Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
docs: improve formatting and clarity in CLI and Composio Tool docs (#1946)
Tony Kipkemboic642ebf97e4a
diff --git a/docs/concepts/cli.mdx b/docs/concepts/cli.mdxindex 19482e428..4c9f617ba 100644--- a/docs/concepts/cli.mdx+++ b/docs/concepts/cli.mdx@@ -12,7 +12,7 @@ The CrewAI CLI provides a set of commands to interact with CrewAI, allowing youTo use the CrewAI CLI, make sure you have CrewAI installed:-```shell+```shell Terminalpip install crewai```@@ -20,7 +20,7 @@ pip install crewaiThe basic structure of a CrewAI CLI command is:-```shell+```shell Terminalcrewai [COMMAND] [OPTIONS] [ARGUMENTS]```@@ -30,7 +30,7 @@ crewai [COMMAND] [OPTIONS] [ARGUMENTS]Create a new crew or flow.-```shell+```shell Terminalcrewai create [OPTIONS] TYPE NAME```@@ -38,7 +38,7 @@ crewai create [OPTIONS] TYPE NAME- `NAME`: Name of the crew or flowExample:-```shell+```shell Terminalcrewai create crew my_new_crewcrewai create flow my_new_flow```@@ -47,14 +47,14 @@ crewai create flow my_new_flowShow the installed version of CrewAI.-```shell+```shell Terminalcrewai version [OPTIONS]```- `--tools`: (Optional) Show the installed version of CrewAI toolsExample:-```shell+```shell Terminalcrewai versioncrewai version --tools```@@ -63,7 +63,7 @@ crewai version --toolsTrain the crew for a specified number of iterations.-```shell+```shell Terminalcrewai train [OPTIONS]```@@ -71,7 +71,7 @@ crewai train [OPTIONS]- `-f, --filename TEXT`: Path to a custom file for training (default: "trained_agents_data.pkl")Example:-```shell+```shell Terminalcrewai train -n 10 -f my_training_data.pkl```@@ -79,14 +79,14 @@ crewai train -n 10 -f my_training_data.pklReplay the crew execution from a specific task.-```shell+```shell Terminalcrewai replay [OPTIONS]```- `-t, --task_id TEXT`: Replay the crew from this task ID, including all subsequent tasksExample:-```shell+```shell Terminalcrewai replay -t task_123456```@@ -94,7 +94,7 @@ crewai replay -t task_123456Retrieve your latest crew.kickoff() task outputs.-```shell+```shell Terminalcrewai log-tasks-outputs```@@ -102,7 +102,7 @@ crewai log-tasks-outputsReset the crew memories (long, short, entity, latest_crew_kickoff_outputs).-```shell+```shell Terminalcrewai reset-memories [OPTIONS]```@@ -113,7 +113,7 @@ crewai reset-memories [OPTIONS]- `-a, --all`: Reset ALL memoriesExample:-```shell+```shell Terminalcrewai reset-memories --long --shortcrewai reset-memories --all```@@ -122,7 +122,7 @@ crewai reset-memories --allTest the crew and evaluate the results.-```shell+```shell Terminalcrewai test [OPTIONS]```@@ -130,7 +130,7 @@ crewai test [OPTIONS]- `-m, --model TEXT`: LLM Model to run the tests on the Crew (default: "gpt-4o-mini")Example:-```shell+```shell Terminalcrewai test -n 5 -m gpt-3.5-turbo```@@ -138,7 +138,7 @@ crewai test -n 5 -m gpt-3.5-turboRun the crew.-```shell+```shell Terminalcrewai run```<Note>@@ -153,7 +153,7 @@ Starting in version `0.98.0`, when you run the `crewai chat` command, you startAfter receiving the results, you can continue interacting with the assistant for further instructions or questions.-```shell+```shell Terminalcrewai chat```<Note>diff --git a/docs/installation.mdx b/docs/installation.mdxindex c98bce9ef..d629c4c80 100644--- a/docs/installation.mdx+++ b/docs/installation.mdx@@ -15,10 +15,48 @@ icon: wrenchIf you need to update Python, visit [python.org/downloads](https://python.org/downloads)</Note>+# Setting Up Your Environment++Before installing CrewAI, it's recommended to set up a virtual environment. This helps isolate your project dependencies and avoid conflicts.++<Steps>+ <Step title="Create a Virtual Environment">+ Choose your preferred method to create a virtual environment:++ **Using venv (Python's built-in tool):**+ ```shell Terminal+ python3 -m venv .venv+ ```++ **Using conda:**+ ```shell Terminal+ conda create -n crewai-env python=3.12+ ```+ </Step>++ <Step title="Activate the Virtual Environment">+ Activate your virtual environment based on your platform:++ **On macOS/Linux (venv):**+ ```shell Terminal+ source .venv/bin/activate+ ```++ **On Windows (venv):**+ ```shell Terminal+ .venv\Scripts\activate+ ```++ **Using conda (all platforms):**+ ```shell Terminal+ conda activate crewai-env+ ```+ </Step>+</Steps>+# Installing CrewAI-CrewAI is a flexible and powerful AI framework that enables you to create and manage AI agents, tools, and tasks efficiently.-Let's get you set up! π+Now let's get you set up! π<Steps><Step title="Install CrewAI">@@ -72,9 +110,9 @@ Let's get you set up! π# Creating a New Project-<Info>+<Tip>We recommend using the YAML Template scaffolding for a structured approach to defining agents and tasks.-</Info>+</Tip><Steps><Step title="Generate Project Structure">@@ -101,10 +139,22 @@ Let's get you set up! πβ βββ __init__.pyβββ config/βββ agents.yaml+ βββ config.yamlβββ tasks.yaml```</Frame>- </Step>+ </Step>++ <Step title="Install Additional Tools">+ You can install additional tools using UV:+ ```shell Terminal+ uv add <tool-name>+ ```++ <Tip>+ UV is our preferred package manager as it's significantly faster than pip and provides better dependency resolution.+ </Tip>+ </Step><Step title="Customize Your Project">Your project will contain these essential files:diff --git a/docs/tools/composiotool.mdx b/docs/tools/composiotool.mdxindex 244a5b657..b72e09dcd 100644--- a/docs/tools/composiotool.mdx+++ b/docs/tools/composiotool.mdx@@ -1,5 +1,5 @@----title: Composio+title: Composio Tooldescription: Composio provides 250+ production-ready tools for AI agents with flexible authentication management.icon: gear-code---@@ -75,7 +75,8 @@ filtered_action_enums = toolset.find_actions_by_use_case()tools = toolset.get_tools(actions=filtered_action_enums)-```<Tip>Set `advanced` to True to get actions for complex use cases</Tip>+```+<Tip>Set `advanced` to True to get actions for complex use cases</Tip>- Using specific tools: