openbmb / agentverse Goto Github PK

All I changed are 2 lines, to redirect calls to my local oobabooga API endpoint which is OpenAI compatible.

$ git diff
diff --git a/agentverse/llms/openai.py b/agentverse/llms/openai.py
index 9b9332f..b221695 100644
--- a/agentverse/llms/openai.py
+++ b/agentverse/llms/openai.py
@@ -20,8 +20,9 @@ except ImportError:
     is_openai_available = False
     logging.warning("openai package is not installed")
 else:
-    openai.api_key = os.environ.get("OPENAI_API_KEY")
+    openai.api_key = "-" #os.environ.get("OPENAI_API_KEY")
     openai.proxy = os.environ.get("http_proxy")
+    openai.api_base = 'http://127.0.0.1:5001/v1'
     if openai.proxy is None:
         openai.proxy = os.environ.get("HTTP_PROXY")

After executing I am getting prompts to my local LLM and also getting responses back into the AgentVerse as seen in log below, but they are not getting parsed and ingested into the web UI.

How should I go about debugging this?

$ python main_demo.py --task nlp_classroom_3players
BMTools is not installed, tools cannot be used. To install BMTools,          please follow the instruction in the README.md file.
Running on local URL:  http://127.0.0.1:7861

To create a public link, set `share=True` in `launch()`.
09/17/2023 11:41:43 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:41:43 - WARNING - root - Retrying...
09/17/2023 11:41:43 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:41:43 - WARNING - root - Retrying...
09/17/2023 11:41:44 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:41:44 - WARNING - root - Retrying...
09/17/2023 11:41:44 - ERROR - root - Professor Micheal failed to generate valid response.
09/17/2023 11:41:44 - INFO - root - Professor Micheal:
09/17/2023 11:42:09 - ERROR - root - Failed to parse output of the model:You are Beta, a student curious about Natural Language Processing and you want to learn some basic concepts of NLP.

09/17/2023 11:42:09 - WARNING - root - Retrying...
09/17/2023 11:42:09 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:42:09 - WARNING - root - Retrying...
09/17/2023 11:42:10 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:42:10 - WARNING - root - Retrying...
09/17/2023 11:42:10 - ERROR - root - Student Beta failed to generate valid response.
09/17/2023 11:42:10 - INFO - root - Student Beta:
09/17/2023 11:42:32 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:42:32 - WARNING - root - Retrying...
09/17/2023 11:42:33 - ERROR - root - Failed to parse output of the model:

09/17/2023 11:42:33 - WARNING - root - Retrying...
09/17/2023 11:42:49 - ERROR - root - Failed to parse output of the model:1) What is a good way to remember important dates without writing them down?

A good way to remember important dates without writing them down is by using mnemonics, such as acronyms and associations. For example, if you need to remember the date of your anniversary with someone, think of it like "20 Years Together" (YT) or "My Lovely Partner's Special Day." This helps create a unique association in your mind so

09/17/2023 11:42:49 - WARNING - root - Retrying...
09/17/2023 11:42:49 - ERROR - root - Teaching Assistant Gamma failed to generate valid response.
09/17/2023 11:42:49 - INFO - root - Teaching Assistant Gamma:

Hi, I try to run the pokemon game, but the UI is not worked

(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'properties' does not exist on type 'GameObject'.
src/scenes/town/town.ts: (166:33)

166         for (let j = 0; j < npc.properties.length; j++) {
                                    ~~~~~~~~~~

src/scenes/town/town.ts: (167:19)

167           if (npc.properties[j].name === "id") {
                      ~~~~~~~~~~

src/scenes/town/town.ts: (168:24)

168             return npc.properties[j].value === i;

很好的项目，非常期待尝试成功，遇到两个问题：
1.如何set share=True
2.export OPENAI_API_KEY ，仍然warning ，提示要设置OPENAI_API_KEY

我是在colab上运行的，

Introduce the agentVerse, including simulation and tasksolving

您好！
我注意到目前的demo中，每个task的config.yaml中的llm_type是text-davinci-003，我尝试直接将其替换为gpt-3.5-turbo，程序会报错无法正常运行。

请问正确的做法是怎样，或者后续会有模型选择方面的改进和说明吗？

非常感谢！

When I want to run "main_simulation_cli.py --task simulation/alice_home ", it reports error "raise ValueError(
ValueError: reflection is not registered. Please register with the .register("reflection") method provided in AgentRegistry registry"

How to fix this ,thank you

Sorry. I don't understand why the version dependency is turned off in setup.py?

pydantic.error_wrappers.ValidationError: 1 validation error for ConversationAgent
prompt_template
field required (type=value_error.missing)

npm run watch

> [email protected] watch
> rollup --watch --config rollup.config.dev.mjs
rollup v3.29.1
bundles ./src/index.ts → dist/bundle.js...
http://127.0.0.1:10001 -> /home/ouwenjie/AgentVerse/ui/dist
(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'rexBoard' does not exist on type 'Scene'.
src/classes/npc.ts: (47:30)

47     this.moveTo = this.scene.rexBoard.add.moveTo(this, {
                                ~~~~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'setDepth' does not exist on type 'GameObject'.
src/classes/npc.ts: (156:13)

156       child.setDepth(this.y + this.height * 0.8);
                ~~~~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2304: Cannot find name 'Live2DCubismCore'.
src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/live2dcubismframework.ts: (93:7)

93       Live2DCubismCore.Logging.csmSetLogFunction(s_option.logFunction);
         ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/live2dcubismframework.ts: (100:31)

100       const version: number = Live2DCubismCore.Version.csmGetVersion();
                                  ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/live2dcubismframework.ts: (218:10)

218     if (!Live2DCubismCore.Logging.csmGetLogFunction()) {
             ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/live2dcubismframework.ts: (222:5)

222     Live2DCubismCore.Logging.csmGetLogFunction()(message);
        ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmoc.ts: (22:39)

22     const moc: Live2DCubismCore.Moc = Live2DCubismCore.Moc.fromArrayBuffer(
                                         ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmoc.ts: (52:43)

52     const model: Live2DCubismCore.Model = Live2DCubismCore.Model.fromMoc(
                                             ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (475:12)

475     return Live2DCubismCore.Utils.hasVertexPositionsDidChangeBit(
               ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (557:13)

557     return !Live2DCubismCore.Utils.hasIsDoubleSidedBit(
                ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (570:12)

570     return Live2DCubismCore.Utils.hasBlendAdditiveBit(
               ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (574:9)

574       : Live2DCubismCore.Utils.hasBlendMultiplicativeBit(
            ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (593:12)

593     return Live2DCubismCore.Utils.hasIsInvertedMaskBit(
               ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (641:12)

641     return Live2DCubismCore.Utils.hasIsVisibleBit(dynamicFlags[drawableIndex]);
               ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (657:12)

657     return Live2DCubismCore.Utils.hasVisibilityDidChangeBit(
               ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (675:12)

675     return Live2DCubismCore.Utils.hasOpacityDidChangeBit(
               ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (693:12)

693     return Live2DCubismCore.Utils.hasRenderOrderDidChangeBit(
               ~~~~~~~~~~~~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2503: Cannot find namespace 'Live2DCubismCore'.
src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/live2dcubismframework.ts: (253:16)

253   logFunction: Live2DCubismCore.csmLogFunction; // ログ出力の関数オブジェクト
                   ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmoc.ts: (22:16)

22     const moc: Live2DCubismCore.Moc = Live2DCubismCore.Moc.fromArrayBuffer(
                  ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmoc.ts: (52:18)

52     const model: Live2DCubismCore.Model = Live2DCubismCore.Model.fromMoc(
                    ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmoc.ts: (80:28)

80   private constructor(moc: Live2DCubismCore.Moc) {
                              ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmoc.ts: (95:9)

95   _moc: Live2DCubismCore.Moc; // Mocデータ
           ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (76:22)

76   public getModel(): Live2DCubismCore.Model {
                        ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (766:29)

766   public constructor(model: Live2DCubismCore.Model) {
                                ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/model/cubismmodel.ts: (799:19)

799   private _model: Live2DCubismCore.Model; // モデル
                      ~~~~~~~~~~~~~~~~

src/phaser3-rex-plugins/plugins/gameobjects/live2d/framework/src/utils/cubismdebug.ts: (117:21)

117     const logPrint: Live2DCubismCore.csmLogFunction =
                        ~~~~~~~~~~~~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'layer' does not exist on type 'GameObject'.
src/scenes/town/town.ts: (145:62)

145       var collide = ["wall", "tree", "house"].includes(chess.layer.name);
                                                                 ~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'index' does not exist on type 'GameObject'.
src/scenes/town/town.ts: (146:28)

146       if (collide && chess.index != -1) {
                               ~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'rexChess' does not exist on type 'GameObject'.
src/scenes/town/town.ts: (147:15)

147         chess.rexChess.setBlocker();
                  ~~~~~~~~

(!) Plugin typescript: @rollup/plugin-typescript TS2339: Property 'properties' does not exist on type 'GameObject'.
src/scenes/town/town.ts: (166:33)

166         for (let j = 0; j < npc.properties.length; j++) {
                                    ~~~~~~~~~~

src/scenes/town/town.ts: (167:19)

167           if (npc.properties[j].name === "id") {
                      ~~~~~~~~~~

src/scenes/town/town.ts: (168:24)

168             return npc.properties[j].value === i;
                           ~~~~~~~~~~

(!) Circular dependency
src/phaser3-rex-plugins/templates/ui/tweaker/TweakerShell.js -> src/phaser3-rex-plugins/templates/ui/tweaker/methods/Methods.js -> src/phaser3-rex-plugins/templates/ui/tweaker/methods/AddFolder.js -> src/phaser3-rex-plugins/templates/ui/tweaker/builders/CreateFolder.js -> src/phaser3-rex-plugins/templates/ui/tweaker/gameobjects/utils/CreateTweaker.js -> src/phaser3-rex-plugins/templates/ui/tweaker/TweakerShell.js
created dist/bundle.js in 54.9s

[2023-09-14 19:06:03] waiting for changes...

08/12/2023 11:42:52 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 502 Bad Gateway"
08/12/2023 11:42:52 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 502 Bad Gateway"
08/12/2023 11:43:34 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 502 Bad Gateway"
08/12/2023 11:43:34 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 502 Bad Gateway"

langchain/llms/openai.py:169: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: from langchain.chat_models import ChatOpenAI

in pycharm terminal it just keep saying all of this

09/25/2023 19:17:33 - WARNING - root - Retrying...
09/25/2023 19:17:56 - ERROR - root - Error communicating with OpenAI
09/25/2023 19:17:56 - WARNING - root - Retrying...
09/25/2023 19:18:27 - ERROR - root - Error communicating with OpenAI
09/25/2023 19:18:27 - WARNING - root - Retrying...
09/25/2023 19:18:27 - ERROR - root - Teaching Assistant Gamma failed to generate valid response.
09/25/2023 19:18:27 - INFO - root - Teaching Assistant Gamma:
09/25/2023 19:18:51 - ERROR - root - Error communicating with OpenAI
09/25/2023 19:18:51 - WARNING - root - Retrying...

在配置好了环境之后（使用了vpn），运行界面如下，但是并不能访问到127.0.0.1。请问下面的这个配置应该添加到哪个函数之中。
import os
os.environ["http_proxy"] = "http://127.0.0.1:7890"
os.environ["https_proxy"] = "http://127.0.0.1:7890"
os.environ["all_proxy"] = "socks5://127.0.0.1:7890"

Hello OpenBMB team,

Your work on AgentVerse is awesome, and we at Gradio are absolutely loving the use-case!

Have you considered showcasing it on Hugging Face Spaces? A few benefits could be :

• Expanded Reach: Introduce your demo to a larger, AI-focused audience.
• Seamless Integration: HuggingFace offers great compatibility with popular ML libraries.
• Engage the Community: Benefit from real-time community feedback and interactions.
• Additionally, our Community GPU Grants might be of interest for resource support.

Would be very happy to help!
This is a step-by-step guide explaining the process of creating a gradio sdk on Spaces, in case you're interested. 😊 This is our docs on Community GPU Grants.

ValueError: debate is not registered. Please register with the .register("debate") method provided in OutputParserRegistry registry

文档内容似乎不一样了，文件没有main_demon.py

而且我的启动模式是这个

在第二个终端输入npm install之后报错。具体如下：

在第一个终端显示：
FileNotFoundError: [WinError 3] 系统找不到指定的路径。: 'C:\AgentVerse\ui\node_modules\.staging\eventemitter3-1e3b8f15\umd'

在第二个终端显示：
npm WARN optional SKIPPING OPTIONAL DEPENDENCY: fsevents@~2.3.2 (node_modules\rollup\node_modules\fsevents):
npm WARN notsup SKIPPING OPTIONAL DEPENDENCY: Unsupported platform for [email protected]: wanted {"os":"darwin","arch":"any"} (current: {"os":"win32","arch":"x64"})
npm WARN optional SKIPPING OPTIONAL DEPENDENCY: fsevents@~2.3.2 (node_modules\chokidar\node_modules\fsevents):
npm WARN notsup SKIPPING OPTIONAL DEPENDENCY: Unsupported platform for [email protected]: wanted {"os":"darwin","arch":"any"} (current: {"os":"win32","arch":"x64"})
npm WARN [email protected] requires a peer of encoding@^0.1.0 but none was installed.
npm WARN [email protected] requires a peer of vite@^3.0.0 || ^4.0.0 but none was installed.
npm ERR! Windows_NT 10.0.19044
npm ERR! argv "C:\Users\anaconda3\envs\agentverse\Library\bin\node.exe" "C:\Users\anaconda3\envs\agentverse\node_modules\npm\bin\npm-cli.js" "install"
npm ERR! node v6.10.3
npm ERR! npm v3.10.10
npm ERR! path C:\AgentVerse\ui\node_modules.staging@types\estree-a9be2c14\package.json
npm ERR! code ENOTDIR
npm ERR! errno -4058
npm ERR! syscall open

npm ERR! ENOENT: no such file or directory, open 'C:\AgentVerse\ui\node_modules.staging@types\estree-a9be2c14\package.json'
npm ERR!
npm ERR! If you need help, you may report this error at:
npm ERR! https://github.com/npm/npm/issues

npm ERR! Please include the following file with any support request:
npm ERR! C:\AgentVerse\ui\npm-debug.log

输入npm -v能正常显示版本号，感觉不像是安装包的原因。

目前我通过测试发现，openai async 模式会造成
APIConnectionError: Error communicating with OpenAI错误。

排查了openai 代码和macos及windows环境测试，均会在开启vpn情况下报错，但是没有找到关闭async模式的开关，是否有这个开关？在代码中能看到有同步执行的代码，特意问问。

Add tutorial

在我运行main.py时，遇到如下报错：

我是用的梯子开了全局模式，并且测试了我的api是可以正常使用的。请问我应该怎样解决这个问题呢？

Hi Team!

Thanks for your contribution! I wonder if you can add minecraft example mentioned in the paper to this repo, so that we can observe the volunteer behaviors. That is a lot of fun.

Have a great time!

Hi I am having trouble when using Llama2 for tasksolving and the report it's like:
''' Loop Round 0
Traceback (most recent call last):
File "/home/likai/AgentVerse/agentverse_command/main_tasksolving_cli.py", line 35, in
cli_main()
File "/home/likai/AgentVerse/agentverse_command/main_tasksolving_cli.py", line 31, in cli_main
agentversepipeline.run()
File "/home/likai/AgentVerse/agentverse/tasksolving.py", line 66, in run
result, advice, previous_plan, logs, success = asyncio.run(
File "/home/likai/.conda/envs/agentverse/lib/python3.9/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/home/likai/.conda/envs/agentverse/lib/python3.9/asyncio/base_events.py", line 642, in run_until_complete
return future.result()
File "/home/likai/AgentVerse/agentverse/environments/tasksolving_env/basic.py", line 54, in step
agents = await self.rule.role_assign(
File "/home/likai/AgentVerse/agentverse/environments/tasksolving_env/rules/base.py", line 82, in role_assign
agents = await self.role_assigner.astep(
File "/home/likai/AgentVerse/agentverse/environments/tasksolving_env/rules/role_assigner/role_description.py", line 31, in astep
roles = await role_assigner.astep(advice, task_description, len(group_members))
File "/home/likai/AgentVerse/agentverse/agents/tasksolving_agent/role_assigner.py", line 34, in astep
prepend_prompt, append_prompt, prompt_token = self.get_all_prompts(
File "/home/likai/AgentVerse/agentverse/agents/base.py", line 68, in get_all_prompts
num_prepend_prompt_token = count_string_tokens(
File "/home/likai/AgentVerse/agentverse/llms/utils/token_counter.py", line 11, in count_string_tokens
return len(tiktoken.encoding_for_model(model).encode(prompt))
File "/home/likai/.conda/envs/agentverse/lib/python3.9/site-packages/tiktoken/model.py", line 97, in encoding_for_model
return get_encoding(encoding_name_for_model(model_name))
File "/home/likai/.conda/envs/agentverse/lib/python3.9/site-packages/tiktoken/model.py", line 84, in encoding_name_for_model
raise KeyError(
KeyError: 'Could not automatically map llama-2-7b-chat-hf to a tokeniser. Please use tiktoken.get_encoding to explicitly get the tokeniser you expect.'
'''
Can you let me know if this is because local llms is still under developing or I made some mistakes using local llms, thank you!

你好，安装最新版本的AgentVerse和BMTools之后，出现了这个ModuleNotFoundError: No module named 'bmtools.agent'。我看了下bmtools package里面好像也没这个定义

Hi I had issue when running the example, both gui and cli:
Is there anything I can do to solve this issue?

will register airbnb
will register job_search
will register gradio_tools
will register travel
will register walmart
Failed to parse output of the model:Action: Speak
Action Input: Good morning, everyone! I hope you're all doing well today. For those who don't know me, my name is Professor Michael, and I'll be your instructor for today's lecture on the Transformer architecture of neural networks. Before we dive into the topic, I just want to remind you
that if you have any questions, please feel free to raise
your hand, and I'll be happy to address them. Now, let's get started!

PULL_REQUEST_TEMPLATE.md

Hi
Thank you for the excellent work!
I am using release-0.1 for simulation. But I have encountered the following problem：

10/18/2023 21:42:49 - ERROR - root - 无效的令牌
10/18/2023 21:42:49 - WARNING - root - Retrying...
10/18/2023 21:42:54 - ERROR - root - Error communicating with OpenAI
10/18/2023 21:42:54 - WARNING - root - Retrying...
10/18/2023 21:42:56 - ERROR - root - 无效的令牌
10/18/2023 21:42:56 - WARNING - root - Retrying...
10/18/2023 21:42:56 - ERROR - root - Professor Michael failed to generate valid response.

我在anaconda prompt 上使用set OPENAI_API_KEY="your_api_key_here" 进行导入，之后运行main.py时报错提示没有api key，
error message:
Did not find openai_api_key, please add an environment variable OPENAI_API_KEY which contains it, or
pass openai_api_key as a named parameter. (type=value_error)

使用release0.1的分支，conda安装python3.9,安装BMtools
使用uvicorn pokemon_server:app --reload --port 10002 运行
显示BMtools没有安装，
missing 1 required positional argument: 'tasks_dir'

您好，我自定了一个自己的环境，写好了相关的config.yaml，接下来我使用命令agentverse-simulation --task medical/medical_consultation去执行，报错。接下来我认为应该是 agentverse-medical --task medical/medical_consultation命令来执行我新自定义的任务，我在阅读readme的时候，没有太明白怎么自定义解析器和将解析器定义在哪里，希望得到你的帮助，或者基于现在的最新版本代码，如何自定义自己的多智能体环境。

安装后，出错信息如下：
请看看是什么问题导致的呢？

-> % python3 main.py --task nlp_classroom_9players
will register chemical-prop
will register douban-film
will register wikidata
will register stock
will register weather
will register wikipedia
will register wolframalpha
will register office-ppt
will register bing_search
will register bing_map
will register baidu_map
will register nllb-translation
will register baidu-translation
will register tutorial
will register file_operation
will register meta_analysis
will register database
will register db_diag
will register code_interpreter
will register hugging_tools
will register arxiv
will register zillow
will register google_scholar
will register google_places
will register google_serper
will register python
will register sceneXplain
will register shell
will register image_generation
will register airbnb
will register job_search
will register gradio_tools
will register travel
will register walmart
Traceback (most recent call last):
File "/Users/nick/personal/AgentVerse/main.py", line 4, in
from agentverse.agentverse import AgentVerse
File "/Users/nick/personal/AgentVerse/agentverse/init.py", line 4, in
from .environments import env_registry
File "/Users/nick/personal/AgentVerse/agentverse/environments/init.py", line 7, in
from .basic import BasicEnvironment
File "/Users/nick/personal/AgentVerse/agentverse/environments/basic.py", line 6, in
from agentverse.agents.conversation_agent import BaseAgent
File "/Users/nick/personal/AgentVerse/agentverse/agents/init.py", line 6, in
from .base import BaseAgent
File "/Users/nick/personal/AgentVerse/agentverse/agents/base.py", line 8, in
from agentverse.memory import BaseMemory, ChatHistoryMemory
File "/Users/nick/personal/AgentVerse/agentverse/memory/init.py", line 7, in
from .summary import SummaryMemory
File "/Users/nick/personal/AgentVerse/agentverse/memory/summary.py", line 7, in
from agentverse.initialization import load_llm
File "/Users/nick/personal/AgentVerse/agentverse/initialization.py", line 18, in
from agentverse.memory_manipulator import memory_manipulator_registry
File "/Users/nick/personal/AgentVerse/agentverse/memory_manipulator/init.py", line 7, in
from .reflection import Reflection
File "/Users/nick/personal/AgentVerse/agentverse/memory_manipulator/reflection.py", line 12, in
from sklearn.metrics.pairwise import cosine_similarity
ModuleNotFoundError: No module named 'sklearn'
(textgen) nick@nickmac [09时30分29秒] [~/personal/AgentVerse] [main]
-> % pip install sklearn
Requirement already satisfied: sklearn in /Users/nick/anaconda3/envs/textgen/lib/python3.10/site-packages (0.0.post7)

10/01/2023 20:28:31 - ERROR - root - Error communicating with OpenAI
10/01/2023 20:28:31 - WARNING - root - Retrying...
10/01/2023 20:29:48 - ERROR - root - Error communicating with OpenAI
10/01/2023 20:29:48 - WARNING - root - Retrying...

报错了，是不是没少提交了代码。

(.venv) ➜ AgentVerse git:(main) ✗ python agentverse_command/main_simulation_gui.py --task simulation/nlp_classroom_9players
Traceback (most recent call last):
File "/Users/weibinke/ChatGPT/AgentVerse/agentverse_command/main_simulation_gui.py", line 2, in
from agentverse.gui import GUI
File "/Users/weibinke/ChatGPT/AgentVerse/.venv/lib/python3.11/site-packages/agentverse/init.py", line 1, in
from .tasks import *
File "/Users/weibinke/ChatGPT/AgentVerse/.venv/lib/python3.11/site-packages/agentverse/tasks/init.py", line 4, in
from .simulation.math_problem_2players_tools.output_parser import (
File "/Users/weibinke/ChatGPT/AgentVerse/.venv/lib/python3.11/site-packages/agentverse/tasks/simulation/math_problem_2players_tools/output_parser.py", line 6, in
from agentverse.parser import OutputParserError, output_parser_registry, OutputParser
File "/Users/weibinke/ChatGPT/AgentVerse/.venv/lib/python3.11/site-packages/agentverse/parser.py", line 4, in
from agentverse.llms.base import LLMResult
File "/Users/weibinke/ChatGPT/AgentVerse/.venv/lib/python3.11/site-packages/agentverse/llms/init.py", line 6, in
from .openai import OpenAIChat
File "/Users/weibinke/ChatGPT/AgentVerse/.venv/lib/python3.11/site-packages/agentverse/llms/openai.py", line 18, in
from agentverse.llms.utils.jsonrepair import JsonRepair
ModuleNotFoundError: No module named 'agentverse.llms.utils'

这个项目非要用到gpt-4吗？
如果只是3.5就不能运行？哪里可以改动成3.5可以走下去？

I try to run demo:

$ python3 main_demo.py --task db_diag

But have a bug

$ ImportError: cannot import name 'get_embedding' from 'agentverse.llms.openai'

I comfirmed in commit c89a6c5. It's look like "get_embedding" function wash deleted.

please help to fix this problem.

最新生成的KEY，游戏画面能进入，但是提示Error communicating with OpenAI

在git clone下来的文件夹中没有找到这个文件？

运行宝可梦出现问题

05/23/2023 09:59:16 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 502 Bad Gateway"
05/23/2023 09:59:17 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 502 Bad Gateway"
05/23/2023 09:59:32 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 502 Bad Gateway"
05/23/2023 09:59:33 - INFO - httpx - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 502 Bad Gateway"

执行 agentverse-simulation-gui --task simulation/db_diag 出现错误


而且对于其他模块

例如alice home,缺少环境参数

I completed the installation according to readme and configured the key, but when I tried running python3 main_demo.py --task nlp_classroom_9players

I cannot get the expected results on the webpage, and when I run other main_ During demo, there are still similar issues

Thank you for your excellent work. I would like to know whether the current framework supports multiple agents acting at the same time or only supports one agent acting at a time.

Do you use GPT-world to draw yourpicture ? What is the prompt ? I did not get good results when use it.

你好，已经安装了bmtools包，但是执行时还会报错ModuleNotFoundError: No module named 'bmtools.agent'，这是为什么？