azure_openai.py

# openai  
import streamlit as st
# from langchain.chat_models import AzureChatOpenAI
from langchain_openai import AzureChatOpenAI
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts.chat import SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate


# LLM Langchain Definition
OPENAI_API_KEY = st.secrets['azure_api_key']
OPENAI_API_TYPE = "azure"
OPENAI_API_BASE = "https://davidfearn-gpt4.openai.azure.com"
# OPENAI_API_VERSION = "2024-02-01"
OPENAI_API_VERSION = "2024-08-01-preview"
# OPENAI_MODEL = "gpt4-turbo-1106"
OPENAI_MODEL = "gpt-4o"
# Initialize an instance of AzureOpenAI using the specified settings

def read_file(file):
    """
    Reads the content of a text file and returns it as a string.

    :param approver: The type of approver.
    :return: The content of the file as a string.
    """
    fp = f"assets/{file}.md"
    try:
        with open(fp, 'r', encoding='utf-8') as file:
            content = file.read()
        return content
    except FileNotFoundError:
        print(f"The file at {fp} was not found.")
    except IOError:
        print(f"An error occurred while reading the file at {fp}.")


def qt(systemMessgae, history, temp, tokens, file):
    asset = read_file(file)
    llm = AzureChatOpenAI(
    openai_api_version=OPENAI_API_VERSION,
    openai_api_key=OPENAI_API_KEY,
    azure_endpoint=OPENAI_API_BASE,
    openai_api_type=OPENAI_API_TYPE,
    deployment_name=OPENAI_MODEL,
    temperature=temp, 
    max_tokens=tokens  # Name of the deployment for identification
)
    userMessage = """## Converstaion to date: {conversationToDate}
    
    ## Create Optimised Query
    """

    system_message_template = SystemMessagePromptTemplate.from_template(systemMessgae)
    human_message_template = HumanMessagePromptTemplate.from_template(userMessage)
    
    # Create a chat prompt template combining system and human messages
    prompt = ChatPromptTemplate.from_messages([system_message_template, human_message_template])

    chain = prompt | llm | StrOutputParser()
    
    return chain.invoke({
        "assetGlossary": asset,
        "conversationToDate": history
    })


def get_response(chat_history, qte, knowledge, temp2, tokens2, persona2SystemMessage, persona2UserMessage, file):
    asset = read_file(file)
    llm = AzureChatOpenAI(
        openai_api_version=OPENAI_API_VERSION,
        openai_api_key=OPENAI_API_KEY,
        azure_endpoint=OPENAI_API_BASE,
        openai_api_type=OPENAI_API_TYPE,
        deployment_name=OPENAI_MODEL,
        temperature=temp2, 
        max_tokens=tokens2
            # Name of the deployment for identification
    )


    system_message_template = SystemMessagePromptTemplate.from_template(persona2SystemMessage)
    
    
    # Create a chat prompt template combining system and human messages
    prompt = ChatPromptTemplate.from_messages([system_message_template, persona2UserMessage])

    chain = prompt | llm | StrOutputParser()

    return chain.stream({
        "assetGlossary": asset,
        "query": qte,
        "chatHistory": chat_history,
        "knowledge": knowledge
    })