v0.2.1

This release is the first update since v0.2.0.

Headsup: the sample app AutoGen Assistant will be renamed as AutoGen Studio in future.

Highlights

• An initial version of AutoBuild for automatically building multi-agent systems.
• v0.1 features that are added back to the new client-based inference: teachable agent, cost calculation and summary, raise content filter error.
• Function Inception: Enable AutoGen agents to update/remove functions during conversations. - View Notebook
• Improvement to group chat: termination,
• Improvement to teachable agent: progress bar for learning.
• Improvement to retrieve chat: more informative warning.
• Improvement to gpt assistant agent: verbose flag for allowing more output to be printed.
• Improvement to testbed: utilize OPENAI_API_KEY; adding GAIA benchmark.
• Improvement to multimodal: generalize the data structure to incorporate gpt-4v message format.
• Improvement to the sample app (will be renamed as AutoGen Studio in future).
• Allow async human input.
• Temporary fix to the breaking change introduced by openai 1.3: limit openai dependency to <1.3.
• Improvement in test, documentation and website: Examples are moved to a standalone tab and a new tab Ecosystem is added.

Thanks to @LinxinS97 @JieyuZ2 @rickyloynd-microsoft @kevin666aa @elecnix @afourney @thinkall @IANTHEREAL @BeibinLi @ShobhitVishnoi30 @olaoluwasalami @hodgesmr @skzhang1 @cpacker @victordibia @joshkyh @PyroGenesis @axa99 @momuno and all the other contributors!

What's Changed

• Restore TeachableAgent tests by @rickyloynd-microsoft in #761
• Add links to newly added notebooks in the website #756 by @olaoluwasalami in #772
• how to register a rely function Issue-478 by @olaoluwasalami in #579
• Remove version condition to fix issue #775 by @thinkall in #777
• Update application figure by @qingyun-wu in #352
• add cost calculation to client by @kevin666aa in #769
• Progress bar for learn_from_user_feedback by @rickyloynd-microsoft in #776
• Quick fix for 765 by @afourney in #809
• Improve docstring of query_texts and search_string by @thinkall in #795
• GroupChat handle is_termination_msg by @afourney in #804
• Fix Langchain link in examples doc by @hodgesmr in #811
• Add a warning message if docs_path not explicitly set by @thinkall in #814
• Testbed folders by @afourney in #792
• Add ecosystem page for website by @skzhang1 in #803
• update about pyautogen 0.2 by @sonichi in #826
• Update Ecosystem.md (MemGPT + AutoGen integration) by @cpacker in #838
• Improvements to AutoGen Assistant by @victordibia in #828
• Enable defining new functions after agent creation by @elecnix in #285
• Add a Blog Post on the AutoGen Assistant by @victordibia in #834
• update the news for v0.2 release by @sonichi in #844
• fix citations by @qingyun-wu in #843
• improve ecosystem page by @qingyun-wu in #823
• Message "content" now supports both str and List in Agents by @BeibinLi in #713
• Register async human input handler by @ShobhitVishnoi30 in #794
• Add cost summary to client.py by @kevin666aa in #812
• Add examples by @qingyun-wu in #851
• Testing AutoBuild by @LinxinS97 in #846
• Fix blog title display error by @LinxinS97 in #855
• Minor grammar and wording issues by @qingyun-wu in #854
• AutoBuild blog refinement by @LinxinS97 in #856
• add a verbose flag to let gpt assistant print more log by @IANTHEREAL in #717
• Testbed can now read the OPENAI_API_KEY in addition to OAI_CONFIG_LIST by @afourney in #848
• fix 0.2 release tag link by @PyroGenesis in #872
• Clarifies the phrasing in notebook agent_hierarchy_flow_using_select_speaker by @joshkyh in #876
• Add details to AutoBuild's blog and fix test error. This PR is related to #846 by @LinxinS97 in #865
• corrected openai utils example by @axa99 in #869
• bump version to 0.2.1 by @sonichi in #867
• Adds the GAIA benchark to the Testbed. This PR depends on #792 by @afourney in #810
• Update position of registered custom generate_reply functions for contrib/ agents per PR #794 by @momuno in #871
• raise error for content_filter by @sonichi in #849

New Contributors

• @hodgesmr made their first contribution in #811
• @cpacker made their first contribution in #838
• @elecnix made their first contribution in #285
• @ShobhitVishnoi30 made their first contribution in #794
• @LinxinS97 made their first contribution in #846
• @PyroGenesis made their first contribution in #872
• @axa99 made their first contribution in #869
• @momuno made their first contribution in #871

Full Changelog: v0.2.0...v0.2.1

v0.2.0

This is a major release since v0.1.1, containing 13 minor releases (from v0.1.1 to v0.1.14) and 6 pre-releases (v0.2.0b1 to v0.2.0b6).

Highlights since v0.1.1

Breaking changes

• Switching to openai v1. Please read the migration guide.

New Features and Enhancements:

• GPT Assistants Support: Integration of GPTAssistantAgent leveraging OpenAI Assistant API for conversational capabilities and state management. https://microsoft.github.io/autogen/blog/2023/11/13/OAI-assistants
• Group Chat Enhancements: Richer speaker selector options and robustness improvements.
• Enhanced retrieve chat, such as rich text format and customized vector db or embedding function in RAG. https://microsoft.github.io/autogen/blog/2023/10/18/RetrieveChat
• AgentEval Framework: Introduction of AgentEval for assessing task utility in LLM-powered applications. https://microsoft.github.io/autogen/blog/2023/11/20/AgentEval
• CompressibleAgent for Long Conversations: Handling long conversations with an experimental CompressibleAgent. https://github.com/microsoft/autogen/blob/main/notebook/agentchat_compression.ipynb
• Streaming Support: Added experimental streaming capabilities.
• Async Execution and Human Input Handling: Enhanced async function execution and better handling of human input.
• Large Multimodal Models (GPT-4V) Support: Enhanced AgentChat capabilities with Large Multimodal Models integration. https://microsoft.github.io/autogen/blog/2023/11/06/LMM-Agent
• TeachableAgent: Introduction of TeachableAgent for persistent user teachings across chat boundaries. https://microsoft.github.io/autogen/blog/2023/10/26/TeachableAgent
• Enhanced Documentation and Developer Tools: Comprehensive updates to README, FAQs, and developer tools.
• AutoGen Assistant: Deployment of a sample web application for practical demonstration. https://github.com/microsoft/autogen/tree/main/samples/apps/autogen-assistant
• Demonstration of Agents using Langchain Tools: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_langchain.ipynb.

Fixes and Improvements:

• Bug Fixes: Resolved issues in caching, filter checking, and other minor bugs.
• Documentation Enhancements: Multiple improvements in documentation, including migration guides and useful tips.
• Model Compatibility and Stability: Enhancements in model compatibility and overall stability of the package.
• Code Execution: more robust code detection/match/extraction, bug fixes for windows and sample code improvements, shell language switch in Docker
• Improved Codebase Reliability: Updates and bug fixes for better codebase reliability.

Thanks to the 80 contributors along this 2-month journey!

What's Changed

• Extact_code can detect single-line code now by @BeibinLi in #2
• fix invalid link by @qingyun-wu in #20
• Improve RetrieveChat by @thinkall in #6
• Remove duplicated sentence by @danizord in #35
• Fix bug for windows and improve sample code by @sonichi in #38
• Fix typo in README.md by @eltociear in #37
• Improves clarity and fixes punctuation in README and Multi-agent documentation by @juanmacuevas in #40
• make retry_time configurable, add doc by @sonichi in #53
• Update no_update_context, fix upsert docs by @thinkall in #52
• Update README.md by @AlyrenN in #54
• retrieve_utils.py - Updated.py to have the ability to parse text from PDF Files by @AaronWard in #50
• Bump version to 0.1.5 by @thinkall in #60
• typing & docstr update by @sonichi in #59
• Updated readme.md : seprated AutoGen and EcoOptGen also removed bibtex by @priyansh4320 in #43
• expand faq by @sonichi in #66
• minor fix by @LittleLittleCloud in #31
• Fixed MD Issue (#71) by @hiftielabs in #72
• fix append_oai_message by @kevin666aa in #47
• enable openai workflow on fork branch by @LittleLittleCloud in #82
• bump version to 0.1.6 by @sonichi in #85
• spelling error by @shauryr in #84
• Format issue by @alhridoy in #69
• Replace the use of assert in non-test code by @cipherself in #80
• Bump postcss from 8.4.18 to 8.4.31 in /website by @dependabot in #93
• show github stars by @sonichi in #92
• Docs: fixed typos and grammar by @masterujjval in #94
• openai_utils.py - functionality for instantiating config_list with a .env file by @AaronWard in #68
• document about docker by @sonichi in #119
• docs: typo fixed by @lgersman in #129
• Fix broken link in README.md by @htcrefactor in #134
• fix doc typo by @HyperCodec in #123
• typo fixed by @SDcodehub in #127
• bump version to 0.1.7 by @sonichi in #141
• Title: Adjust shell language switch in execute_code for Docker usage by @mrauter1 in #139
• move citation before contributing by @manish7017 in #154
• add twitter account to website by @olaoluwasalami in #150
• Update num tokens from text by @thinkall in #149
• add twitter account to start page by @olaoluwasalami in #159
• Update termination logic to fix #117 by @thinkall in #155
• Added twitter link to the contributing section by @vidhula17 in #162
• fix: replace gpt-35-turbo in model name to gpt-3.5-turbo so the name … by @AllenJShi in #138
• Output a warning if the OAI_CONFIG_LIST file is not found. by @afourney in #174
• Warn if GroupChat is underpopulatd. by @afourney in #170
• Warn if use_docker evaluates to True but the python docker package is not available. by @afourney in #172
• bump version to 0.1.9 by @sonichi in #177
• Warn if oai.Completion is provided with an empty config_list by @afourney in #178
• Bump version to 0.1.10 by @thinkall in #181
• Add support to customized vectordb and embedding functions by @thinkall in #161
• Fix typo in agentchat_MathChat.ipynb by @eltociear in #191
• Make getting started a little easier by @wayliums in #180
• Fix edge cases extracting code when the message's content is None by @msaelices in #205
• Add md for faqs by @gagb in #194
• Fix typo in README.md by @creator0131 in #193
• Icons not centered in the "autogen_agentchat.png" by @Steellgold in #169
• Addresses issue #199 by @afourney in #200
• Improving logging in oai.completion to show token_count by @kevin666aa in #179
• Update Getting-Started.md by @javidjamae in #213
• Added comment about config_list in the README example #216 by @smty2018 in #218
• fix: be compatible with customizing model without all fields in the response by @jtsang4 in #222
• Update Installation.md-with detailed explanation on add a period or newline #219 by @05hiteshbansal in #231
• Spelling fixes. by @shruti222patel in #220
• Typo by @qingyun-wu in #234
• bump version to 0.1.11 by @sonichi in #242
• docstr updated for use_docker in execute_code by @Gourav2609 in #233
• document retrieve chat by @olaoluwasalami in #258
• Add a figure to autogen notebook #215 by @smty2018 in #246
• Langchain tool bridge (#262) by @sonichi in #263
• Add support to custom text spliter by @thinkall in #270
• Update FAQ.md, elaborate on how to customise docker image and pick 'python:3' to solve typical errors by @maxim-saplin in https://github.com/micro...

v0.2.0b6

Highlights

• Support files in GPTAssistants. Notebook: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_retrieval.ipynb
• Richer choice of speaker selector and robustness improvement in GroupChat.
• Support custom text formats and recursive in RAG.
• Fix bugs in caching and filter checking.
• Robustness improvement in code block extraction.
• Sample web application: https://github.com/microsoft/autogen/tree/main/samples/apps/autogen-assistant.
• Adding first version of AgentEval -- a framework for assessing task utility for LLM-powered applications. Blogpost: https://microsoft.github.io/autogen/blog/2023/11/20/AgentEval.

Thanks to @IANTHEREAL @thinkall @afourney @gagb @victordibia @julianakiseleva @Narabzad @DearVa and all the other contributors!

What's Changed

• Fix typos in my affiliation by @gagb in #667
• Update index.mdx with version number by @gagb in #670
• Issue-560 by @olaoluwasalami in #578
• Sets the umask before executing the task in Docker. by @afourney in #593
• Allows users to specify a different requirements.txt file to install … by @afourney in #671
• Addresses issue 635, relating to newlines in Windows. by @afourney in #678
• Added an 'auto' mode to last_n_messages by @afourney in #693
• fix assistant creating without file by @IANTHEREAL in #689
• Fix typos in website blog by @Hao-tian-Zheng in #696
• Add RAG gptassistant example notebook by @gagb in #694
• Fix some type annotations and edge cases by @s-cerevisiae in #572
• Makes select_speaker more robust by checking for mentions anywhere. by @afourney in #669
• update side bar by @skzhang1 in #702
• Update speaker selector in GroupChat and update some notebooks by @thinkall in #688
• Update FAQ.md with api_base vs base_url question by @gagb in #672
• Re-added completion logging when using older versions of Autogen. by @afourney in #701
• add relevant dependency to the oai test workflow by @qingyun-wu in #712
• bump version to 0.2.0b6 by @sonichi in #710
• fix typos in function helper text by @shresthasurav in #503
• Sample Web Application Built with AutoGen by @victordibia in #695
• Fixes cache issue from 703 and 679 by @afourney in #707
• Support custom text formats and recursive by @thinkall in #496
• Adding first version of AgentEval -- a framework for assessing task utility for LLM-powered applications by @julianakiseleva in #681
• improve CODE_BLOCK_PATTERN for a more robust code match by @DearVa in #571

New Contributors

• @Hao-tian-Zheng made their first contribution in #696
• @s-cerevisiae made their first contribution in #572
• @skzhang1 made their first contribution in #702
• @shresthasurav made their first contribution in #503
• @julianakiseleva made their first contribution in #681
• @DearVa made their first contribution in #571

Full Changelog: 0.2.0b5...v0.2.0b6

0.2.0b5

Highlights

🔥 Experimental GPTAssistantAgent, which leverages the OpenAI Assistant API for conversational capabilities in AutoGen. This agent is unique in its reliance on the OpenAI Assistant API for state management, differing from other agents using the Completion API.

• Blogpost: https://microsoft.github.io/autogen/blog/2023/11/13/OAI-assistants/
• Notebook 1: GPTAssistantAgent in a hello-world example: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_twoagents_basic.ipynb
• Notebook 2: GPTAssistantAgent using function call: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_function_call.ipynb
• Notebook 3: GPTAssistantAgent with code interpreter: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_code_interpreter.ipynb
• Notebook 4: GPTAssistantAgent in a group chat: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_groupchat.ipynb

🔥 Blogpost for EcoAssistant, which is designed to solve user queries more accurately and affordably using assistant hierarchy and solution demonstration.

Thanks to @IANTHEREAL @gagb @LeoLjl @kevin666aa @qingyun-wu @sonichi @JieyuZ2 and all the other contributors!

What's Changed

• Fix docstring of get_or_create by @thinkall in #583
• Refactor GPTAssistantAgent by @gagb in #632
• uncomment test_hierarchy_flow_using_select_speaker by @qingyun-wu in #640
• Add basic notebook for gptassistant by @gagb in #636
• Openai assistant function usage notebook by @IANTHEREAL in #639
• bump version by @sonichi in #645
• add EcoAssistant blog by @JieyuZ2 in #647
• Add code interpreter for GptAssistant Notebook. by @LeoLjl in #644
• Add openai_client as property and update notebook. by @LeoLjl in #654
• fix tag in EcoAssistant blog by @JieyuZ2 in #657
• Add agentchat_oai_assistant_groupchat.ipynb by @LeoLjl in #656
• Add blog post for open ai assistants by @gagb in #638
• add doc about openai assistants by @qingyun-wu in #659

New Contributors

• @LeoLjl made their first contribution in #644

Full Changelog: v0.2.0b4...0.2.0b5

v0.2.0b4

Highlights

• CompressibleAgent (experimental) can be used to handle long conversations. Notebook: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_compression.ipynb
• Introducing Experimental GPT Assistant Agent: https://github.com/microsoft/autogen/blob/main/autogen/agentchat/contrib/gpt_assistant_agent.py. More improvements are under way.
• Experimental streaming support is added.
• seed is renamed to cache_seed to be compatible with openai's seed parameter in chat completion. Migration guide is updated: https://microsoft.github.io/autogen/docs/Installation/#migration-guide-to-v02
• Better warnings and error handling for group chat.

Thanks to @IANTHEREAL @kevin666aa @Alvaromah and all the other contributors!

What's Changed

• seed -> cache_seed by @sonichi in #600
• Added link to the new notebook by @joshkyh in #594
• update return type of WolframAlphaAPIWrapper.run() by @1073710317 in #523
• news update by @sonichi in #609
• Add EcoAssistant to the research page by @JieyuZ2 in #612
• Add CompressibleAgent by @kevin666aa in #443
• add AutoGen paper info at the beginning of readme by @qingyun-wu in #621
• Update oai_completion.ipynb by @AndreasVolkmann in #623
• Added warnings for some GroupChat misconfigurations and selection errors by @afourney in #603
• Introducing Experimental GPT Assistant Agent in AutoGen by @IANTHEREAL in #616
• added twitter(X) banner + link to readme by @malikmmoaz in #615
• Enable streaming support for openai v1 by @Alvaromah in #597
• improve readme by @qingyun-wu in #630
• Handled possible unclear IndexError in ConversableAgent.last_message method by @jeezrick in #622
• Fix test error of compressible agent by @kevin666aa in #631

New Contributors

• @1073710317 made their first contribution in #523
• @JieyuZ2 made their first contribution in #612
• @AndreasVolkmann made their first contribution in #623
• @IANTHEREAL made their first contribution in #616
• @malikmmoaz made their first contribution in #615
• @Alvaromah made their first contribution in #597
• @jeezrick made their first contribution in #622

Full Changelog: v0.2.0b3...v0.2.0b4

v0.2.0b3

A quick release to switch to openai-python v1.1.1.
Thanks to @joshkyh for a new group chat notebook example with hierarchical flow: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_hierarchy_flow_using_select_speaker.ipynb

What's Changed

• update version of openai dependency by @sonichi in #588
• Notebook/hierarchy flow by @joshkyh in #482

New Contributors

• @joshkyh made their first contribution in #482

Full Changelog: v0.2.0b2...v0.2.0b3

v0.2.0b2

This is a beta release of v0.2.0b2.

Highlights

• Support for GPT-4V! Introduced Large Multimodal Models in AgentChat, enhancing capabilities and interactions within the platform. Blogpost: https://microsoft.github.io/autogen/blog/2023/11/06/LMM-Agent
• Improved codebase reliability with updates such as dict copying before modifications (fixing a bug for Azure OpenAI) and various typo fixes.
• Added support for unstructured data in retrieve chat (RAG).
• Expanded functionality with async support for better get_human_input handling.
• A new simple Testbed tool for Autogen processes.
• Enhanced developer tools and documentation, including new README and TRANSPARENCY_FAQS updates.

Thanks to all the testers for the v0.2 migration. Thanks to @BeibinLi @sonichi @AkariLan @vatsalya-vyas @gfggithubleet @gagb @thinkall @hung-ngm @afourney @AaadityaG @jasondotparse @bonadio @aayushchhabra1999 @qingyun-wu @eltociear @marcgreen and other contributors!

What's Changed

• Added a simple Testbed tool for repeatedly running templated Autogen scenarios with tightly-controlled initial conditions. by @afourney in #455
• Fix typo import autogen by @hung-ngm in #549
• Add support to unstructrued by @thinkall in #501
• Update TRANSPARENCY_FAQS.md by @gfggithubleet in #492
• Update README.md by @vatsalya-vyas in #507
• fix wrong 'Langchain Provided Tools as Functions' doc ref by @AkariLan in #495
• copy dicts before modifying by @sonichi in #551
• Large Multimodal Models in AgentChat by @BeibinLi in #554

New Contributors

• @hung-ngm made their first contribution in #549
• @gfggithubleet made their first contribution in #492
• @vatsalya-vyas made their first contribution in #507
• @AkariLan made their first contribution in #495

Full Changelog: v0.2.0b1...v0.2.0b2

v0.2.0b1

This is a beta release of v0.2.0.

Highlights

• Switching to openai v1. Please read the migration guide and report bugs.
• Support async function execution & get_human_input.
• Improvements in documentation and notebooks.

Thanks to all the reviewers for the v0.2 migration. Thanks to @aayushchhabra1999 @bonadio @marcgreen and other contributors!
 

What's Changed

• Update Installation.md by @gagb in #456
• Update FAQ with workaround for Issue #251 by @marcgreen in #405
• Fix typo in README.md by @eltociear in #481
• Fix/async function and tool execution by @aayushchhabra1999 in #87
• Adding async support to get_human_input by @bonadio in #466
• Added example .txt file for agentchat_langchain sample notebook by @jasondotparse in #373
• Fix : Typo by @AaadityaG in #506
• Dev/v0.2 by @sonichi in #393

New Contributors

• @marcgreen made their first contribution in #405
• @aayushchhabra1999 made their first contribution in #87
• @bonadio made their first contribution in #466
• @jasondotparse made their first contribution in #373
• @AaadityaG made their first contribution in #506

Full Changelog: v0.1.14...v0.2.0b1

v0.1.14

Highlights

• 👀Give vision to your agent: multimodal examples are added at https://github.com/microsoft/autogen/blob/main/notebook/agentchat_lmm_llava.ipynb.
• 📖TeachableAgent blogpost: https://microsoft.github.io/autogen/blog/2023/10/26/TeachableAgent.
• 🧵 Run a chat in a different thread/process: using thread safe timeout for code execution.
• 🪶 Qdrant vector store: A QdrantRetrieveUserProxyAgent is added in contrib/.
• 🚦 Support new version of chromadb in retrieve chat.
• 🧮 Token count utils.
• 🐋 Improve vscode extension setup in codespace.
• 📝 Many improvements in documentation, FAQ, useful tips, such as
  • how to prevent gpt-3.5 agents' appreciation loop
  • fixes in the langchain notebook
  • link to the roadmap
  • common issues in retrieve chat

Thanks to @BeibinLi @rickyloynd-microsoft @ragyabraham @Anush008 @thinkall @kevin666aa @shruti222patel @craigomatic @AaronWard and all the other contributors!

Headsup

v0.2 release is near the corner, and we'll switch to openai v1 in it. Please check for breaking changes in #393. We'll try to add as many features back as possible before the release. If you see any breaking changes that affect your work, please comment in the PR thread.

What's Changed

• Added Roadmap to Getting-Started.md by @Gourav2609 in #324
• Resolves Typo Correction #336 by @2good4hisowngood in #338
• Update README.md by @IshitaPathak in #321
• Updating Examples to follow new categorical structure. #273 by @rabbabansh in #327
• Fix grammar in agentchat_auto_feedback_from_code_execution.ipynb by @shruti222patel in #342
• Fix spellings in notebooks by @shruti222patel in #341
• Fix grammar and spelling in agentchat_chess.ipynb by @shruti222patel in #346
• Improve readability for agentchat_function_call.ipynb by @shruti222patel in #347
• Improve readability in agentchat_groupchat_research.ipynb by @shruti222patel in #350
• fix format issue by @qingyun-wu in #358
• Improve readability in oai_openai_utils.ipynb by @shruti222patel in #365
• Improve readability in oai_completion.ipynb by @shruti222patel in #364
• Fix grammar in agentchat_web_info.ipynb by @shruti222patel in #362
• Improve readability for agentchat_two_users.ipynb by @shruti222patel in #361
• Fix the grammar and spelling in agentchat_human_feedback.ipynb by @shruti222patel in #354
• Fix spelling and grammar in agentchat_langchain.ipynb by @shruti222patel in #355
• Fix grammar and spelling in agentchat_planning.ipynb by @shruti222patel in #356
• Fix grammar in agentchat_stream.ipynb by @shruti222patel in #357
• headsup about dependency change by @sonichi in #378
• Add link to OptiGuide #371 by @smty2018 in #376
• Update docs in RetrieveChat notebook and Installation by @thinkall in #379
• config list for test by @sonichi in #395
• Supporting MultiModal Models: an example with LLaVA Notebook by @BeibinLi in #286
• using thread safe timeout to allow code execution to be compatible wi… by @ragyabraham in #224
• Fix tmp dir not exists by @thinkall in #401
• feat: Qdrant vector store support by @Anush008 in #303
• [Blocking Issue] Add tests dependencies for qdrant and fix chromadb errors by @thinkall in #435
• TeachableAgent blog post by @rickyloynd-microsoft in #436
• Adds jupyter as a vscode extension, fix validation errors in devcontainer.json by @craigomatic in #433
• Update FAQ section in documentation by @AaronWard in #390
• Add token_count_util by @kevin666aa in #421
• spelling fix for math_user_proxy_agent.py by @codingdrone in #431
• bump version to 0.1.14 by @sonichi in #400

New Contributors

• @2good4hisowngood made their first contribution in #338
• @IshitaPathak made their first contribution in #321
• @rabbabansh made their first contribution in #327
• @ragyabraham made their first contribution in #224
• @Anush008 made their first contribution in #303
• @craigomatic made their first contribution in #433
• @codingdrone made their first contribution in #431

Full Changelog: v0.1.13...v0.1.14

v0.1.13

Highlights

A preliminary TeachableAgent is added to allow users to teach their assistant facts, preferences, and tasks unrelated to code generation. Example notebook: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teachability.ipynb

Conversational assistants based on LLMs can remember the current chat with the user, and can even demonstrate in-context learning of things that the user teaches the assistant during the chat. But these memories and learnings are lost once the chat is over, or when a single chat grows too long. In subsequent chats, the user is forced to repeat any necessary instructions over and over.

TeachableAgent addresses these limitations by persisting user teachings across chat boundaries in long-term memory (a vector database). Memory is saved to disk at the end of each chat, then loaded from disk at the start of the next. Instead of copying all of memory into the context window, which would eat up valuable space, individual memories (called memos) are retrieved into context as needed. This allows the user to teach frequently used facts, preferences and skills to the agent just once, and have the agent remember them in later chats.

This release also contains an update about openai models and pricing, and restricts the openai package dependency version. In v0.2 we will switch to openai>=1.

Thanks to @rickyloynd-microsoft @kevin666aa and all the other contributors!

What's Changed

• doc: Update FAQ.md by @haseeb-xd in #282
• Fix format and links in documentations by @thinkall in #310
• update openai models and pricing by @kevin666aa in #316
• guidance for contribution by @sonichi in #320
• TeachableAgent by @rickyloynd-microsoft in #278
• add downloads stats in readme by @sonichi in #334
• bump version to 0.1.13 by @sonichi in #333

New Contributors

• @haseeb-xd made their first contribution in #282
• @rickyloynd-microsoft made their first contribution in #278

Full Changelog: v0.1.12...v0.1.13