Build and run agents you can see, understand and trust.
Python agentchatbotlarge-language-modelsllmllm-agentmcpmulti-agentmulti-modalreact-agentrealtime-agentvoice-agentvoice-assistant
Commits on main
fix(toolkit): fix meta tool failing to deactivate tool groups (#962)
5bc937a DavdGao committed 12 months ago
fix(plan): update the typing of `plan_change_hook` argument to support awaitables (#940)
a2bf80e lixiaofei123 committed 12 months ago
fix(model): unify `client_args` and `client_kwargs` arguments in the chat model classes into `client_kwargs` (#957)
d2fcea0 qbc committed 12 months ago
feat(agent-skill): support Anthropic agent skills in `ReActAgent` and `Toolkit` class (#952)
811c127 DavdGao committed 12 months ago
fix(docs): fix the incorrect port number in the tutorial (#954)
b56c4dd hulz committed 12 months ago
fix(formatter): implement image extraction from tool results (#938)
f5fdc37 qbc committed 12 months ago
fix(memory): fix the case when `Mem0LongTermMemory` uses graphstore (#942)
233915d Osier-Yi committed 12 months ago
fix(toolkit): merge $defs when extending tool function schema with nested models (#941)
873cfe2 qbc committed 1 year ago
refactor(config): support thread and async safe configuration by using `ContextVar` (#933)
9a6f452 zhijianma committed 1 year ago
feat(toolkit): support different strategies when registering duplicated tools in toolkit (#939)
d662bec DavdGao committed 1 year ago
fix(reme): fix the error when creating `ReMePersonalLongTermMemory` using `OpenAITextEmebdding` (#929)
c7266f6 清吾 committed 1 year ago
fix(tool): fix the bug of `execute_python_code` in Win by setting utf-8 environment (#916)
8299e1b Eric Shaw committed 1 year ago
feat(memory): add `limit` parameter in base `LongTermMemroyBase` class (#913)
04ece23 Osier-Yi committed 1 year ago
docs(reme): remove unnecessary Python version requirements (#924)
93938ee jinliyl committed 1 year ago
fix(agent): set `tool_choice` to "required" when requring structured output (#928)
f4c6b6f qbc committed 1 year ago
refactor(agent): refactor the structured output logic within the `ReActAgent` class (#910)
23fb3c8 qbc committed 1 year ago
fix(pipeline): use `Sequence` for covariant type substitution in MsgHub (#909)
51145a9 cccc committed 1 year ago
docs(README): update README.md and README_zh.md with update news (#899)
3ca8561 DavdGao committed 1 year ago
fix(plan, rag) fix the bug in the word reader and plan notebook class. (#895)
58a4858 DavdGao committed 1 year ago
feat(toolkit): support async func for the `postprocess_func` argument in toolkit (#885)
51b6b83 qbc committed 1 year ago
fix(example): handle the wrong input type of the `tool_names` parameter in the meta planner example (#870)
fd1335f qbc committed 1 year ago
docs(contributing): add CONTRIBUTING.md; adjust the example directories (#890)
073d16d DavdGao committed 1 year ago
feat(docs): refine github workflow to remove unnecessary files in git (#879)
c2c59e5 qbc committed 1 year ago
feat(rl): support RL training by adding a `tune` module in agentscope (#816)
9f018b6 Xuchen Pan committed 1 year ago
fix(agent): separate the logic of the arguments `enable_meta_tool` and `plan_notebook` (#880)
7f83c1e Zheng Dayu committed 1 year ago
fix(agent): raise the CancelError when interruption happens during the tool execution (#888)
34a8a30 DavdGao committed 1 year ago