fix chat issue

Author: leehuwuj

templates/components/engines/python/agent/engine.py

@@ -8,7 +8,7 @@
 from llama_index.core.tools.query_engine import QueryEngineTool
 
 
-def get_chat_engine(filters=None, params=None, event_handlers=None):
+def get_chat_engine(filters=None, params=None, event_handlers=None, **kwargs):
     system_prompt = os.getenv("SYSTEM_PROMPT")
     top_k = int(os.getenv("TOP_K", 0))
     tools = []

templates/components/engines/python/chat/engine.py

@@ -9,7 +9,7 @@
 from llama_index.core.settings import Settings
 
 
-def get_chat_engine(filters=None, params=None, event_handlers=None):
+def get_chat_engine(filters=None, params=None, event_handlers=None, **kwargs):
     system_prompt = os.getenv("SYSTEM_PROMPT")
     citation_prompt = os.getenv("SYSTEM_CITATION_PROMPT", None)
     top_k = int(os.getenv("TOP_K", 0))

templates/types/streaming/fastapi/app/api/routers/chat.py

@@ -1,10 +1,10 @@
 import logging
 from typing import List
 
-from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException, Request, status
+from fastapi import APIRouter, BackgroundTasks, HTTPException, Request, status
 from llama_index.core.agent import AgentRunner
 from llama_index.core.chat_engine import CondensePlusContextChatEngine
-from llama_index.core.chat_engine.types import BaseChatEngine, NodeWithScore
+from llama_index.core.chat_engine.types import NodeWithScore
 from llama_index.core.llms import MessageRole
 
 from app.api.routers.events import EventCallbackHandler
@@ -86,11 +86,12 @@ async def chat(
 @r.post("/request")
 async def chat_request(
     data: ChatData,
-    chat_engine: BaseChatEngine = Depends(get_chat_engine),
 ) -> Result:
     last_message_content = data.get_last_message_content()
     messages = data.get_history_messages()
 
+    chat_engine = get_chat_engine(filters=None, params=None)
+
     response = await chat_engine.achat(last_message_content, messages)
     return Result(
         result=Message(role=MessageRole.ASSISTANT, content=response.response),

templates/types/streaming/fastapi/app/api/routers/vercel_response.py

@@ -8,7 +8,6 @@
 from fastapi.responses import StreamingResponse
 from llama_index.core.chat_engine.types import StreamingAgentChatResponse
 
-from app.agents.single import AgentRunEvent, AgentRunResult
 from app.api.routers.events import EventCallbackHandler
 from app.api.routers.models import ChatData, Message, SourceNodes
 from app.api.services.suggestion import NextQuestionSuggestion
@@ -144,16 +143,16 @@ def _create_stream(
         self,
         request: Request,
         chat_data: ChatData,
-        event_handler: AgentRunResult | AsyncGenerator,
-        events: AsyncGenerator[AgentRunEvent, None],
+        event_handler: "AgentRunResult" | AsyncGenerator,
+        events: AsyncGenerator["AgentRunEvent", None],
         verbose: bool = True,
     ):
         # Yield the text response
         async def _chat_response_generator():
             result = await event_handler
             final_response = ""
 
-            if isinstance(result, AgentRunResult):
+            if isinstance(result, "AgentRunResult"):
                 for token in result.response.message.content:
                     final_response += token
                     yield self.convert_text(token)
@@ -185,7 +184,7 @@ async def _event_generator():
         return combine
 
     @staticmethod
-    def _event_to_response(event: AgentRunEvent) -> dict:
+    def _event_to_response(event: "AgentRunEvent") -> dict:
         return {
             "type": "agent",
             "data": {"agent": event.name, "text": event.msg},