 Eric Zhu
|
ec314c586c
|
feat: Add strict mode support to BaseTool, ToolSchema and FunctionTool (#5507)
Resolves #4447
For `openai` client's structured output support is through its beta
client, which requires the function JSON schema to be strict when in
structured output mode.
Reference:
https://platform.openai.com/docs/guides/function-calling#strict-mode
|
1 year ago |
 wistuba
|
7a772a2fcd
|
feat: add indictor for tool failure to FunctionExecutionResult (#5428)
Some LLMs recieve an explicit signal about tool use failures.
Closes #5273
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
|
1 year ago |
|
Eric Zhu
|
9a028acf9f
|
feat: enhance Gemini model support in OpenAI client and tests (#5461)
|
1 year ago |
 afourney
|
0b659de36d
|
Mitigates #5401 by optionally prepending names to messages. (#5448)
Mitigates #5401 by optionally prepending names to messages.
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
|
1 year ago |
|
Eric Zhu
|
569bc19769
|
feat: add gemini model families, enhance group chat selection for Gemini model and add tests (#5334)
Resolves #5322
|
1 year ago |
|
Eric Zhu
|
f656ff1e01
|
feat: Support R1 reasoning text in model create result; enhance API docs (#5262)
Resolves #5255
---------
Co-authored-by: afourney <adamfo@microsoft.com>
|
1 year ago |
|
Eric Zhu
|
44db2cc1fb
|
fix: handle non-string function arguments in tool calls and add corresponding warnings (#5260)
|
1 year ago |
|
Eric Zhu
|
b441d5b43a
|
fix: Enhance OpenAI client to handle additional stop reasons and improve tool call validation in tests to address empty tool_calls list. (#5223)
Resolves #5222
|
1 year ago |
|
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
|
1 year ago |
|
Eric Zhu
|
af420a83e2
|
fix: ensure proper handling of structured output in OpenAI client and improve test coverage for structured output (#5116)
|
1 year ago |
 Jack Gerrits
|
cb1633b501
|
feat!: Add support for model family specification (#4856)
* Add support for model family specification
* spelling mistake
* lint, etc
* fixes
|
1 year ago |
 Sachin Joglekar
|
3b4dd6e050
|
Support custom models with OpenAI client (#4808)
|
1 year ago |
 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>
|
1 year ago |
|
Jack Gerrits
|
218e84fd8e
|
Migrate remaining components (#4626)
|
1 year ago |
|
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
|
1 year ago |
|
Jack Gerrits
|
3022369eeb
|
Flatten core base and components (#4513)
* Flatten core base and components
* remove extra files
* dont export from deprecated locations
* format
* fmt
|
1 year ago |
|
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
|
1 year ago |
|
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>
|
1 year ago |
 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>
|
1 year ago |
|
Leonardo Pinheiro
|
38f62e1609
|
migrate models (#3848)
* migrate models
* Update python/packages/autogen-agentchat/src/autogen_agentchat/agents/_tool_use_assistant_agent.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* refactor missing imports
* ignore type check errors
* Update python/packages/autogen-ext/src/autogen_ext/models/_openai/_model_info.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* update packages index page
---------
Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
|
1 year ago |
