function file

functions/gptResponse.py

@@ -0,0 +1,41 @@
+from langchain_openai import ChatOpenAI
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+openai_key = os.getenv('OPENAI_API_KEY')
+
+def get_response(user_query, chat_history, context):
+    template = """
+    You are a helpful assistant. Answer the following questions considering the background information of the conversation:
+
+    Chat History: {chat_history}
+
+    Background Information: {context}
+
+    User question: {user_question}
+    """
+
+
+    llm = ChatOpenAI(api_key=openai_key)
+    try:
+        prompt = ChatPromptTemplate.from_template(template)
+
+        llm = ChatOpenAI(api_key=openai_key)
+            
+        chain = prompt | llm | StrOutputParser()
+        
+        value = chain.stream({
+            "chat_history": chat_history,
+            "context": context,
+            "user_question": user_query,
+        })
+        if value:
+            response = " ".join([part for part in value])
+            return response
+        else:
+            return "No response received from model."
+    except Exception as e:
+        return f"Error in generating response: {str(e)}"

functions/sidebar.py

@@ -0,0 +1,8 @@
+import streamlit as st
+
+def sidebar():
+
+    st.sidebar.page_link("app.py", label="Home")
+    st.sidebar.page_link("pages/chat_rag.py", label="RAG CHAT")
+    st.sidebar.page_link("pages/test.py", label="TESTING")
+

functions/web_chain.py

@@ -0,0 +1,48 @@
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_chroma import Chroma
+from langchain_openai import OpenAIEmbeddings
+from PyPDF2 import PdfReader
+
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+def loadUrlData(url):
+    loader = WebBaseLoader(url)
+    loader.requests_kwargs = {'verify':False}
+    html = loader.load()
+    return html
+
+def splitDoc(data):
+    text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=1000, chunk_overlap=200, add_start_index=True)
+    return text_splitter.split_documents(data)
+
+def splitText(data):
+    text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=400,
+    chunk_overlap=50,
+    length_function=len,
+    is_separator_regex=False,
+)
+    return text_splitter.split_text(data)
+
+def vectorize(data, type):
+    if type == "document":
+        docs = splitDoc(data)
+        return Chroma.from_documents(documents=docs, embedding=OpenAIEmbeddings())
+    elif type == "text":
+        texts = splitText(data)
+        return Chroma.from_texts(texts=texts, embedding=OpenAIEmbeddings())
+
+
+
+
+
+
+