We're excited to present the 0.4.3 maintenance release of Auto-GPT! This update primarily focuses on refining the LLM command execution, extending support for OpenAI's latest models (including the powerful GPT-3 16k model), and laying the groundwork for future compatibility with OpenAI's innovative function calling feature.
Release Highlights 🌟
- OpenAI API Key Prompt: Auto-GPT will now courteously prompt users for their OpenAI API key, if it's not already provided.
- Summarization Enhancements: We've optimized Auto-GPT's use of the LLM context window even further, boosting the effectiveness of summarization tasks.
- JSON Memory Reading: Support for reading memories from JSON files has been improved, resulting in enhanced task execution.
- New "replace_in_file" Command: This nifty new feature allows Auto-GPT to modify files without loading them entirely.
- Enhanced Token Counting: We've refined our token counting system to provide more precise cost estimates.
Deprecated Commands ❌
As part of our ongoing commitment to refining Auto-GPT, the following commands, which we determined to be either better suited as plugins or redundant, have been retired from the core application:
- analyze_code
- write_tests
- improve_code
- audio_text
- web_playwright
- web_requests
Progress Update on Re-Architecting 🚧
As you may recall, we recently embarked on a significant re-architecting journey to future-proof the Auto-GPT project. We're thrilled to report that elements of this massive overhaul are now being integrated back into the core application. For instance, you may notice less reliance on global state being passed around via singletons.
Stay tuned for further updates and advancements in our future releases! Head over to the discussion forums or discord to share your feedback on this release, and we appreciate your continued support.
New Contributors & Notable Catalysts 🦾
- @DrMurx made their first contribution in #2821
- @BorntraegerMarc made their first contribution in #1569
- @javableu made their first contribution in #4167
- @scenaristeur made their first contribution in #4561
- @Qoyyuum made their first contribution in #2486
What's Changed 📜
- Add
replace_in_filecommand to change occurrences of text in a file by @bfalans in #4565 - Update OpenAI model info and remove duplicate modelsinfo.py by @Pwuts in #4700
- Implement loading
MemoryItems from file inJSONFileMemoryby @Pwuts in #4703 - Count tokens with tiktoken by @merwanehamadi in #4704
- Refactor module layout of command classes by @erik-megarad in #4706
- Remove analyze code by @merwanehamadi in #4705
- Remove write_tests and improve_code by @merwanehamadi in #4707
- Remove app commands, audio text and playwright by @merwanehamadi in #4711
- Improve plugin backward compatibility by @lc0rp in #4716
- Fix summarization happening in first cycle by @merwanehamadi in #4719
- Bulletin.md update for 0.4.1 release by @lc0rp in #4721
- Use JSON format for commands signature by @merwanehamadi in #4714
- Fix execute_command coming from plugins in 0.4.1 by @erik-megarad in #4730
- Fix execute_command coming from plugins by @erik-megarad in #4729
- Pass config everywhere in order to get rid of singleton by @merwanehamadi in #4666
- Remove config from command decorator by @merwanehamadi in #4736
- Fix issues with execute_python_code responses by @erik-megarad in #4738
- Retry 503 OpenAI errors by @merwanehamadi in #4745
- Sync release v0.4.1 back into master by @lc0rp in #4741
- Merge Release v0.4.2 back to master by @merwanehamadi in #4747
- Remove config singleton by @merwanehamadi in #4737
- Make JSON errors more silent by @merwanehamadi in #4748
- Fix up Python execution commands by @Wladastic in #4756
- OpenAI Functions Support by @erik-megarad in #4683
- Create run_task python hook to interface with benchmarks by @merwanehamadi in #4778
- ❇️ Improved OpenAI API Key Insert to Env by @Qoyyuum in #2486
- Link all challenges to benchmark python hook by @merwanehamadi in #4786
- Prevent docker-compose.yml and Dockerfile from being written by @erik-megarad in #4761
- Only take subclasses of AutoGPTPluginTemplate as plugins by @ppetermann in #4345
- Filtering out ANSI escape codes in printed assistant thoughts by @lc0rp in #4812
- Unregister commands incompatible with current config. by @lc0rp in #4815
- Bulletin.md updates and version toggling by @lc0rp in #4816
- Release v0.4.3 by @lc0rp in #4802
Full Changelog: v0.4.2...v0.4.3