Further changes:
* remove `init` param from `get_memory()`, replace usages by `memory.clear()`
* make token length calculation optional in `MemoryItem.dump()`
* Correct and clean up JSON handling
* Use ast for message history too
* Lint
* Add comments explaining why we use literal_eval
* Add descriptions to llm_response_format schema
* Parse responses in code blocks
* Be more careful when parsing in code blocks
* Lint
* Fix issues with file reading and writing with Python code
* Change error message, use Workspace.get_path
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* feat: pass config to call_ai_functions in coimmands
* feat: config for read_audio_from_file
* feat: file operations cfg
NOTE: we replaced the CFG in the command enable with TRUE b/c not sure how to handle this yet
* feat: git command conversion
* feat: google search
* feat: image generation
* feat: extract cfg from browser commands
* feat: remove cfg from execute code commands
* fix: file operation related tests
* fix: linting
* fix: tests for read_audio
* fix: test error
* feat: update cassettes
* fix: linting
* fix: test typechecking
* fix: google_search errors if unexpected kw arg is passed
* fix: pass config param to google search test
* fix: agent commands were broken + cassettes
* fix: agent test
* feat: cassettes
* feat: enable/disable logic for commands
* fix: some commands threw errors
* feat: fix tests
* Add new cassettes
* Add new cassettes
* ci: trigger ci
* Update autogpt/commands/execute_code.py
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* fix prompt
* fix prompt + rebase
* add config remove useless imports
* put back CFG just for download file
* lint
* The signature should be mandatory in the decorator
* black isort
* fix: remove the CFG
* fix: non typed arg
* lint: type some args
* lint: add types for libraries
* Add new cassettes
* fix: windows compatibility
* fix: add config access to decorator
* fix: remove twitter mention
* DDGS search works at 3.0.2 version
* ci: linting
---------
Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: kinance <kinance@gmail.com>
* adding requiered packages for loading pdf, docx, md, tex files (preferably pure python packages)
* adding text file utils providing function to load file based on extension && adding read_text_file command
* adding test cases for text file loading (pdf file creation is hardcoded due to external package requierment for creation (a sample file can be added))
* formatting
* changing command name from 'read_text_file' to 'parse_text_document'
* fallback to txtParser if file extension is not known to read script and code files
* adding extension respective parsers
* adding binary file check function
* adding file existance check && raising valueError for unsupported binary file formats
* adding check file type (binary) in test_parsers for specific extensions && fixing mock pdf generation to include null bytes
* adding .yml extension parser
* removal of .doc parser
* updating file loading commands names
* updating test (removing .doc mock function)
* fix: import sort
* new cassette for mem A
* feat: update Cassettes
* feat: consolidate commands
* feat: linting
* feat: updates to cassettes
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
* * there is really no need to return the reference to the Selenium driver along with the text summary and list of links.
* * removing unused second return value from browse_website()
* * updated cassette
* * updated YAML cassette for test_browse_website
* * after requirements reinstall, another update YAML cassette for test_browse_website
* * another update YAML cassette for test_browse_website, only as a placholder commit to trigger re-testing due to some docker TCP timeout issue
* * another update YAML cassette for test_browse_website
---------
Co-authored-by: batyu <batyu@localhost>
* feat: move task_complete command out of prompt
* fix: formatting fixes
* Add the shutdown command to the test agents
* tests: update test vcrs
---------
Co-authored-by: James Collins <collijk@uw.edu>
Co-authored-by: James Collins <collijk@uw.edu>
Co-authored-by: Luke Kyohere <lkyohere@mfsafrica.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Media <12145726+rihp@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
* The unlooping and fixing of file execution.
* lint
* Use static random seed during testing. remove unused import.
* Fix bug
* Actually fix bug.
* lint
* Unloop a bit more an fix json.
* Fix another bug.
* lint.
---------
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
* Add workspace abstraction
* Remove old workspace implementation
* Extract path resolution to a helper function
* Add api key requirements to new tests
Reinier van der Leer
Erik Peterson
merwanehamadi
Benny van der Lans
k-boikov
Nicholas Tindle
Kinance
Robin Richtsfeld
sherif-med
WladBlank
Kory Becker
Boostrix
Abdelkarim Habouch
bszollosinagy
sidewaysthought
non-adjective
Bob
Richard Beales
Steven Baumann
James Collins
rickythefox
Irmius
Montana Flynn
BillSchumacher
Peter Svensson
Eddie Cohen