
+    retrieved_chunks = max([(util.cos_sim(match[0],query_embedding),match[-1])for  match in vector_store])[-1]
 
+
+
+    with implementation:
+        
+            text_lookup=retrieved_chunks
+            pages=[]
+            with fitz.open("temp.pdf") as doc:
+                page_number = st.sidebar.number_input(
+    "Page number", min_value=1, max_value=doc.page_count, value=1, step=1
+                
+                    
+    )               
+                for page_no in range(doc.page_count):
+                    pages.append(doc.load_page(page_no - 1))
+                
+                # areas = pages[page_number-1].search_for(text_lookup)
+                with st.container(height=int(screen_height//1.8)):
+                    for pg_no in pages[::-1]:
+                        areas = pg_no.search_for(text_lookup)
+                        for area in areas:
+                            pg_no.add_rect_annot(area)
+
+                        pix = pg_no.get_pixmap(dpi=100).tobytes()
+                        st.image(pix,use_column_width=True)
+                        
 if bg_doc and prompt:
     query_embedding = model.encode([prompt])
     retrieved_chunks = max([(util.cos_sim(match[0],query_embedding),match[-1])for  match in vector_store])[-1]