Update azure_openai.py

azure_openai.py

@@ -1,16 +1,14 @@
 # openai  
-import os
 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
 
-# Initialize an instance of AzureOpenAI using the specified settings
-
 
 # LLM Langchain Definition
-OPENAI_API_KEY = st.secrets['azure_api_key']
+# OPENAI_API_KEY = st.secrets['azure_api_key']
+OPENAI_API_KEY = "86b631a9c0294e9698e327c59ff5ac2c"
 OPENAI_API_TYPE = "azure"
 OPENAI_API_BASE = "https://davidfearn-gpt4.openai.azure.com"
 # OPENAI_API_VERSION = "2024-02-01"
@@ -19,9 +17,26 @@ OPENAI_API_VERSION = "2024-08-01-preview"
 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.
 
-def get_res(user_query, history, knowledge, systemMessgae, userMessage, temp, tokens):
+    :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,
@@ -31,6 +46,7 @@ def get_res(user_query, history, knowledge, systemMessgae, userMessage, temp, to
     temperature=temp, 
     max_tokens=tokens  # Name of the deployment for identification
 )
+    userMessage = """{conversationToDate}"""
 
     system_message_template = SystemMessagePromptTemplate.from_template(systemMessgae)
     human_message_template = HumanMessagePromptTemplate.from_template(userMessage)
@@ -40,33 +56,41 @@ def get_res(user_query, history, knowledge, systemMessgae, userMessage, temp, to
 
     chain = prompt | llm | StrOutputParser()
     
-    return chain.stream({
-        "user_question": user_query,
-        "history": history,
-        "knowledge": knowledge
+    return chain.invoke({
+        "assetGlossary": asset,
+        "conversationToDate": history
     })
 
-def qt(systemMessgae, history, temp, tokens):
 
+def get_response(chat_history, qte, knowledge, temp1, temp2, tokens1, 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=temp, 
-    max_tokens=tokens  # Name of the deployment for identification
-)
-    userMessage = """ Converstaion to date: {history}
-"""
-    system_message_template = SystemMessagePromptTemplate.from_template(systemMessgae)
-    human_message_template = HumanMessagePromptTemplate.from_template(userMessage)
+        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, human_message_template])
+    prompt = ChatPromptTemplate.from_messages([system_message_template, persona2UserMessage])
 
     chain = prompt | llm | StrOutputParser()
     
-    return chain.invoke({
-        "history": history,
-    })
+    print(asset)
+
+    return chain.stream({
+        "assetGlossary": asset,
+        "query": chat_history,
+        "knowledge": knowledge
+    })
+
+
+