Create version/semapdf1.0.py

version/semapdf1.0.py

@@ -0,0 +1,105 @@
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS
+from langchain.callbacks import get_openai_callback
+from PyPDF2 import PdfReader
+import json
+import openai
+import streamlit as st
+import os
+import requests
+
+
+# Page configuration
+st.set_page_config(page_title="PesaQ", page_icon="💸", layout="wide",)
+
+#set Open-AI key
+os.environ["OPENAI_API_KEY"] = st.secrets["OPENAI_API_KEY"]
+
+
+# Sema Translator
+def translate(userinput, target_lang, source_lang=None):
+    if source_lang:
+       url = "https://5d5c-44-208-85-154.ngrok-free.app/translate_enter/"
+       data = {
+           "userinput": userinput,
+           "source_lang": source_lang,
+           "target_lang": target_lang,
+        }
+       response = requests.post(url, json=data)
+       result = response.json()
+       print(type(result))
+       source_lange = source_lang
+       translation = result['translated_text']
+       return source_lange, translation
+    else:
+      url = "https://5d5c-44-208-85-154.ngrok-free.app/translate_detect/"
+      data = {
+        "userinput": userinput,
+        "target_lang": target_lang,
+      }
+
+      response = requests.post(url, json=data)
+      result = response.json()
+      source_lange = result['source_language']
+      translation = result['translated_text']
+      return source_lange, translation
+
+
+def main():
+        st.title("📚 PesaDoc")
+        # upload file
+        pdf = st.file_uploader("Upload a financial Document and ask questions to get insights", type="pdf")
+
+        # extract the text
+        if pdf is not None:
+          reader = PdfReader(pdf)
+          pdf_text = ''
+          for page in (reader.pages):
+            text = page.extract_text()
+            if text:
+              pdf_text += text
+
+          # Define our text splitter
+          text_splitter = CharacterTextSplitter(
+          separator = "\n",
+          chunk_size = 1000, #thousand charctere
+          chunk_overlap  = 200,
+          length_function = len,
+          )
+          #Apply splitting
+          text_chunks = text_splitter.split_text(pdf_text)
+
+          # Use embeddings from OpenAI
+          embeddings = OpenAIEmbeddings()
+          #Convert text to embeddings
+          pdf_embeddings = FAISS.from_texts(text_chunks, embeddings)
+          chain = load_qa_chain(OpenAI(), chain_type="stuff")
+
+          #user_question = st.text_input("Get insights into your finances ...")
+          # show user input
+          if "messages" not in st.session_state:
+              st.session_state.messages = []
+
+          for message in st.session_state.messages:
+              with st.chat_message(message["role"]):
+                st.markdown(message["content"])
+
+          if user_question := st.chat_input("Ask your document anything ......?"):
+            with st.chat_message("user"):
+                st.markdown(user_question)
+            user_langd, Queryd = translate(user_question, 'eng_Latn')
+            st.session_state.messages.append({"role": "user", "content": user_question})
+            docs = pdf_embeddings.similarity_search(Queryd)
+            # print(len(docs))
+            response = chain.run(input_documents=docs, question=Queryd)
+            output = translate(response, user_langd, 'eng_Latn')[1]
+            with st.chat_message("assistant"):
+                st.markdown(output)
+                st.session_state.messages.append({"role": "assistant", "content": output})
+
+
+if __name__ == '__main__':
+    main()