A programming framework for agentic AI
pre-commit version update and a few spelling fixes (#2913)
Davor Runjea0787aced3f1
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yamlindex 8f2521cbd..c9a4405ac 100644--- a/.pre-commit-config.yaml+++ b/.pre-commit-config.yaml@@ -8,7 +8,7 @@ ci:repos:- repo: https://github.com/pre-commit/pre-commit-hooks- rev: v4.5.0+ rev: v4.6.0hooks:- id: check-added-large-files- id: check-ast@@ -23,21 +23,21 @@ repos:- id: end-of-file-fixer- id: no-commit-to-branch- repo: https://github.com/psf/black- rev: 24.3.0+ rev: 24.4.2hooks:- id: black- repo: https://github.com/astral-sh/ruff-pre-commit- rev: v0.3.4+ rev: v0.4.8hooks:- id: rufftypes_or: [ python, pyi, jupyter ]args: ["--fix", "--ignore=E402"]exclude: notebook/agentchat_databricks_dbrx.ipynb- repo: https://github.com/codespell-project/codespell- rev: v2.2.6+ rev: v2.3.0hooks:- id: codespell- args: ["-L", "ans,linar,nam,tread,ot,"]+ args: ["-L", "ans,linar,nam,tread,ot,assertIn,dependin,socio-economic"]exclude: |(?x)^(pyproject.toml |diff --git a/autogen/oai/gemini.py b/autogen/oai/gemini.pyindex 60a2062bb..54a5c85d3 100644--- a/autogen/oai/gemini.py+++ b/autogen/oai/gemini.py@@ -151,7 +151,7 @@ class GeminiClient:if not model_name:raise ValueError("Please provide a model name for the Gemini Client. "- "You can configurate it in the OAI Config List file. "+ "You can configure it in the OAI Config List file. ""See this [LLM configuration tutorial](https://microsoft.github.io/autogen/docs/topics/llm_configuration/) for more details.")diff --git a/notebook/agentchat_groupchat_stateflow.ipynb b/notebook/agentchat_groupchat_stateflow.ipynbindex b8810d2fb..53eb0f2ff 100644--- a/notebook/agentchat_groupchat_stateflow.ipynb+++ b/notebook/agentchat_groupchat_stateflow.ipynb@@ -74,7 +74,7 @@"- Scientist: Read the papers and write a summary.\n","\n","\n",- "In the Figure, we define a simple workflow for research with 4 states: Init, Retrieve, Reserach and End. Within each state, we will call different agents to perform the tasks.\n",+ "In the Figure, we define a simple workflow for research with 4 states: Init, Retrieve, Research and End. Within each state, we will call different agents to perform the tasks.\n","- Init: We use the initializer to start the workflow.\n","- Retrieve: We will first call the coder to write code and then call the executor to execute the code.\n","- Research: We will call the scientist to read the papers and write a summary.\n",diff --git a/test/oai/_test_completion.py b/test/oai/_test_completion.pyindex 05798911c..fe410255d 100755--- a/test/oai/_test_completion.py+++ b/test/oai/_test_completion.py@@ -4,7 +4,6 @@ import jsonimport osimport sysfrom functools import partial-from test.oai.test_utils import KEY_LOC, OAI_CONFIG_LISTimport datasetsimport numpy as np@@ -18,6 +17,7 @@ from autogen.code_utils import (implement,)from autogen.math_utils import eval_math_responses, solve_problem+from test.oai.test_utils import KEY_LOC, OAI_CONFIG_LISThere = os.path.abspath(os.path.dirname(__file__))diff --git a/website/blog/2024-01-23-Code-execution-in-docker/index.mdx b/website/blog/2024-01-23-Code-execution-in-docker/index.mdxindex 067f16210..f729e37a1 100644--- a/website/blog/2024-01-23-Code-execution-in-docker/index.mdx+++ b/website/blog/2024-01-23-Code-execution-in-docker/index.mdx@@ -33,7 +33,7 @@ user_proxy.initiate_chat(assistant, message="Plot a chart of NVDA and TESLA stocTo opt out of from this default behaviour there are some options.-### Diasable code execution entirely+### Disable code execution entirely- Set `code_execution_config` to `False` for each code-execution agent. E.g.:diff --git a/website/blog/2024-02-29-StateFlow/index.mdx b/website/blog/2024-02-29-StateFlow/index.mdxindex 173344002..c4fff5313 100644--- a/website/blog/2024-02-29-StateFlow/index.mdx+++ b/website/blog/2024-02-29-StateFlow/index.mdx@@ -102,7 +102,7 @@ scientist = autogen.AssistantAgent()```-In the Figure, we define a simple workflow for research with 4 states: Init, Retrieve, Reserach, and End. Within each state, we will call different agents to perform the tasks.+In the Figure, we define a simple workflow for research with 4 states: Init, Retrieve, Research, and End. Within each state, we will call different agents to perform the tasks.- Init: We use the initializer to start the workflow.- Retrieve: We will first call the coder to write code and then call the executor to execute the code.- Research: We will call the scientist to read the papers and write a summary.diff --git a/website/blog/2024-05-24-Agent/index.mdx b/website/blog/2024-05-24-Agent/index.mdxindex 520805dc6..25fa0d937 100644--- a/website/blog/2024-05-24-Agent/index.mdx+++ b/website/blog/2024-05-24-Agent/index.mdx@@ -141,7 +141,7 @@ better with low cost. [EcoAssistant](/blog/2023/11/09/EcoAssistant) is a good ex- [AutoDefense](/blog/2024/03/11/AutoDefense/Defending%20LLMs%20Against%20Jailbreak%20Attacks%20with%20AutoDefense) demonstrates that using multi-agents reduces the risk of suffering from jailbreak attacks.-There are certainly tradeoffs to make. The large design space of multi-agents offers these tradeoffs and opens up new opportunites for optimization.+There are certainly tradeoffs to make. The large design space of multi-agents offers these tradeoffs and opens up new opportunities for optimization.> Over a year since the debut of Ask AT&T, the generative AI platform to which we’ve onboarded over 80,000 users, AT&T has been enhancing its capabilities by incorporating 'AI Agents'. These agents, powered by the Autogen framework pioneered by Microsoft (https://microsoft.github.io/autogen/blog/2023/12/01/AutoGenStudio/), are designed to tackle complicated workflows and tasks that traditional language models find challenging. To drive collaboration, AT&T is contributing back to the open-source project by introducing features that facilitate enhanced security and role-based access for various projects and data.>