Create app.py

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+import os
+from langchain import PromptTemplate
+from langchain.chat_models import AzureChatOpenAI
+import tiktoken
+from langchain.docstore.document import Document
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains.summarize import load_summarize_chain
+from langchain.chains import AnalyzeDocumentChain
+
+
+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"
+
+def generate_response(txt):
+    # Instantiate the LLM model
+    llm = AzureChatOpenAI(temperature=0, deployment_name='gpt-4-32k', openai_api_version="2023-03-15-preview")
+    # Split text
+    text_splitter = CharacterTextSplitter()
+    texts = text_splitter.split_text(txt)
+    # Create multiple documents
+    docs = [Document(page_content=t) for t in texts]
+    # Text summarization
+    prompt_template = """Write a structured report on the quality issues in the following text, are there any similarities across sites?:
+
+
+    {text}
+
+
+    Report:"""
+    PROMPT = PromptTemplate(template=prompt_template, input_variables=["text"])
+    chain = load_summarize_chain(AzureChatOpenAI(deployment_name="chat", temperature=0), chain_type="map_reduce", return_intermediate_steps=True, map_prompt=PROMPT, combine_prompt=PROMPT, verbose=True)
+    output = chain({"input_documents": docs}, return_only_outputs=True)['output_text']
+
+
+    return output
+
+# Page title
+st.set_page_config(page_title='Health Data Summarization App')
+st.title('quality issues')
+
+# Text input
+txt_input = st.text_area('Enter your quality data', '', height=200)
+
+# Form to accept user's text input for summarization
+result = []
+with st.form('summarize_form', clear_on_submit=True):
+    submitted = st.form_submit_button('Submit')
+    if submitted:
+        with st.spinner('Calculating...'):
+            response = generate_response(txt_input)
+            result.append(response)
+        
+
+if len(result):
+    st.info(response)