Duplicate from Rajagopal/Nand1OpenPDF

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: csrd trying
+emoji: 🏆
+colorFrom: yellow
+colorTo: gray
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: Rajagopal/Nand1OpenPDF
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,73 @@
+import os
+from langchain.chains import RetrievalQA
+from langchain.llms import AzureOpenAI
+from langchain.document_loaders import TextLoader
+from langchain.document_loaders import PyPDFLoader
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import AzureOpenAI
+from langchain.chains.question_answering import load_qa_chain
+import streamlit as st
+from PIL import Image
+import time
+
+@st.cache_data
+def findanswer(Nand_url, Nand_question):
+    if True:
+      if Nand_url:
+          index = None
+          loader1 = PyPDFLoader(Nand_url)
+          langchainembeddings = OpenAIEmbeddings(deployment="textembedding", chunk_size=1)
+
+          index = VectorstoreIndexCreator(
+                  # split the documents into chunks
+                  text_splitter=CharacterTextSplitter(chunk_size=1000, chunk_overlap=0),
+                  # select which embeddings we want to use
+                  embedding=langchainembeddings,
+                  # use Chroma as the vectorestore to index and search embeddings
+                  vectorstore_cls=Chroma
+              ).from_loaders([loader1])             
+#          st.write("indexed PDF...AI finding answer....please wait")
+      if Nand_question:
+        answer = index.query(llm=llmgpt3, question=yourquestion, chain_type="map_reduce")
+        return answer
+
+
+          
+image = Image.open('Wipro logo.png')
+st.image(image,   width=100)
+
+st.write("Learn best practices in Data Centre Sustainability")
+
+
+
+
+os.environ['OPENAI_API_TYPE'] = 'azure'
+os.environ['OPENAI_API_VERSION'] = '2023-03-15-preview'
+
+llmgpt3 = AzureOpenAI(      deployment_name="testdavanci", model_name="text-davinci-003" )
+#llmchatgpt = AzureOpenAI(     deployment_name="esujnand", model_name="gpt-35-turbo" )
+
+samplequestions = ["What is  Energy Star 4.0 Standard?", "What is RoHS Directive?", "What is Green IT?", "Benefits of greening IT?", "Holistic Approach to Green IT",
+                   "Using IT: Environmentally Sound Practices", "Designing Green Computers", "Epeat" ]
+
+
+with st.form("my_form"):
+
+   myurl = st.text_input("What is the URL?", "https://sites.pitt.edu/~dtipper/2011/GreenPaper.pdf")
+
+   yourquestion = st.selectbox(
+    'Select',  samplequestions    )    
+
+   # Every form must have a submit button.
+   submitted = st.form_submit_button("Ask question")
+   if submitted:
+      #st.write("AI is looking for the answer...It will take atleast 2 mintutes... Answers will appear below....")
+      Nandanswer = findanswer(myurl, yourquestion )
+      st.write(Nandanswer)
+
+
+

requirements.txt

@@ -0,0 +1,7 @@
+openai
+langchain
+streamlit
+PyPDF2
+tiktoken
+pypdf
+chromadb