Commit Graph

10 Commits

Author SHA1 Message Date
Erik Peterson
857d26d101 Add OpenAI function call support (#4683)
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
2023-06-22 04:52:44 +02:00
Luke K (pr-0f3t)
eb2410ac6c Merge remote-tracking branch 'upstream/master' into Release-v0.4.1 2023-06-19 14:08:06 -04:00
merwanehamadi
a7f805604c Pass config everywhere in order to get rid of singleton (#4666)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-06-18 19:05:41 -07:00
Reinier van der Leer
9943c58fba Fix test_make_agent 2023-06-15 23:59:15 +02:00
Reinier van der Leer
244393e4ef Add fallback token limit in llm.utils.create_chat_completion 2023-06-15 23:11:52 +02:00
merwanehamadi
3525a4b6db Count tokens with tiktoken (#4704)
* Update OpenAI model info and remove duplicate modelsinfo.py (#4700)

* Update OpenAI model info and remove duplicate modelsinfo.py

* Fix max_tokens for gpt-4-0613

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Update count_message_tokens to support new OpenAI models

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Fix error message in count_message_tokens

---------

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Erik Peterson <e@eriklp.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
2023-06-15 09:09:59 -07:00
James Collins
6e6e7fcc9a Extract openai API calls and retry at lowest level (#3696)
* Extract open ai api calls and retry at lowest level

* Forgot a test

* Gotta fix my local docker config so I can let pre-commit hooks run, ugh

* fix: merge artiface

* Fix linting

* Update memory.vector.utils

* feat: make sure resp exists

* fix: raise error message if created

* feat: rename file

* fix: partial test fix

* fix: update comments

* fix: linting

* fix: remove broken test

* fix: require a model to exist

* fix: BaseError issue

* fix: runtime error

* Fix mock response in test_make_agent

* add 429 as errors to retry

---------

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-06-14 07:59:26 -07:00
merwanehamadi
e7c0d3330c Create cassette submodule (#4420)
* gfeat: specify directory of cassettes and automatically load them depending on module

fix: formatting for linter

test: commit newly generated cassettes to their respective folder

tests: update latest fixtures with master

fix: update .gitattributes with updated path to cassettes

fix: use cassettes from master instead of generating them myself

fix: update path in .gitattributes

fix: make sure to match default functionality by using test name for cassette directory

fix: actually add git submodule

ci: checkout git submodules in CI

ci: update git submodules separately to ensure it gets called

feat: add a hooks directory so we can update git submodules on post-checkout

feat: make sure we push the tests/cassettes submodule on merge into master

ci: remove unused code now that we are using git submodules to keep cassettes in sync

fix: simplify how we load the submodule and fix updating cassettes on merge to master

chore: remove echo of checkout hook, it's unneeded

ci: remove unneccesary step

* cassettes submodule

* cassettes submodule

* cassettes submodule

* cassettes submodule

* cassettes submodule

---------

Co-authored-by: Stefan Ayala <stefanayala3266@gmail.com>
2023-05-26 12:33:49 -07:00
Nicholas Tindle
acfd966aa4 Pass Configs to Commands and remove CFG = Config() in the commands/ folder (#4328)
* 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>
2023-05-26 08:39:25 -07:00
Reinier van der Leer
bfbe613960 Vector memory revamp (part 1: refactoring) (#4208)
Additional changes:

* Improve typing

* Modularize message history memory & fix/refactor lots of things

* Fix summarization

* Move memory relevance calculation to MemoryItem & improve test

* Fix import warnings in web_selenium.py

* Remove `memory_add` ghost command

* Implement overlap in `split_text`

* Move memory tests into subdirectory

* Remove deprecated `get_ada_embedding()` and helpers

* Fix used token calculation in `chat_with_ai`

* Replace Message TypedDict by dataclass

* Fix AgentManager singleton issues in tests

---------

Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
2023-05-25 20:31:11 +02:00