Duplicate from Rajagopal/Nand1

.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/Nand1
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,133 @@
+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
+
+image = Image.open('Wipro logo.png')
+st.image(image)
+
+st.title("Wipro Impact | CSRD | Advisor")
+
+st.header("Enable clients to prepare for CSRD.. ")
+
+
+genre = st.radio(
+    "Choose a CSRD focus area for AI question answering",
+    ('E1-Climate Change', 'E4-Biodiversity and ecosystem', 'S1-Own Workforce'), index=0)
+
+url = "https://www.efrag.org/Assets/Download?assetUrl=%2Fsites%2Fwebpublishing%2FSiteAssets%2F13%2520Draft%2520ESRS%2520S1%2520Own%2520workforce%2520November%25202022.pdf"
+
+if genre == 'E1-Climate Change':
+  url = "https://www.efrag.org/Assets/Download?assetUrl=%2Fsites%2Fwebpublishing%2FSiteAssets%2F08%2520Draft%2520ESRS%2520E1%2520Climate%2520Change%2520November%25202022.pdf"
+  samplequestions = ["What are the climate related indicators?", "List all the disclosure requirments listed in page 3?",  "Policies related to climate change mitigation and adaptation?", 
+  "What should the company disclose regarding Actions and resources in relation to climate change policies?" , "How should the  GHG emission reduction targets be reported?" , 
+  "Total energy consumption from non-renewable sources for high climate impact sectors should be disaggregated as ?", 
+  "Total energy consumption from renewable sources should be disaggregated as ?" , 
+  "What should be disclosed on GHG removals and GHG mitigation projects financed through carbon credits ?" , 
+  "Is it wise to invest on carbon credits? ",
+  "What is Climate change adaptation? ", "What are Decarbonisation levers?"   ]
+
+if genre == 'E4-Biodiversity and ecosystem':
+  url = "https://www.efrag.org/Assets/Download?assetUrl=%2Fsites%2Fwebpublishing%2FSiteAssets%2F11%2520Draft%2520ESRS%2520E4%2520Biodiversity%2520and%2520ecosystems%2520November%25202022.pdf"
+  samplequestions = ["What are the Biodiversity related indicators?", "List all the disclosure requirments listed in page 3?"]
+if genre == 'S1-Own Workforce':
+  url = "https://www.efrag.org/Assets/Download?assetUrl=%2Fsites%2Fwebpublishing%2FSiteAssets%2F13%2520Draft%2520ESRS%2520S1%2520Own%2520workforce%2520November%25202022.pdf" 
+  samplequestions = ["What are the social related indicators?", "List all the disclosure requirments listed in page 3?"]
+
+
+
+
+sampleselectedquestion = st.selectbox(
+    'Just ask your question or start with a one of these example questions...',  samplequestions    )
+
+st.write(" :green[ Ask any thing on your mind...just type your question here...]")
+yourquestion = st.text_input('Your question', sampleselectedquestion)
+st.write('Your typed .. ', yourquestion)
+
+
+
+
+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" )
+chain = load_qa_chain(llm=llmgpt3, chain_type="map_reduce")
+
+aimethod = st.radio(
+    "Choose a AI brain or document comprehension method",
+    ('2 minutes AI method map_reduce', '4 minutes AI method refine' ), index=0)
+
+mychain_type = "map_reduce"
+if aimethod ==  '2 minutes AI method map_reduce':
+  mychain_type = "map_reduce"
+if aimethod ==  '4 minutes AI method refine':
+  mychain_type = "refine"
+
+chain = load_qa_chain(llm=llmgpt3, chain_type=mychain_type)
+
+
+loader1 = PyPDFLoader(url)
+
+
+def history():
+  mycount = 0 
+  if 'count' not in st.session_state:
+    st.session_state['count'] =  0
+  else:
+    mycount = st.session_state['count']
+
+  if True:
+    st.write(mycount)
+    mycount = mycount + 1 
+    st.session_state['count'] = mycount
+    for i in range(mycount):
+      mystatekeyindex = "element" + str(i)
+      mystatekeyanswerindex = "elementANS" + str(i)
+      if mystatekeyindex not in st.session_state:
+        st.session_state[mystatekeyindex] =  yourquestion
+        st.session_state[mystatekeyanswerindex] = answer
+      if mystatekeyindex in st.session_state:
+        with st.expander(st.session_state[mystatekeyindex]):
+          st.write( st.session_state[mystatekeyanswerindex] )
+
+
+def colorizedtext(acolor, astring):
+  formattedcolor = ":" + acolor + "[" + astring +  "]"
+  return formattedcolor
+
+ 
+
+if st.button("Ask QA "):
+  documents = loader1.load()
+  answer = ""
+  with st.spinner(" Finding answer for your question .... AI will get you answer in 2 more minutes... "  ):
+    with st.expander( "Employing your choice of AI method ... " + aimethod + "..."):
+      st.write(str(chain)[:700])
+    st.write("AI is reading this [link](%s)" % url)    
+    prgpgress = st.progress(0)
+    st.subheader(colorizedtext("red", yourquestion))
+    for i in range(100):
+        time.sleep(0.9)
+        prgpgress.progress(i+1)
+
+
+
+    answer = chain.run(input_documents=documents, question=yourquestion)
+  st.subheader(colorizedtext("blue", answer))
+  history()
+
+
+
+
+ 

requirements.txt

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