Update app.py

app.py

@@ -1,87 +1,43 @@
-# import streamlit as st
-# from langchain.text_splitter import CharacterTextSplitter
-# from langchain_community.document_loaders import TextLoader
-# from langchain.embeddings import OpenAIEmbeddings
-# from langchain.vectorstores import Chroma
-# from langchain.chains import RetrievalQA
-# from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
-
-# def get_text():
-#     input_text = st.text_input("You: ", key="input")
-#     return input_text
-
-
-# user_input = get_text()
-# submit = st.button('Get Answer')
-
-
-# loader = TextLoader('India.txt')
-# documents =loader.load()
-
-# text_splitter = CharacterTextSplitter (chunk_size=200,
-# chunk_overlap=0)
-
-# texts= text_splitter.split_documents(documents)
-
-
-
-# embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
-# db = Chroma.from_documents(texts, embeddings)
-# db._collection.get(include=['embeddings'])
-# retriever = db.as_retriever(search_kwargs={"k": 1})
-
-# if user_input and submit:
-    
-#     docs = retriever.get_relevant_documents(user_input)
-#     st.write("Answer")
-#     document = docs[0]
-#     page_content = document.page_content
-
-#     st.write(page_content)
-# # st.text(file_content)
-
 import streamlit as st
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.document_loaders import TextLoader
+from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
-from langchain.embeddings.base import Embeddings
-import numpy as np
-
-class CharLevelEmbeddings(Embeddings):
-    def embed_documents(self, texts):
-        return [self.embed_text(text) for text in texts]
-    
-    def embed_text(self, text):
-        # Example: Simple character-level embedding by converting characters to their ASCII values.
-        # In practice, use a more sophisticated method or pretrained model.
-        return np.array([ord(char) for char in text])
-    
-    def embed_query(self, text):
-        return self.embed_text(text)
+from langchain.chains import RetrievalQA
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
 
 def get_text():
     input_text = st.text_input("You: ", key="input")
     return input_text
 
+
 user_input = get_text()
 submit = st.button('Get Answer')
 
+
 loader = TextLoader('India.txt')
-documents = loader.load()
+documents =loader.load()
+
+text_splitter = CharacterTextSplitter (chunk_size=200,
+chunk_overlap=0)
+
+texts= text_splitter.split_documents(documents)
 
-text_splitter = CharacterTextSplitter(chunk_size=200, chunk_overlap=0)
-texts = text_splitter.split_documents(documents)
 
-embeddings = CharLevelEmbeddings()
+
+embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
 db = Chroma.from_documents(texts, embeddings)
 db._collection.get(include=['embeddings'])
 retriever = db.as_retriever(search_kwargs={"k": 1})
 
 if user_input and submit:
+    
     docs = retriever.get_relevant_documents(user_input)
     st.write("Answer")
     document = docs[0]
     page_content = document.page_content
 
     st.write(page_content)
+# st.text(file_content)
+