Jimmy_L

无人机悬停后会乱飞

3

版本v1.11，按照文档建立通信后启动键盘控制，速度调到0.3以上进入offboard并启动，升高后按s进入悬停模式，过一会无人机就开始自动乱飞乱撞。

用vins-fuison和ego跑三维路径规划，地图是indoor4；先是从起始点每隔一小段给一个目标点，让无人机走过拐角，同时rviz显示这段路的点云信息，然后再把目标点设在之前的起始点，规划的路径（红线）居然是直接穿过转角点云的，这是哪出问题了？  

some funtion is not valid in vscode such as "build a coordinate and make visualization"

5

### Checklist - [X] I have searched for [similar issues](https://github.com/isl-org/Open3D/issues). - [X] For Python issues, I have tested with the [latest development wheel](https://www.open3d.org/docs/latest/getting_started.html#development-version-pip). - [X] I have checked the [release...

Does anyone know that this method can get the real size of an object？

1

If I reconstruction a 10cm^3 cube, will the output 3D model be the same size as the real world? Or is there a certain conversion ratio?

The agent does not use tool to make response？

3

I refer to [https://github.com/langchain-ai/langserve/blob/main/examples/agent/server.py](url) to build my own RAG agent. test code as follows: ``` from fastapi import FastAPI from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder from langserve import add_routes from langchain_openai...

How do I use create_react_agent in langServe?

2

## Server test code as follows: ``` llm_end_point_url = "http://172.16.21.155:8000/v1/" model = ChatOpenAI(model="glm4v-9b",base_url=llm_end_point_url, api_key="api_key") ### embedding ### embedding_model = HuggingFaceEmbeddings(model_name='/root/ljm/bge/bge-large-zh-v1.5') ### milvus ### milvus_host = "***" milvus_port = *** collection_name...

GLM4私有部署如果要用langchain搭建agent，还需要做哪些改进？

1

看到仓库的GLM4 demo里面用fasiapi自定义了api，`langchain`接入部分只有简单QA。 本人也只是刚接触大模型一个月，想请教一下，如果接入`langchain`去搭建`Agent`调用`tool`的话，api里面还要定义哪些东西？

请教一下，glm-4v会支持vllm推理吗？

2

### Feature request / 功能建议 glm-4v使用vllm推理。 ### Motivation / 动机 目前想尝试服务器部署，使用多客户端对glm4v的api server发起请求，但是用Transformers推理返回结果太慢。看到glm4-chat用vllm推理的速度快了不少，因此希望4v也能支持vllm推理。 ### Your contribution / 您的贡献 *

[Feature Request]: How to deploy ragflow using images

1

### Is there an existing issue for the same feature request? - [x] I have checked the existing issues. ### Is your feature request related to a problem? ```Markdown ```...

[Performance]: inference with qwen2.5 using version vLLM 0.6.3 is felt to be slower

4

### Your current environment Then I roughly wrote a concurrent test code The output of `concurrent_test.py` import asyncio import time import random from datetime import datetime import httpx import csv...