final baserag

app.py

@@ -1,49 +1,14 @@
-import easyocr as ocr  #OCR
 import streamlit as st  #Web App
-from PIL import Image #Image Processing
 import numpy as np #Image Processing 
-
-# To analyze the PDF layout and extract text
-from pdfminer.high_level import extract_pages, extract_text
-from pdfminer.layout import LTTextContainer, LTChar, LTRect, LTFigure
-# To extract text from tables in PDF
-import pdfplumber
-# To extract the images from the PDFs
-from PIL import Image
-from pdf2image import convert_from_path
-
-import streamlit as st
 import pandas as pd
 
-import gradio as gr
 import time
-from PyPDF2 import PdfReader
-import easyocr as ocr  #OCR
-import streamlit as st  #Web App
-from PIL import Image #Image Processing
-import numpy as np #Image Processing 
-# To read the PDF
-import PyPDF2
-# To analyze the PDF layout and extract text
-from pdfminer.high_level import extract_pages, extract_text
-from pdfminer.layout import LTTextContainer, LTChar, LTRect, LTFigure
-# To extract text from tables in PDF
-import pdfplumber
-# To extract the images from the PDFs
-from PIL import Image
-from pdf2image import convert_from_path
-# To perform OCR to extract text from images
-import pytesseract
-# To remove the additional created files
+
 import os
 import tiktoken
-import streamlit as st
-import pandas as pd
 from io import StringIO
 import time
 import json
-import openai
-
 
 import requests
 from langchain_community.document_loaders import TextLoader
@@ -62,17 +27,6 @@ from langchain.schema.output_parser import StrOutputParser
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationChain
 
-from datasets import Dataset
-
-from ragas import evaluate
-from ragas.metrics import (
-    faithfulness,
-    answer_relevancy,
-    context_recall,
-    context_precision,
-)
-
-import os
 from dotenv import load_dotenv
 from htmlTemplates import bot_template, user_template, css
 

requirements.txt

@@ -1,33 +1,51 @@
 aiohttp==3.9.3
 aiosignal==1.3.1
+altair==5.2.0
 annotated-types==0.6.0
 anyio==4.3.0
 async-timeout==4.0.3
 attrs==23.2.0
+blinker==1.7.0
+cachetools==5.3.3
 certifi==2024.2.2
 cffi==1.16.0
 charset-normalizer==3.3.2
+click==8.1.7
 cryptography==42.0.5
 dataclasses-json==0.6.4
+datasets==2.18.0
+dill==0.3.8
 distro==1.9.0
 exceptiongroup==1.2.0
 faiss-cpu==1.8.0
+filelock==3.13.1
 frozenlist==1.4.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.42
 greenlet==3.0.3
 h11==0.14.0
 httpcore==1.0.4
 httpx==0.27.0
+huggingface-hub==0.21.4
 idna==3.6
+Jinja2==3.1.3
 jsonpatch==1.33
 jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
 langchain==0.1.13
 langchain-community==0.0.29
 langchain-core==0.1.33
 langchain-openai==0.1.1
 langchain-text-splitters==0.0.1
 langsmith==0.1.31
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
 marshmallow==3.21.1
+mdurl==0.1.2
 multidict==6.0.5
+multiprocess==0.70.16
 mypy-extensions==1.0.0
 numpy==1.26.4
 openai==1.14.2
@@ -38,9 +56,14 @@ pdf2image==1.17.0
 pdfminer.six==20231228
 pdfplumber==0.11.0
 pillow==10.2.0
+protobuf==4.25.3
+pyarrow==15.0.2
+pyarrow-hotfix==0.6
 pycparser==2.21
 pydantic==2.6.4
 pydantic_core==2.16.3
+pydeck==0.8.1b0
+Pygments==2.17.2
 PyPDF2==3.0.1
 pypdfium2==4.28.0
 pytesseract==0.3.10
@@ -48,16 +71,25 @@ python-dateutil==2.9.0.post0
 python-dotenv==1.0.1
 pytz==2024.1
 PyYAML==6.0.1
+referencing==0.34.0
 regex==2023.12.25
 requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
 six==1.16.0
+smmap==5.0.1
 sniffio==1.3.1
 SQLAlchemy==2.0.28
+streamlit==1.32.2
 tenacity==8.2.3
 tiktoken==0.6.0
+toml==0.10.2
+toolz==0.12.1
+tornado==6.4
 tqdm==4.66.2
 typing-inspect==0.9.0
 typing_extensions==4.10.0
 tzdata==2024.1
 urllib3==2.2.1
+xxhash==3.4.1
 yarl==1.9.4