Duplicate from Rajagopal/try4245

.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: Contract Summarization
+emoji: 🏆
+colorFrom: yellow
+colorTo: gray
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: Rajagopal/try4245
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,57 @@
+import streamlit as st
+from langchain import OpenAI, PromptTemplate, LLMChain
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains.mapreduce import MapReduceChain
+from langchain.prompts import PromptTemplate
+from langchain.chat_models import AzureChatOpenAI
+from langchain.chains.summarize import load_summarize_chain
+from langchain.chains import AnalyzeDocumentChain
+from PyPDF2 import PdfReader
+from langchain.document_loaders import TextLoader
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.document_loaders import PyPDFLoader
+
+
+
+import os
+os.environ["OPENAI_API_TYPE"] = "azure"
+os.environ["OPENAI_API_VERSION"] = "2023-05-15"
+os.environ["OPENAI_API_BASE"] = "https://cog-mnjbf5r4o6b3e.openai.azure.com/"
+os.environ["OPENAI_API_KEY"] = "957f7d98b47a467a98a786f7ca903112"
+
+llm = AzureChatOpenAI(
+                       deployment_name="gpt-4",
+            openai_api_version="2023-03-15-preview")
+
+
+
+st.title("Contract Management System")
+
+# description text
+st.write("""Hello! I'm an Al chatbot specifically created to assist vou with any procurement-related questions you may have. My range of capabilities includes providing information on contract expiry dates payment terms, and other relevant details. 
+
+Feel free to ask me anything you need help with!
+To get started, just provide me with the contract number and let me know what specitic details you're interested in. Additionally, tee tree to ask me any general questions you may have regardinc procurement. I'm here to assist vou in any way can 😊""")
+
+# pdf file upload
+pdf_file = st.file_uploader("Upload file", type=["pdf"])
+
+
+def extract_text_from_pdf():
+    reader = PdfReader(pdf_file)
+    # get all pages text
+    text = [reader.pages[i].extract_text() for i in range(len(reader.pages))]
+    # join all pages text
+    text = " ".join(text)
+    return text
+
+
+
+if st.button("Summerize Contract"):
+    with st.spinner("Extracting Text..."):
+        summary_chain = load_summarize_chain(llm, chain_type="map_reduce")
+        summarize_document_chain = AnalyzeDocumentChain(combine_docs_chain=summary_chain, verbose=True)
+        text = extract_text_from_pdf()
+    with st.spinner("Summarizing..."):
+        result = summarize_document_chain.run(text)
+    st.write(result)

requirements.txt

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