refactor: simplify stream_chat_request method by removing unnecessary request_body parameter

Author: Pavan-Microsoft

src/api/api/api_routes.py

@@ -119,7 +119,7 @@ async def conversation(request: Request):
         conversation_id = request_json.get("conversation_id")
         query = request_json.get("query")
         chat_service = ChatService(request=request)
-        result = await chat_service.stream_chat_request(request_json, conversation_id, query)
+        result = await chat_service.stream_chat_request(conversation_id, query)
         track_event_if_configured(
             "ChatStreamSuccess",
             {"conversation_id": conversation_id, "query": query}

src/api/services/chat_service.py

@@ -8,9 +8,6 @@
 
 import json
 import logging
-import time
-import uuid
-from types import SimpleNamespace
 import asyncio
 import random
 import re
@@ -25,7 +22,6 @@
 
 from cachetools import TTLCache
 
-from helpers.utils import format_stream_response
 from common.config.config import Config
 
 # Constants
@@ -135,11 +131,10 @@ async def stream_openai_text(self, conversation_id: str, query: str) -> Streamin
                         ChatService.thread_cache[corrupt_key] = thread_id
                 yield "I cannot answer this question with the current data. Please rephrase or add more details."
 
-    async def stream_chat_request(self, request_body, conversation_id, query):
+    async def stream_chat_request(self, conversation_id, query):
         """
         Handles streaming chat requests.
         """
-        history_metadata = request_body.get("history_metadata", {})
 
         async def generate():
             try:

src/tests/api/services/test_chat_service.py

@@ -252,8 +252,7 @@ async def mock_stream_openai_text(conversation_id, query):
 
         chat_service.stream_openai_text = mock_stream_openai_text
 
-        request_body = {"history_metadata": {"test": "metadata"}}
-        generator = await chat_service.stream_chat_request(request_body, "conv_1", "Hello")
+        generator = await chat_service.stream_chat_request("conv_1", "Hello")
 
         chunks = []
         async for chunk in generator:
@@ -280,8 +279,7 @@ async def mock_stream_openai_text_rate_limit_error(conversation_id, query):
 
         chat_service.stream_openai_text = mock_stream_openai_text_rate_limit_error
 
-        request_body = {"history_metadata": {}}
-        generator = await chat_service.stream_chat_request(request_body, "conv_1", "Hello")
+        generator = await chat_service.stream_chat_request("conv_1", "Hello")
 
         chunks = []
         async for chunk in generator:
@@ -304,8 +302,7 @@ async def mock_stream_openai_text_generic_error(conversation_id, query):
 
         chat_service.stream_openai_text = mock_stream_openai_text_generic_error
 
-        request_body = {"history_metadata": {}}
-        generator = await chat_service.stream_chat_request(request_body, "conv_1", "Hello")
+        generator = await chat_service.stream_chat_request("conv_1", "Hello")
 
         chunks = []
         async for chunk in generator:
@@ -328,8 +325,7 @@ async def mock_stream_openai_text_generic_error(conversation_id, query):
 
         chat_service.stream_openai_text = mock_stream_openai_text_generic_error
 
-        request_body = {"history_metadata": {}}
-        generator = await chat_service.stream_chat_request(request_body, "conv_1", "Hello")
+        generator = await chat_service.stream_chat_request("conv_1", "Hello")
 
         chunks = []
         async for chunk in generator: