andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

docs: Update model reference in LLM configuration (#2267)

Browse Source 
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
This commit is contained in:
Matisse
2025-03-21 15:12:26 -04:00
committed by GitHub
parent 0a116202f0
commit bb3829a9ed
1 changed files with 18 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
docs/concepts/llms.mdx
View File

@@ -59,7 +59,7 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
goal: Conduct comprehensive research and analysis goal: Conduct comprehensive research and analysis
backstory: A dedicated research professional with years of experience backstory: A dedicated research professional with years of experience
verbose: true verbose: true
llm: openai/gpt-4o-mini # your model here llm: openai/gpt-4o-mini # your model here
# (see provider configuration examples below for more) # (see provider configuration examples below for more)
``` ```
@@ -111,7 +111,7 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
## Provider Configuration Examples ## Provider Configuration Examples
CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities. CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities.
In this section, you'll find detailed examples that help you select, configure, and optimize the LLM that best fits your project's needs. In this section, you'll find detailed examples that help you select, configure, and optimize the LLM that best fits your project's needs.
<AccordionGroup> <AccordionGroup>
@@ -121,7 +121,7 @@ In this section, you'll find detailed examples that help you select, configure,
```toml Code ```toml Code
# Required # Required
OPENAI_API_KEY=sk-... OPENAI_API_KEY=sk-...
# Optional # Optional
OPENAI_API_BASE=<custom-base-url> OPENAI_API_BASE=<custom-base-url>
OPENAI_ORGANIZATION=<your-org-id> OPENAI_ORGANIZATION=<your-org-id>
@@ -226,7 +226,7 @@ In this section, you'll find detailed examples that help you select, configure,
AZURE_API_KEY=<your-api-key> AZURE_API_KEY=<your-api-key>
AZURE_API_BASE=<your-resource-url> AZURE_API_BASE=<your-resource-url>
AZURE_API_VERSION=<api-version> AZURE_API_VERSION=<api-version>
# Optional # Optional
AZURE_AD_TOKEN=<your-azure-ad-token> AZURE_AD_TOKEN=<your-azure-ad-token>
AZURE_API_TYPE=<your-azure-api-type> AZURE_API_TYPE=<your-azure-api-type>
@@ -289,7 +289,7 @@ In this section, you'll find detailed examples that help you select, configure,
| Mistral 8x7B Instruct | Up to 32k tokens | An MOE LLM that follows instructions, completes requests, and generates creative text. | | Mistral 8x7B Instruct | Up to 32k tokens | An MOE LLM that follows instructions, completes requests, and generates creative text. |
</Accordion> </Accordion>
<Accordion title="Amazon SageMaker"> <Accordion title="Amazon SageMaker">
```toml Code ```toml Code
AWS_ACCESS_KEY_ID=<your-access-key> AWS_ACCESS_KEY_ID=<your-access-key>
@@ -474,7 +474,7 @@ In this section, you'll find detailed examples that help you select, configure,
WATSONX_URL=<your-url> WATSONX_URL=<your-url>
WATSONX_APIKEY=<your-apikey> WATSONX_APIKEY=<your-apikey>
WATSONX_PROJECT_ID=<your-project-id> WATSONX_PROJECT_ID=<your-project-id>
# Optional # Optional
WATSONX_TOKEN=<your-token> WATSONX_TOKEN=<your-token>
WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id> WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id>
@@ -491,7 +491,7 @@ In this section, you'll find detailed examples that help you select, configure,
<Accordion title="Ollama (Local LLMs)"> <Accordion title="Ollama (Local LLMs)">
1. Install Ollama: [ollama.ai](https://ollama.ai/) 1. Install Ollama: [ollama.ai](https://ollama.ai/)
2. Run a model: `ollama run llama2` 2. Run a model: `ollama run llama3`
3. Configure: 3. Configure:
```python Code ```python Code
@@ -600,7 +600,7 @@ In this section, you'll find detailed examples that help you select, configure,
```toml Code ```toml Code
OPENROUTER_API_KEY=<your-api-key> OPENROUTER_API_KEY=<your-api-key>
``` ```
Example usage in your CrewAI project: Example usage in your CrewAI project:
```python Code ```python Code
llm = LLM( llm = LLM(
@@ -723,7 +723,7 @@ Learn how to get the most out of your LLM configuration:
- Small tasks (up to 4K tokens): Standard models - Small tasks (up to 4K tokens): Standard models
- Medium tasks (between 4K-32K): Enhanced models - Medium tasks (between 4K-32K): Enhanced models
- Large tasks (over 32K): Large context models - Large tasks (over 32K): Large context models
```python ```python
# Configure model with appropriate settings # Configure model with appropriate settings
llm = LLM( llm = LLM(
@@ -760,11 +760,11 @@ Learn how to get the most out of your LLM configuration:
<Warning> <Warning>
Most authentication issues can be resolved by checking API key format and environment variable names. Most authentication issues can be resolved by checking API key format and environment variable names.
</Warning> </Warning>
```bash ```bash
# OpenAI # OpenAI
OPENAI_API_KEY=sk-... OPENAI_API_KEY=sk-...
# Anthropic # Anthropic
ANTHROPIC_API_KEY=sk-ant-... ANTHROPIC_API_KEY=sk-ant-...
``` ```
@@ -773,11 +773,11 @@ Learn how to get the most out of your LLM configuration:
<Check> <Check>
Always include the provider prefix in model names Always include the provider prefix in model names
</Check> </Check>
```python ```python
# Correct # Correct
llm = LLM(model="openai/gpt-4") llm = LLM(model="openai/gpt-4")
# Incorrect # Incorrect
llm = LLM(model="gpt-4") llm = LLM(model="gpt-4")
``` ```
@@ -786,5 +786,10 @@ Learn how to get the most out of your LLM configuration:
<Tip> <Tip>
Use larger context models for extensive tasks Use larger context models for extensive tasks
</Tip> </Tip>
```python
# Large context model
llm = LLM(model="openai/gpt-4o") # 128K tokens
```
</Tab> </Tab>
</Tabs> </Tabs>