Leonardo Pinheiro
3fe106621e
fix: update SK model adapter constructor ( #5150 )
...
* update constructor
* fix typing error
* revert/fix doc changes
* add unsaved changes
---------
Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
2025-01-23 14:53:39 +10:00
Eric Zhu
da1c2bf12e
fix: use tool_calls field to detect tool calls in OpenAI client; add integration tests for OpenAI and Gemini ( #5122 )
...
* fix: use tool_calls field to detect tool calls in OpenAI client
* Add unit tests for tool calling; and integration tests for openai and gemini
2025-01-21 09:06:19 -05:00
Eric Zhu
142e102ce8
fix: update gpt-4o model version to 2024-08-06 ( #5117 )
...
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
2025-01-20 21:15:04 +00:00
Eric Zhu
af420a83e2
fix: ensure proper handling of structured output in OpenAI client and improve test coverage for structured output ( #5116 )
2025-01-20 20:54:39 +00:00
Leonardo Pinheiro
918292f51e
Semantic kernel model adapter ( #4851 )
...
* initial sk model adapter implementation
* add sk tool module
* implement streaming and update tests
* update lock
* linting
* add semantic kernel extras
* add docstring and format
* update dependencies and format/lint
* add model info to sk constructor
* update uv.lock
* customize prompt settings
* update uv.lock
* add docs
* fix sk docstring linting
* update create docstrings
* fmt and improve tool docstring
* update sk tool docs
* coerce doc json serialization failure
---------
Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
2025-01-18 18:57:20 +10:00
Eric Zhu
ce20de9afb
fix: normalize finish reason in CreateResult response ( #5085 )
...
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2025-01-17 14:10:06 +00:00
Sachin Joglekar
8bd65c672f
Add ChatCompletionCache along with AbstractStore for caching completions ( #4924 )
...
* Add ChatCompletionCache along with AbstractStore for caching completions
* Addressing comments
* Improve interface for cachestore
* Improve documentation & revert protocol
* Make cache store typed, and improve docs
* remove unnecessary casts
2025-01-16 15:47:38 -08:00
Hankyeol Kyung
acb9117513
Update gpt-4o model version and add new model details ( #5056 )
...
feat: Update gpt-4o-2024-11-20 version and model pointer
- Add version information for gpt-4o-2024-11-20
- Update model pointer
Signed-off-by: Hankyeol Kyung <kghnkl0103@gmail.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: gagb <gagb@users.noreply.github.com>
2025-01-15 19:44:43 +00:00
Jacob Alber
ae98c9d764
feat: Change async input strategy ( #5060 )
2025-01-15 10:12:47 -05:00
Jack Gerrits
70f7e998d2
fix: Fix provider string for AzureTokenProvider ( #4992 )
...
Fix provider string for AzureTokenProvider
2025-01-13 20:40:33 +00:00
Jack Gerrits
c0082dd9cc
fix: Normalize openai client stop reason to make more robust ( #5027 )
...
* Normalize stop reason to make more robust
* format
* add unknown finish reason
2025-01-13 18:26:31 +00:00
Jack Gerrits
c2721ff65b
Update all versions to 0.4.0 ( #4941 )
...
* Update all versions to 0.4.0
* update redirect
* install with upgrade for agentchat
2025-01-09 15:29:54 -05:00
Griffin Bassman
0446ce924f
feat: Add o1-2024-12-17 model ( #4965 )
...
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2025-01-09 11:05:20 -08:00
afourney
7131dc945d
Added m1 cli package ( #4949 )
...
* Added m1 cli package
* update CI, install card, deprecations
* Update python/packages/magentic-one-cli/pyproject.toml
* fix mypy and pyright
* add package
* Suppress 'ResourceWarning: unclosed socket'
---------
Co-authored-by: Jack Gerrits
2025-01-08 14:05:08 -08:00
Jack Gerrits
7b10f0ad1b
Improve docs for model clients, add missing docs ( #4930 )
...
* Improve docs for model clients
* formatting
* Fix usage
---------
Co-authored-by: peterychang <49209570+peterychang@users.noreply.github.com>
2025-01-08 09:12:48 -05:00
Jack Gerrits
d4b406b78c
refactor!: Reduce dependencies of core, remove image from URL ( #4919 )
...
* Reduce dependencies of core
* Update lock
* add package to test deps
* Update lock
* aio console dep
* Update lock
2025-01-07 18:30:04 +00:00
Jack Gerrits
f4382f01c8
Log messages and response for LLMCall event ( #4910 )
...
* Log messages and response for LLMCall event
* Remove accidental change
* newline
2025-01-07 12:32:29 -05:00
Jack Gerrits
310564908b
fix!: Move azure auth provider to separate module ( #4912 )
...
* Move azure auth provider to separate module
* Update lock
* fix component gen
2025-01-07 12:21:50 -05:00
Jack Gerrits
fb1094d9c3
Update to dev13 ( #4862 )
2024-12-30 17:12:51 -05:00
Gerardo Moreno
0569689e6b
Fix BaseOpenAIChatCompletionClient token usage ( #4770 )
...
* Fix openai client token usage (#4769 )
* Include actual_usage in add_usage function
* Make sure result is assigned
* remove method
---------
Co-authored-by: Jack Gerrits <jack@jackgerrits.com>
2024-12-30 15:33:06 -05:00
Jack Gerrits
cb1633b501
feat!: Add support for model family specification ( #4856 )
...
* Add support for model family specification
* spelling mistake
* lint, etc
* fixes
2024-12-30 15:09:21 -05:00
Jack Gerrits
0b34211c1e
refactor!: Remove deprecations ( #4853 )
...
* Remove deprecations
* imports
2024-12-30 14:55:21 -05:00
Eric Zhu
d933b9ab5f
dev12 ( #4839 )
...
* dev12
2024-12-27 11:49:12 -08:00
Sachin Joglekar
d1dff316bc
Update pydantic version & fix mypy errors ( #4811 )
...
* Update pydantic version & fix mypy errors
* uv lock changes
* Update lock
* update lockfile
---------
Co-authored-by: Jack Gerrits <jack@jackgerrits.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-12-27 08:53:52 -05:00
Leonardo Pinheiro
9a2dbb4fba
Add * before keyword args for ChatCompletionClient ( #4822 )
...
add * before keyword args
Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-12-27 08:41:16 -05:00
Sachin Joglekar
3b4dd6e050
Support custom models with OpenAI client ( #4808 )
2024-12-24 13:04:23 -08:00
Jack Gerrits
2c76ff9fcc
More improvements for component config ( #4799 )
...
* More improvements for component config
* clean output
* working dir
* fix fstring
* key error
* remove mv
2024-12-23 18:29:23 -05:00
Jack Gerrits
90d6723685
Usability improvements to component config ( #4794 )
...
* Usability improvements to component config
* Implement model upgrade
2024-12-23 14:03:58 -05:00
Jack Gerrits
dda208f9b4
Add component config support ( #4757 )
...
* Add wip component impl
* finishing touches
* remove test file
* fix json usage
* Format
---------
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
2024-12-20 13:14:24 -05:00
Jack Gerrits
453fe0cafd
Replace single quotes with double quotes ( #4760 )
...
* Replace single quotes with double quotes
* Fix version
* formatting
2024-12-19 14:21:51 -05:00
Eric Zhu
6c1f638960
dev11 release ( #4642 )
...
* dev11 release
2024-12-10 08:28:48 -08:00
Jack Gerrits
c234e77617
Add deprecated alias for openai model clients ( #4641 )
...
Add alias for openai model clients
2024-12-10 08:03:42 -08:00
Leonardo Pinheiro
253fe216fd
Add models.openai and tools.langchain namespaces ( #4601 )
...
* add models.openai namespace
* refactor tools namespace
* update lock file
* revert pyproject changes
* update docs and add cast
* update ext models doc ref
* increase underline
* add reply models namespace
* update imports
* fix test
* linting
* fix missing conflicts
* revert pydantic changes
* rename to replay
* replay
* fix reply
* Fix test
* formatting
* example
---------
Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Jack Gerrits <jack@jackgerrits.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-12-09 19:18:09 -08:00
Jack Gerrits
218e84fd8e
Migrate remaining components ( #4626 )
2024-12-09 18:39:07 -08:00
Jack Gerrits
87011ae01b
Migrate model context and models modules out of components ( #4613 )
...
* Move model context out of components
* move models out of components
* rename docs file
2024-12-09 10:00:08 -08:00
Eric Zhu
8dac072658
Update references in docs ( #4590 )
...
* Update agent doc
* Remove outdated doc
* Update references
* Update readme
* Update readme
2024-12-06 01:59:28 -08:00
Eric Zhu
8707729da9
dev9 ( #4585 )
...
* dev9
2024-12-06 00:43:56 -08:00
Jack Gerrits
2b878763f8
Move grpc runtimes to ext, flatten application ( #4553 )
...
* Move grpc runtimes to ext, flatten application
* rename to grpc
* fmt
2024-12-04 16:23:20 -08:00
Jack Gerrits
3022369eeb
Flatten core base and components ( #4513 )
...
* Flatten core base and components
* remove extra files
* dont export from deprecated locations
* format
* fmt
2024-12-03 17:00:44 -08:00
Eric Zhu
f70869f236
update dev8 ( #4417 )
2024-11-27 14:39:31 -08:00
Eric Zhu
52790a8de7
o1 support for agent chat, and validate model capabilities ( #4397 )
2024-11-27 10:45:51 -08:00
Jack Gerrits
1a02e2ba4b
Update version to dev7 ( #4359 )
...
* Update version to dev7
* update other references
2024-11-25 14:09:41 -08:00
Jack Gerrits
6c8b656588
Fix examples in docstrings ( #4356 )
...
* Fix examples in docstrings
* formatting
* Update python/packages/autogen-ext/src/autogen_ext/models/_reply_chat_completion_client.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Update python/packages/autogen-ext/src/autogen_ext/models/_reply_chat_completion_client.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Update python/packages/autogen-ext/src/autogen_ext/agents/_openai_assistant_agent.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Update python/packages/autogen-ext/src/autogen_ext/agents/_openai_assistant_agent.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Update python/packages/autogen-ext/src/autogen_ext/models/_reply_chat_completion_client.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Update python/packages/autogen-ext/src/autogen_ext/models/_reply_chat_completion_client.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Formattinggp
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2024-11-25 16:07:45 -05:00
Jack Gerrits
b2ae4d1203
Add warnings for deprecated azure oai config changes ( #4317 )
...
* Add warnings for deprecated azure oai config changes
* Update docs and usages, simplify capabilities
2024-11-25 09:34:52 -08:00
Mohammad Mazraeh
341417e636
add tolerance for empty choices ( #4311 )
...
* add tolerance for empty choices
Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>
* address pr comments
Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>
* Update python/packages/autogen-ext/src/autogen_ext/models/_openai/_openai_client.py
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* Update python/packages/autogen-ext/src/autogen_ext/models/_openai/_openai_client.py
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* address pr comments
Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>
* Update python/packages/autogen-ext/src/autogen_ext/models/_openai/_openai_client.py
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* Update _openai_client.py
---------
Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-11-25 09:06:35 -05:00
Leonardo Pinheiro
ac53961bc8
Delete autogen-ext refactor deprecations ( #4305 )
...
* delete files and update dependencies
* add explicit config exports
* ignore mypy error on nb
---------
Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-11-22 11:29:39 -05:00
Eric Zhu
1bf5fbb67b
Add API docs for builtin clients ( #4232 )
...
* Add API docs for builtin clients
* Address feedbacks
---------
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
2024-11-17 21:33:33 -05:00
Mohammad Mazraeh
570471bed7
Add reply chat completion client ( #4096 )
...
* initial implementation of reply chat completion client
---------
Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2024-11-11 15:33:44 -05:00
Rohan Thacker
3c63f6f3ef
Corrected typo in get_capabilities in _model_info.py ( #4002 )
2024-10-30 13:39:45 -07:00
Anthony Uphof
87bd1de396
Fix: provide valid Prompt and Completion Token usage counts from create_stream ( #3972 )
...
* Fix: `create_stream` to return valid usage token counts
* documentation
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2024-10-29 16:20:03 -07:00