Update app.py

app.py

@@ -1,90 +1,90 @@
-import os
-import streamlit as st
-import pickle
-import time
-from langchain.chains import RetrievalQA
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.document_loaders import UnstructuredURLLoader
-#from langchain.vectorstores import FAISS
-from langchain_community.vectorstores import FAISS
-from langchain_huggingface import HuggingFaceEndpoint
-from sentence_transformers import SentenceTransformer
-from langchain.embeddings import HuggingFaceEmbeddings
-#from langchain import HuggingFaceHub
-from langchain_community.llms import HuggingFaceHub
-from dotenv import load_dotenv
-
-
-
-with st.sidebar:
-    st.image("sriram.jpg", caption="Say cheese :)", use_column_width=True)
-
-
-load_dotenv()
-
-st.title("Sriram’s Q Reflections 🔎")
-#st.sidebar.title("Article URLs")
-
-
-# urls=[]
-# for i in range(3):
-#     url=st.sidebar.text_input(f"URL {i+1}")
-#     urls.append(url)
-# process_url_clicked=st.sidebar.button("Process URLs")
-
-
-file_path="faiss_index.pkl"
-chunk_path="chunks.pkl"
-placeholder=st.empty()
-temp=st.empty()        
-query=placeholder.text_input("Search for a Memory :")
-submit=st.button("Recall it")
-if query:
-    temp.text("Searching for memories..!")
-    if os.path.exists(file_path):
-        with open(file_path,'rb') as f:
-            index=pickle.load(f)
-        with open(chunk_path,'rb') as f:
-            chunks=pickle.load(f)    
-        model = SentenceTransformer("thenlper/gte-large")#'sentence-transformers/paraphrase-MiniLM-L12-v2')
-        temp.text("Searching for memories..!")
-        query_embedding = model.encode(query).astype('float32').reshape(1, -1)  # Encode the query
-        k = 6  # Number of nearest neighbors to retrieve
-        distances, indices = index.search(query_embedding, k)
-        retrieved_chunks = [chunks[i] for i in indices[0]]
-        # # Use a prompt to generate a response with your language model
-        # input_prompt = f"""Given the question and 
-        # context, Understand the question and give answer based on the context passed.
-        # Question: {query}\nContext: {context}\n Answer:  """
-        # response = llm.invoke(input_prompt)  # Replace with your LLM call
-        # text=response
-        if query or submit:
-            
-            st.header("Q Memories :")
-            temp.text("Memories retrieved..!")
-            cleaned_text_list = []
-            for item in retrieved_chunks:
-                item = item.strip()
-                item = item.replace(" .", ".").replace("\n", " ")
-                item = item.lstrip(". ").strip()
-                item+="."
-                cleaned_text_list.append(item)
-            temp.empty()
-            for item in cleaned_text_list:
-                st.write(item)
-            # start_index = text.find("\nHelpful Answer:")
-
-            # # Extract everything after "\nHelpful Answer:" if it exists
-            # if start_index != -1:
-            #      parsed_text =text[start_index + len("\nHelpful Answer:"):]
-            #      parsed_text = parsed_text.strip()  # Optionally strip any extra whitespace
-            #      if query or submit:
-            #         st.header("Answer :")
-            #         st.write(parsed_text)
-
-st.markdown("""
-    <hr style="margin-top: 2em;">
-    <p style="text-align: center; color: gray; font-size: small;">
-        Developed by Aditya Hariharan
-    </p>
+import os
+import streamlit as st
+import pickle
+import time
+from langchain.chains import RetrievalQA
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders import UnstructuredURLLoader
+#from langchain.vectorstores import FAISS
+from langchain_community.vectorstores import FAISS
+from langchain_huggingface import HuggingFaceEndpoint
+from sentence_transformers import SentenceTransformer
+from langchain.embeddings import HuggingFaceEmbeddings
+#from langchain import HuggingFaceHub
+from langchain_community.llms import HuggingFaceHub
+from dotenv import load_dotenv
+
+
+
+with st.sidebar:
+    st.image("sriram.jpg", caption="Say cheese :)", use_container_width=True)
+
+
+load_dotenv()
+
+st.title("Sriram’s Q Reflections 🔎")
+#st.sidebar.title("Article URLs")
+
+
+# urls=[]
+# for i in range(3):
+#     url=st.sidebar.text_input(f"URL {i+1}")
+#     urls.append(url)
+# process_url_clicked=st.sidebar.button("Process URLs")
+
+
+file_path="faiss_index.pkl"
+chunk_path="chunks.pkl"
+placeholder=st.empty()
+temp=st.empty()        
+query=placeholder.text_input("Search for a Memory :")
+submit=st.button("Recall it")
+if query:
+    temp.text("Searching for memories..!")
+    if os.path.exists(file_path):
+        with open(file_path,'rb') as f:
+            index=pickle.load(f)
+        with open(chunk_path,'rb') as f:
+            chunks=pickle.load(f)    
+        model = SentenceTransformer("thenlper/gte-large")#'sentence-transformers/paraphrase-MiniLM-L12-v2')
+        temp.text("Searching for memories..!")
+        query_embedding = model.encode(query).astype('float32').reshape(1, -1)  # Encode the query
+        k = 6  # Number of nearest neighbors to retrieve
+        distances, indices = index.search(query_embedding, k)
+        retrieved_chunks = [chunks[i] for i in indices[0]]
+        # # Use a prompt to generate a response with your language model
+        # input_prompt = f"""Given the question and 
+        # context, Understand the question and give answer based on the context passed.
+        # Question: {query}\nContext: {context}\n Answer:  """
+        # response = llm.invoke(input_prompt)  # Replace with your LLM call
+        # text=response
+        if query or submit:
+            
+            st.header("Q Memories :")
+            temp.text("Memories retrieved..!")
+            cleaned_text_list = []
+            for item in retrieved_chunks:
+                item = item.strip()
+                item = item.replace(" .", ".").replace("\n", " ")
+                item = item.lstrip(". ").strip()
+                item+="."
+                cleaned_text_list.append(item)
+            temp.empty()
+            for item in cleaned_text_list:
+                st.write(item)
+            # start_index = text.find("\nHelpful Answer:")
+
+            # # Extract everything after "\nHelpful Answer:" if it exists
+            # if start_index != -1:
+            #      parsed_text =text[start_index + len("\nHelpful Answer:"):]
+            #      parsed_text = parsed_text.strip()  # Optionally strip any extra whitespace
+            #      if query or submit:
+            #         st.header("Answer :")
+            #         st.write(parsed_text)
+
+st.markdown("""
+    <hr style="margin-top: 2em;">
+    <p style="text-align: center; color: gray; font-size: small;">
+        Developed by Aditya Hariharan
+    </p>
 """, unsafe_allow_html=True)