AutoGPT最新版本下载

当前版本

Auto-GPT v0.4.7

来源:AutoGTP中文网

Github下载链接:https://github.com/Significant-Gravitas/Auto-GPT/releases/latest

发布日期:2023年8月12日

Auto-GPT v0.4.7引入了初始的REST API支持,使用e2b的agent protocol SDK提供支持。它还改进了提示生成功能,并支持我们的新基准测试工具Auto-GPT-Benchmarks。

我们还将文档迁移到了Material Theme,网址为https://docs.aGPT.co。同时,我们修复了一些错误并进行了底层改进。

 

历史版本

AutoGPT-0.3.0

 

来源:AutoGTP中文网

发布日期:2023年5月3日

 

版本介绍

自上一个版本 v0.2.2 发布以来已经过去了一个星期,产生了275 个推请求(push request),我们很高兴地宣布发布 v0.3.0版本!从现在开始,我们将专注于重大改进而不是修复错误,因为我们认为稳定性已经达到了一个合理的水平。剩下的大部分问题与提示生成和内存系统的限制有关,这将成为我们下一个版本的重点。

 

亮点

  • 插件:
    • 支持第三方开发者可以通过编写插件来扩展 AutoGPT 的功能。
  • 测试驱动开发
  • 简化Prompt
    • 自动初始Prompt生成器使 Auto-GPT 变得更加容易使用。
  • 自我反馈
    • 这个功能使 AI 可以通过考虑自己的内部评估来进行反思并且提高其思考、计划和推理能力。要使用此功能,请在 Auto-GPT 要求您输入时按下“S”键。
  • 内存管理

记录

由@BillSchumacher在#757中实现插件支持
由@richbeales在#1986中更新docker-hub镜像推送操作
由@juanignacioronca在#2272中实现稳定性
由@k-boikov在#2669中实现docker构建中包括openapi-python-client
由@chenfengyanyu在#2523中修复README中的./run.sh start-> ./run.sh
在#2619中取消正在进行的docker CI的过时流程
在#2667中更新git clone命令以使用stable分支的文档
由@peterbanda在#2680中固定BeautifulSoup版本以修复browse_website
由@Pwuts在#2727中修复#2654 spacy语言模型安装
由@mickjagger19在#2665中修复当cwd!=项目根目录时,validate_json文件错误
由@AndresCdo在#2691中添加丢失的size参数以生成带有dalle的图像
由@Nickfost在#2753中修复下载文件命令的标签

查看详细
  • Plugin Support by @BillSchumacher in #757
  • Shirt size labeling for PRs by @ntindle in #2467
  • fix shirt-sizing workflow permissions by @Pwuts in #2605
  • Update docker-hub image push action by @richbeales in #1986
  • Stable by @juanignacioronca in #2272
  • include openapi-python-client in docker build by @k-boikov in #2669
  • Fix README ./run.sh start -> ./run.sh by @chenfengyanyu in #2523
  • Cancel in-progress docker CI on outdate by @edcohen08 in #2619
  • doc: update git clone command to use stable branch by @egonm12 in #2667
  • Use inclusive language: Rename 'blacklist' to 'denylist' and 'whitelist' to 'allowlist' by @riensen in #2644
  • Pin BeautifulSoup version to fix browse_website by @peterbanda in #2680
  • fix #2654 spacy language model installation by @Pwuts in #2727
  • Fix validate_json file error when cwd != project root by @mickjagger19 in #2665
  • Add missing size param to generate_image_with_dalle by @AndresCdo in #2691
  • Fix label of download_file command by @Nickfost in #2753
  • Fix typo's by @lengweiping1983 in #2735
  • Add Coverage reporting to CI pipeline by @ntindle in #2628
  • Make load_azure_config throw if azure.yaml does not exist by @Pwuts in #2758
  • docs: fix small typo in README by @chrisvxd in #2752
  • Update README.md by @Bsodoge in #2709
  • add instruction to show .env by @itsmarble in #2705
  • Update pre-commit version by @AndresCdo in #2682
  • Improve plugin section in README.md to prevent dependency errors by @riensen in#2651
  • Added version select to bug template by @cryptidv in #2545
  • only adjust argument order by @lengweiping1983 in #2313
  • Make config load and override for every new run by @coditamar in #2788
  • Update README.md by @T-Higgins in #2785
  • fix indentation of bug template yml by @k-boikov in #2832
  • Fix docker usage readme by @pkqs90 in #2406
  • Update README.md ( IMAGE_PROVIDER=sd=> IMAGE_PROVIDER=huggingface ) by @okunishinishi in #2802
  • [Hotfix] Fix coverage tooling by @ntindle in #2771
  • Add OS Info into the initial prompt by @MikelCalvo in #2587
  • Update readme to more clearly describe usage between platforms by @BuildEverything in #2837
  • Use readline if available by @jlxip in #2558
  • Add file op tests by @rocks6 in #2205
  • fixed typo by @sudouser777 in #2851
  • [feat] Update milvus_memory_test.py error log by @AndresCdo in #2679
  • Add Code Cov by @ntindle in #2877
  • Added basic spinner tests and modified spinner method docstring by @OmriGM in #2855
  • Documentation: fixing typos in README.md by @didier-durand in #2886
  • Update README to include Eleven Labs speech setup by @minghinmatthewlam in #2884
  • Fixing header of CONTRIBUTING.md by @didier-durand in #2888
  • adjust file_operations.py code format by @gklab in #2756
  • Fix(tests): restore config values after changing them in tests by @Torantulino in #2904
  • Add CodeCov CI coverage requirements by @ntindle in #2881
  • Re-work Docs and split out README (using MkDocs) by @richbeales in #2894
  • ci: selenium safari bug fixed by @dharana77 in #2915
  • Replace print statements with logging.error by @ugobok in #2708
  • Fix plugin command arg ordering issue. by @BillSchumacher in #2631
  • misc: fix typo in benchmark by @jazelly in #2521
  • Tests utils suite by @rihp in #2961
  • Automatic prompting by @Torantulino in #2896
  • Documentation typo: serach -> search by @didier-durand in #2977
  • Mark test test_generate_aiconfig_automatic_typical as @requires_api_… by @richbeales in #2981
  • Add note for windows install by @ntindle in #2970
  • Fix to prompt generator - "Ensure the response can beparsed" by @richbeales in #2980
  • Add missing test decorator by @richbeales in #2989
  • update weaviate.py for weaviate compatibility by @non-adj in #2985
  • Documentation: fixing typos by @didier-durand in #2978
  • Documentation: ensuring naming consistency by @didier-durand in #2975
  • update documentation deploy gh action by @richbeales in #3030
  • Support secure and authenticated Milvus memory backends by @chyezh in #2127
  • Fix Milvus module config import by @chyezh in #3036
  • Add workspace abstraction by @collijk in #2982
  • Fix typo in warning message when non allowlisted plugins found by @hdkiller in #3044
  • Make Auto-GPT aware of its running cost by @Vwing in #762
  • Add tests for json_utils.json_fix_llm by @coditamar in #2952
  • Perm memory test cases by @rihp in #2996
  • Refactor/collect embeddings code by @collijk in #3060
  • Bugfix/make local memory json when it doesnt exist by @collijk in #3066
  • Resolve sequencing issue in global state management by @collijk in #3089
  • Fixed incorrect comment: Clear memory instead of Redis by @scout9ll in #3092
  • Handle API timeouts by @soheil in #3024
  • Validate URLs in web commands before execution by @edcohen08 in #2616
  • Add function and class descriptions to tests by @AndresCdo in #2715
  • Improve docker setup & config by @Pwuts in #1843
  • Add arg to do_nothing command by @fluxism in #3090
  • fix test_search_files for windows by @k-boikov in #3073
  • Clean up GitHub Workflows by @Pwuts in #3059
  • Adjust test_json_parser file by @younessZMZ in #1935
  • Error if null bytes are included in the path on windows by @collijk in #3147
  • Agent and agent manager tests by @rihp in #3116
  • Add indirection layer to entry point by @collijk in #3152
  • anontation fix by @zhanglei1172 in #3018
  • Hotfix/global agent manager workaround by @collijk in #3157
  • Remove dead permanent memory module by @collijk in #3145
  • Refactor/move singleton out of config module by @collijk in #3161
  • Add option to install plugin dependencies by @dychen in #3068
  • Re-add install-plugin-deps to CLI by @dychen in #3170
  • Update ci.yml by @ntindle in #3179
  • Bulletin patch - Updating 'BULLETIN.MD' to warn about the deprecation of baked-in 'send_tweet' command by @desojo in #3181
  • Ensure Fore.RED is followed by Fore.RESET by @lwneal in #3182
  • Add a little more descriptive installation instruction by @resduo in #3180
  • Update installation.md by @MarKiSS2000 in #3166
  • Refactor/decouple logger from global configuration by @collijk in #3171
  • docs fix to image generation by @ntindle in #3186
  • Feature: Added Self Feedback by @AbTrax in #3013
  • fix: use config instead of hardcoded filename by @ppetermann in #3189
  • unit test agent feedback by @merwanehamadi in #3209
  • Remove plugin notice from CONTRIBUTING.md by @Pwuts in #3227
  • Extract OpenAI API retry handler and unify ADA embeddings calls. by @collijk in #3191
  • Use explicit API keys when querying OpenAI by @collijk in #3241
  • Fix readme centering by @richbeales in #3243
  • Remove import time loading of config from llm_utils by @collijk in #3245
  • adding probably erroneously removed return value from execut_shell, g… by @psvensson in #3212
  • Load .env in package init by @collijk in #3251
  • Fix PR size autolabeler message by @ntindle in #3194
  • Fix get_ada_embedding return type by @Androbin in #3263
  • Fix docs alignment by @richbeales in #3302
  • Fix(docs) Contributing, CoC and License links by @Pwuts in #3308
  • Fix(docs) requirements link in installation guide by @apurvsibal in #3264
  • Codecov - don't fail pipelines for project cov changes by @vlad-ko in #3327
  • Update installation.md by @MarKiSS2000 in #3325
  • mock openai in test agent manager by @merwanehamadi in #3285
  • Have api manager use singleton pattern by @collijk in #3269
  • use pytest-recording with VCR by @merwanehamadi in #3283
  • test image gen by @merwanehamadi in #3287
  • Fix docs by @Pwuts in #3336
  • Clean up image generation tests by @collijk in #3338
  • fix set_total_budget docstring by @karlivory in #3288
  • Chat plugin capability by @Wladastic in #2929
  • Cassettes should not record Transfer-Encoding and test_write_file should use no memory by @merwanehamadi in #3342
  • Fix(workspace) root resolution by @Pwuts in #3365
  • Remove do_nothing (Do nothing) by @merwanehamadi in #3369
  • Hotfix/validate url strips query params by @edcohen08 in #3370
  • Run the integration tests in the CI pipeline BUT without API keys by @merwanehamadi in #3359
  • Set vcr_config scope to "session" by @Androbin in #3361
  • Fix MilvusMemory connecting to Zilliz by @chyezh in #3278
  • The unlooping and fixing of file execution. by @BillSchumacher in #3368
  • Exclude docs and test cassettes from linguist stats by @Pwuts in #3402
  • Minor improvements to the docs for voice config and testing by @Pwuts in #3407
  • Add makedirs to file operations by @montanaflynn in #3289
  • Browse Site Regression test by @merwanehamadi in #3387
  • Fix imports, type hints and fixtures for goal oriented tests by @Pwuts in #3415
  • Fix browse_website headless mode for Firefox by @Irmius in #2816
  • Update broken link by @ledrui in #3416
  • Fix README: remove redundant "Disclaimer" by @DhruvAwasthi in #3391
  • Add a regression test for the embedding by @collijk in #3422
  • Make y/n configurable by @edcohen08 in #3178
  • Fix URL to docs in API throttling message by @gantit in #3201
  • Add tests for code/shell execution & improve config fixture by @rickythefox in #1268
  • Removing unitest in favor of pytest from test_config.py by @rihp in #3417
  • Remove unittest in favor of pytest in the test_token_counter module by @rihp in #3453
  • move remove_color_codes to utils and add tests by @k-boikov in #3260
  • Refactor test_chat to use pytest instead of unittest by @rihp in #3484
  • Organize all the llm stuff into a subpackage by @collijk in #3436
  • Fix memory by adding it only when context window full by @merwanehamadi in #3469
  • More graceful browsing error handling by @collijk in #3494
  • update pyproject by @BillSchumacher in #2757
  • Architecture-agnostic dev-container patch, now with Redis  by @desojo in #3102
  • Feature/llm data structs by @collijk in #3486
  • Fix clone_repository to conform to URL validation by @SBNovaScript in #3150
  • Extend & improve file operations tests by @k-boikov in #3404
  • fix typo in testing.md by @eltociear in #3537
  • Removing duplicate tests browse_tests by @rihp in #3535
  • Refactor test_spiunner to deprecate unittest in favor of pytest by @rihp in #3532
  • Feature/challenge memory management by @merwanehamadi in #3425
  • Feature/challenge memory challenge B by @merwanehamadi in #3550
  • replace 50+ occurrences of print() with logger by @richbeales in #3056
  • Refactor AIConfig to Sanitize Input for Goal Parameters by @pr-0f3t in #3492
  • Feature/test summarization against memory challenge by @merwanehamadi in #3567
  • added tests for clone_repository by @k-boikov in #3558
  • add report method to typewriter_log & load report plugins into logger by @Wladastic in #3582
  • rename search_files to list_files by @richbeales in #3595
  • fix bug #3455 by @zyt600 in #3591
  • [bug] list_files api signature change in data_ingestion.py and lo… by @valayDave in #3601
  • Update documentation URLs to docs.agpt.co by @Pwuts in #3621
  • Fix side effects on message history by @AbTrax in #3619
  • Message about Pinecone initializing by @Ashutoshkataria19 in #1194
  • Fix file operations logger by @bobisme in #3489
  • update web_selenium.py to use try-with for headers by @non-adj in #2988
  • Fix multi-byte character handling in read_file by @sidewaysthought in #3173
  • Fix validate_json scheme path by @k-boikov in #3631
  • Fix the maximum context length issue by chunking by @kinance in #3222
  • Add warning for LLM to avoid context overflow by @Pwuts in #3646
  • Fix MACOS Zip Import Error when compressing plugin by @gravelBridge in #3629
  • Synchronize stable -> master by @Pwuts in #3677
  • Release v0.3.0 by @Pwuts in #3683

AutoGPT-0.2.2

本地下载链接

在 #1983 中由 @jakubbober 添加“Memory Backend Setup”字幕
在 #1866 中由 @merwanehamadi 进行基准测试json错误、清理json解析代码并实现json schema
在 #1977 中由 @cryptidv 修复了新的后端未添加到支持的内存中的问题
在 #1925 中由 @MrBrain295 修复了README.md
在 #1743 中由 @lonrun 添加了运行shell脚本的脚本
在 #1679 中由 @Slowly-Grokking 修复了data_ingestion.py的'no module named 'autogpt'"问题,并更新了ReadMe
在 #1859 中由 @0xArty 添加pytest
在 #2009 中由 @0xArty 将ci改为pytest
在 #1942 中由 @bennyhobart 改进了开发容器,使autogpt能够浏览网络
在 #2007 中由 @merwanehamadi 修复了用户输入被修改的问题
在 #1916 中由 @k-boikov 为日志记录添加了文件处理程序的utf-8编码
在 #2019 中由 @merwanehamadi 实现了特性/hotfix用户输入
在 #2020 中由 @ccheney 确保git操作在工作目录中发生
在 #2040 中由 @Pwuts 清理README
在 #2041 中由 @Void-n-Null 将新的演示视频实现到README.md中
在 #2022 中由 @AdrianScott 在句号后添加一个空格以获得更好的格式

查看详细

  • Add "Memory Backend Setup" subtitle by @jakubbober in #1983
  • benchmark json errors, clean json parsing code and implement json schema by @merwanehamadi in #1866
  • Fixed new backends not being added to supported memory by @cryptidv in #1977
  • Fix README.md by @MrBrain295 in #1925
  • Add run scripts for shell by @lonrun in #1743
  • data_ingestion.py 'no module named 'autogpt'" fix and ReadMe update by @Slowly-Grokking in #1679
  • minimall add pytest by @0xArty in #1859
  • Change ci to pytest by @0xArty in #2009
  • Improve dev containers so autogpt can browse the web by @bennyhobart in #1942
  • fix user input being modified by @merwanehamadi in #2007
  • add utf-8 encoding to file handlers for logging by @k-boikov in #1916
  • Feature/hotfix user input by @merwanehamadi in #2019
  • ensure git operations occur in the working directory by @ccheney in #2020
  • Clean up README by @Pwuts in #2040
  • Implement new demo video into README.md by @Void-n-Null in #2041
  • Added one space after period for better formatting by @AdrianScott in #2022
  • Added Credit to README.md Demo by @Void-n-Null in #2063
  • Add File Downloading Capabilities by @cryptidv in #1680
  • Fix milvus test Error: 'NameError: name 'MockConfig' is not defined' by @wangxuqi in #2061
  • Fix: Update run_continuous.sh to correctly pass all command-line arguments by @0xf333 in #2012
  • move comment to correct position by @nolan23 in #1555
  • feat: (aesthetic) add space on warning message by @BatesJernigan in #2003
  • Remove irrelevant noqa comments by @endolith in #905
  • add docker requirements - jsonschema by @Song2017 in #2083
  • Add the OpenAI API Keys Configuration to the top of the readme by @cryptidv in #2089
  • Add Nix flakes support through direnv by @superherointj in #1091
  • Don't incapacitate yourself! by @lfricken in #1240
  • feat(pr-labels): auto-label conflicting PRs by @Pwuts in #2195
  • Use latest alpine image for code execution by @rickythefox in #1192
  • fix(pr-label): set job permissions explicitly by @Pwuts in #2198
  • internal resource request bug by @REal0day in #2001
  • install chrome/firefox for headless browing when running in docker co… by @obonyojimmy in #1723
  • Unbound summary size by @tkaitchuck in #2056
  • Fix split file to handle edge case where overlap size > last chunk size by @rocks6 in #2062
  • 【fix】config.py format by @gklab in #2108
  • fix(pr-label): mitigate excessive concurrent runs by @Pwuts in #2203
  • fix a missing import by @XFFXFF in #2129
  • Update .env.template by @mawsyh in #2132
  • config.py: update OpenAI link to platform.openai.com by @suzuken in #2137
  • Update README.md with Weaviate installation and reference by @bobvanluijt in #2153
  • Remove requirements-docker.txt by @deece in #2024
  • Fix BRIAN_TTS - Prevent TypeError exception in _speech method by @gabrielrbarbosa in #2105
  • Update .env.template by @Funkelfetisch in #2172
  • Spelling Fixes by @H-jj-R in #2168
  • fix(pr-label): concurrency group cannot be empty by @Pwuts in #2217
  • Improve the error logging for OAI Issues by @cryptidv in #1987
  • added missing import by @aminghani in #2183
  • docs: update docs around Milvus by @hamidzr in #2176
  • memory object move to memory_add block by @lengweiping1983 in #2093
  • Add Fixes for Selenium Browsing On Linux by @cryptidv in #2096
  • Allow local Development without pip install using "pip install -e ." by @bszollosinagy in #1474
  • fixes Weaviate index name to classname conversion by @cs0lar in #1836
  • fix: unreadable text in console and potentially over the max token by @tzengyuxio in #2050
  • Added return type hint to execute_code.py file by @Tmpecho in #2227
  • changed rstrip for strip and added case for empty string by @Lootheo in #2193
  • Align flake, black and isort to pipelines and precommit hooks by @merwanehamadi in #2192
  • Make Continuous Integration Automatic by @Torantulino in #2327
  • Add non-essential warning for contributors by @cryptidv in #2359
  • Use click to parse arguments by @0xArty in #2373
  • Improve the Issue Templates by @cryptidv in #2375
  • Hotfix bugs template by @cryptidv in #2408
  • [Hotfix] bugs template again by @cryptidv in #2415
  • Fix for execute_shell_popen using WORKING_DIRECTORY by @ezolenko in #2318
  • Added ability to output news/announcements on startup by @richbeales in #2429
  • Hotfix - Announcement filename was incorrect by @richbeales in #2441
  • feat: Add support for running Chrome in Headless mode. by @ickma in #1473
  • Move to Python 3.10 & improve CI workflow by @Pwuts in #2369
  • fix(python-run): prompt users to install Docker when execute_python_file encounters a Docker error by @willcallender in #2231
  • Ensure Python 3.10 & 3.11 compatability by @drikusroor in #1815
  • Option to disable working directory restrictions by @Josh-XT in #1875
  • Rename evaluate_code to analyze_code by @willcallender in #1371
  • Image generation improvements by @Tymec in #1477
  • Delete unused folder /outputs/ by @wnasich in #1130
  • refactoring all json utilities by @bingoko in #2032
  • Print the current Git branch on startup - warn if unsupported by @richbeales in #2494
  • Update README.md Windows run.bat instructions by @Explorergt92 in #2495
  • Fix Issue #1211 - gpt-3.5 chunk is less than the default by @itaihochman in #2324
  • fix: remove duplicate task complete command prompt by @zzzgydi in #2321
  • Update config.py fix: azure_model_to_deployment_id_map default type should be a dict, not list by @zvrr in #2351
  • Fix azure config by @yunzheng1112 in #2355
  • Don't install sorcery on docker by @mikekelly in https://github.com/Signific...

AutoGPT-0.2.1

@shaped1 在 #1476 中修复了 65 处 "gtp" 而不是 "GPT" 的错别字。
@BillSchumacher 在 #1537 中重新组织代码。
@chyezh 在 #801 中启用了 Milvus 作为内存后端。
@merwanehamadi 在 #1202 中添加了集成测试的特性/设置。
@suensummit 在 #1269 中清理了 env.template 中的 Azure 参数并删除了 config.py 中未使用的 env。
@JuroOravec 在 #1304 中更新了 README,解释了 OpenAI API 密钥的计费方式(解决了“API 速率限制已达到,等待 20 秒...在 5 次重试后未能获得响应”问题)。
@jedak1ah 在 #1381 中修复了当 Google 搜索结果包含奇怪字符时出现的错误。
@merwanehamadi 在 #1417 中将默认温度设置为 0。
@droosma 在 #1525 中更新了 docker-compose.yml。
@shaiss 在 #1528 中修正了目录中的错别字。
@pitmonticone 在 #1558 中修正了错别字。
@drikusroor 在 #1567 中为 token_counter 编写了单元测试。
@cryptidv 在 #1572 中使使用 Selenium 浏览器进行浏览更加通用。
@bufo24 在 #1579 中从 Docker 构建中移除了 sourcery。
@youkaichao 在 #1580 中更新了类型注释。
@nicostubi 在 #1586 中添加了一些要忽略的文件扩展名。

查看详细

  • Fix all 65 typos of it being gtp instead of GPT by @shaped1 in #1476
  • Reorg by @BillSchumacher in #1537
  • enable milvus as memory backend by @chyezh in #801
  • Feature/setup integration tests by @merwanehamadi in #1202
  • Cleanup azure parameters in env.template and remove unused env in config.py by @suensummit in #1269
  • README: Explain OpenAI billing for API key (Fixes issue about "API Rate Limit Reached. Waiting 20 seconds ... Failed to get response after 5 retries") by @JuroOravec in #1304
  • Fixed error when google results might have weird characters by @jedak1ah in #1381
  • make 0 the default temperature by @merwanehamadi in #1417
  • Update docker-compose.yml by @droosma in #1525
  • typo in TOC by @shaiss in #1528
  • Fix typo by @pitmonticone in #1558
  • test: Write unit tests for token_counter by @drikusroor in #1567
  • Make browsing with Selenium Browser Agnostic by @cryptidv in #1572
  • remove sourcery from docker build by @bufo24 in #1579
  • update type annotation by @youkaichao in #1580
  • Some more file extensions to ignore by @nicostubi in #1586
  • Fixed the import by @twajothi in #1590
  • Update README.md by @eltociear in #1623
  • Add ability to use local embeddings model by @Tymec in #1320
  • command clone github repository by @edcohen08 in #1229
  • Only add execute shell scripts to prompt if AI is allowed to do it. by @richbeales in #1551
  • Create a list of synonyms for commands for when the AI hallucinates by @richbeales in #1526
  • Adjust test_prompt_generator and add test report generation by @younessZMZ in #1609
  • [1607] Sourcery is detecting linting issues in autogpt/json_fixes/aut… by @adityaoke in #1610
  • Adjust test_config file by @younessZMZ in #1618
  • Fix for 'requires string as left operand, not PosixPath' by @alexonab in #1625
  • Fix agent key error by @jacobtohahn in #1507
  • Easy run with bat file (with requirements check and install if needed) by @DenTheProgrammer in #870
  • Remove please from prompts by @hdkiller in #1489
  • Fix list_agents to return string instead of JSON object by @gersh in #1471
  • Error notation in the split_file function in file_operations.py by @yueliu1999 in #1637
  • [doc] Improvements: Tutorials and Explanation by @Ding3LI in #1603
  • Revert "Add ability to use local embeddings model" by @richbeales in #1662
  • Fix invalid config import in git_operations by @richbeales in #1657
  • Update requirements.txt by @p-i- in #1676
  • Fix Milvus as a long-term memory backend. by @wangxuqi in #1658
  • Fix typo in .env.template by @CatMe0w in #1659
  • Fix run.bat to use the new module by @nponeccop in #1678
  • Quality update by @BillSchumacher in #1694
  • Embedding Improvement by @Imccccc in #1635
  • Update README.md by @thisislvca in #1682
  • Update requirements.txt by @DJStompZone in #1690
  • in debug mode add a log about rate limit error by @Hyaxia in #1683
  • Update docs: Data ingestion script location by @EdgarBarrantes in #1518
  • Update README.md "ELEVENLABS_API_KEY" by @manskx in #1702
  • Merge #72 by @BillSchumacher in #1712
  • Fix JSON string escaping issue by @PhilipAD in #72
  • Improve extract_hyperlinks to honor base url by @mharris717 in #87
  • First draft at adding persistent memory via sqlite3 by @EricFedrowisch in #124
  • fixing tests to fit latest merges into master by @coditamar in #1722
  • Use playwright instead of requests for browse by @ryanmac in #96
  • twitter_send_tweets_command by @rihp in #1717
  • Update consistent code command style by @warmthsea in #1263
  • Transcribe audio using huggingface by @gucky92 in #1718
  • ElevenLabs Voice ID's by @Bentlybro in #1767
  • Show readme love by @Bentlybro in #1755
  • resolved tweepy not in requirements.txt by @kumayu0108 in #1791
  • add tweepy module by @Qinbf in #1779
  • Added packages necessary to run docker from terminal by @danmohad in #1763
  • Update README.md .env.template instructions by @Explorergt92 in #1794
  • Typo in prompt start - missing space resulted in joined words in the prompt by @Zorinik in #1730
  • Catch exception of repository clone by @yueliu1999 in #1798
  • Add missing clarifications and method usages by @Ding3LI in #1719
  • Fix update bracket_termination.py with f string by @alexonab in #1732
  • Added tests for create_chat_message and generate_context methods of the chat module by @OmriGM in #1700
  • File Logger that tracks changes to file operations to prevent looping by @CalCameron in #1436
  • README fix, update Table Of Contents, fix and better memory backend s… by @chyezh in #1787
  • Create Docker Image CI by @richbeales in #1796
  • Feature/weaviate memory by @cs0lar in #424
  • fix: add necessary space to the prompt by @zzzgydi in #1814
  • Create a Docker image on DockerHub on release to stable by @richbeales in #1817
  • Remove least relevant items from memory first by @farizrahman4u in #1825
  • Only add audio to text command to the prompt if model is set by @hdkiller in #1826
  • Fix google api fetch error by @ickma in #1793
  • updated contributing docs by @0xArty in #1833
  • Fix file logging infinite loop issue by @rocks6 in #1901
  • Fix README by @Flying-Durian-Cake in #1868
  • fix: config save and load path inconsistent by @zzzgydi in #1842
  • simply removing a duplicate "Milvus Setup" in the README.md by @Bentlybro in #1934
  • Consolidate and fix workspace resolution by @Pwuts in #1947
  • Fix .env.template documentation, incorrect default value for TEMPERATURE by @smendig in #1932
  • Improve bug report template by @Pwuts in #1904

AutoGPT-0.2.0

我们已经改变了Auto-GPT启动的方式,它现在被包裹在一个模块中,这将使我们在未来能更好地测试代码,并使其更易于维护和扩展。

注意:Auto-GPT(在此版本中)目前需要安装Chrome才能浏览网络。 还引入了其他依赖项-请重新运行pip install -r requirements.txt

Autogpt命名空间修复导入错误,由@merwanehamadi在#1380中完成;
基于Selenium实现的Web浏览,由@Void-n-Null在#1397中完成;
特性/预提交格式化程序,由@0xArty在#1393中完成;
由BillSchumacher在#1418中发出的Pi的消息;
修复了commands.py,由@merwanehamadi在#1426中完成;
添加了Selenium依赖项,由@merwanehamadi在#1432中完成;
修复了所有问题,由BillSchumacher在#1444中完成;
AI名称热修复,由BillSchumacher在#1452中完成;
将其合并到稳定版本0.2.0中,由@richbeales在#1478中完成。

查看详细

We have changed the way that Auto-GPT is launched, it is now wrapped in a module which will allow us better testing and make
the code more maintainable and extensible in the future.

Please see the updated README.md for instructions how to run this version.

NOTE: Auto-GPT (in this release) currently requires Chrome to be installed in order to browse the web.
Other dependencies have also been introduced - please re-run pip install -r requirements.txt

  • Autogpt namespace fix imports by @merwanehamadi in #1380
  • Implemented Selenium based web browsing. by @Void-n-Null in #1397
  • Feature/pre commit formatter by @0xArty in #1393
  • Pi's message. by @BillSchumacher in #1418
  • fix commands.py by @merwanehamadi in #1426
  • added selenium dependencies by @merwanehamadi in #1432
  • Fix everything by @BillSchumacher in #1444
  • AI name hotfix. by @BillSchumacher in #1452
  • Pulling into stable for version 0.2.0 by @richbeales in #1478

AutoGPT-0.1.0

2023年4月12日发布第一版本