Refactoring

docs/source/en/_toctree.yml

@@ -131,8 +131,6 @@
  title: Notebooks with examples
  - local: community
  title: Community resources
- - local: custom_tools
- title: Custom Tools and Prompts
  - local: troubleshooting
  title: Troubleshoot
  - local: hf_quantizer

docs/source/en/main_classes/agent.md

@@ -28,30 +28,28 @@ contains the API docs for the underlying classes.
 
 ## Agents
 
-We provide three types of agents: [`HfAgent`] uses inference endpoints for opensource models, [`LocalAgent`] uses a model of your choice locally and [`OpenAiAgent`] uses OpenAI closed models.
+We provide two types of agents, based on the main [`Agent`] class:
+- [`CodeAgent`] acts in one shot, generating code to solve the task, then executes it at once.
+- [`ReactAgent`] acts step by step, each step consisting of one thought, then one tool call and execution. It has two classes:
+ - [`ReactJSONAgent`] writes its tool calls in JSON.
+ - [`ReactCodeAgent`] writes its tool calls in Python code.
 
-### HfAgent
 
-[[autodoc]] HfAgent
+### CodeAgent
 
-### LocalAgent
+[[autodoc]] CodeAgent
 
-[[autodoc]] LocalAgent
+### React agents
 
-### OpenAiAgent
+[[autodoc]] ReactAgent
 
-[[autodoc]] OpenAiAgent
+[[autodoc]] ReactJSONAgent
 
-### AzureOpenAiAgent
-
-[[autodoc]] AzureOpenAiAgent
+[[autodoc]] ReactCodeAgent
 
 ### Agent
 
 [[autodoc]] Agent
- - chat
- - run
- - prepare_for_new_chat
 
 ## Tools
 
@@ -94,12 +92,12 @@ These types have three specific purposes:
 
 ### AgentText
 
-[[autodoc]] transformers.tools.agent_types.AgentText
+[[autodoc]] transformers.agents.agent_types.AgentText
 
 ### AgentImage
 
-[[autodoc]] transformers.tools.agent_types.AgentImage
+[[autodoc]] transformers.agents.agent_types.AgentImage
 
 ### AgentAudio
 
-[[autodoc]] transformers.tools.agent_types.AgentAudio
+[[autodoc]] transformers.agents.agent_types.AgentAudio