andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:crewAIInc/crewAI into lorenze/agent-query-for-knowledge

Browse Source
This commit is contained in:
lorenzejay
2025-05-06 15:32:26 -07:00
parent eb9ae78158 cac06adc6c
commit bd61c52371
6 changed files with 58 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
docs/concepts/llms.mdx
View File

@@ -27,23 +27,19 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
</Card> </Card>
</CardGroup> </CardGroup>
## Setting Up Your LLM ## Setting up your LLM
There are three ways to configure LLMs in CrewAI. Choose the method that best fits your workflow: There are different places in CrewAI code where you can specify the model to use. Once you specify the model you are using, you will need to provide the configuration (like an API key) for each of the model providers you use. See the [provider configuration examples](#provider-configuration-examples) section for your provider.
<Tabs> <Tabs>
<Tab title="1. Environment Variables"> <Tab title="1. Environment Variables">
The simplest way to get started. Set these variables in your environment: The simplest way to get started. Set the model in your environment directly, through an `.env` file or in your app code. If you used `crewai create` to bootstrap your project, it will be set already.
```bash ```bash .env
# Required: Your API key for authentication MODEL=model-id # e.g. gpt-4o, gemini-2.0-flash, claude-3-sonnet-...
OPENAI_API_KEY=<your-api-key>
# Optional: Default model selection # Be sure to set your API keys here too. See the Provider
OPENAI_MODEL_NAME=gpt-4o-mini # Default if not set # section below.
# Optional: Organization ID (if applicable)
OPENAI_ORGANIZATION_ID=<your-org-id>
``` ```
<Warning> <Warning>
@@ -53,13 +49,13 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
<Tab title="2. YAML Configuration"> <Tab title="2. YAML Configuration">
Create a YAML file to define your agent configurations. This method is great for version control and team collaboration: Create a YAML file to define your agent configurations. This method is great for version control and team collaboration:
```yaml ```yaml agents.yaml {6}
researcher: researcher:
role: Research Specialist role: Research Specialist
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: provider/model-id # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
# (see provider configuration examples below for more) # (see provider configuration examples below for more)
``` ```
@@ -74,23 +70,23 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
<Tab title="3. Direct Code"> <Tab title="3. Direct Code">
For maximum flexibility, configure LLMs directly in your Python code: For maximum flexibility, configure LLMs directly in your Python code:
```python ```python {4,8}
from crewai import LLM from crewai import LLM
# Basic configuration # Basic configuration
llm = LLM(model="gpt-4") llm = LLM(model="model-id-here") # gpt-4o, gemini-2.0-flash, anthropic/claude...
# Advanced configuration with detailed parameters # Advanced configuration with detailed parameters
llm = LLM( llm = LLM(
model="gpt-4o-mini", model="model-id-here", # gpt-4o, gemini-2.0-flash, anthropic/claude...
temperature=0.7, # Higher for more creative outputs temperature=0.7, # Higher for more creative outputs
timeout=120, # Seconds to wait for response timeout=120, # Seconds to wait for response
max_tokens=4000, # Maximum length of response max_tokens=4000, # Maximum length of response
top_p=0.9, # Nucleus sampling parameter top_p=0.9, # Nucleus sampling parameter
frequency_penalty=0.1, # Reduce repetition frequency_penalty=0.1 , # Reduce repetition
presence_penalty=0.1, # Encourage topic diversity presence_penalty=0.1, # Encourage topic diversity
response_format={"type": "json"}, # For structured outputs response_format={"type": "json"}, # For structured outputs
seed=42 # For reproducible results seed=42 # For reproducible results
) )
``` ```
@@ -110,7 +106,6 @@ 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.
@@ -383,7 +378,7 @@ In this section, you'll find detailed examples that help you select, configure,
| microsoft/phi-3-medium-4k-instruct | 4,096 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. | | microsoft/phi-3-medium-4k-instruct | 4,096 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3-medium-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. | | microsoft/phi-3-medium-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3.5-mini-instruct | 128K tokens | Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments | | microsoft/phi-3.5-mini-instruct | 128K tokens | Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments |
| microsoft/phi-3.5-moe-instruct | 128K tokens | Advanced LLM based on Mixture of Experts architecure to deliver compute efficient content generation | | microsoft/phi-3.5-moe-instruct | 128K tokens | Advanced LLM based on Mixture of Experts architecture to deliver compute efficient content generation |
| microsoft/kosmos-2 | 1,024 tokens | Groundbreaking multimodal model designed to understand and reason about visual elements in images. | | microsoft/kosmos-2 | 1,024 tokens | Groundbreaking multimodal model designed to understand and reason about visual elements in images. |
| microsoft/phi-3-vision-128k-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. | | microsoft/phi-3-vision-128k-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
| microsoft/phi-3.5-vision-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. | | microsoft/phi-3.5-vision-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
@@ -407,19 +402,19 @@ In this section, you'll find detailed examples that help you select, configure,
</Accordion> </Accordion>
<Accordion title="Local NVIDIA NIM Deployed using WSL2"> <Accordion title="Local NVIDIA NIM Deployed using WSL2">
NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux). NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux).
This approach allows you to leverage your NVIDIA GPU for private, secure, and cost-effective AI inference without relying on cloud services. This approach allows you to leverage your NVIDIA GPU for private, secure, and cost-effective AI inference without relying on cloud services.
Perfect for development, testing, or production scenarios where data privacy or offline capabilities are required. Perfect for development, testing, or production scenarios where data privacy or offline capabilities are required.
Here is a step-by-step guide to setting up a local NVIDIA NIM model: Here is a step-by-step guide to setting up a local NVIDIA NIM model:
1. Follow installation instructions from [NVIDIA Website](https://docs.nvidia.com/nim/wsl2/latest/getting-started.html) 1. Follow installation instructions from [NVIDIA Website](https://docs.nvidia.com/nim/wsl2/latest/getting-started.html)
2. Install the local model. For Llama 3.1-8b follow [instructions](https://build.nvidia.com/meta/llama-3_1-8b-instruct/deploy) 2. Install the local model. For Llama 3.1-8b follow [instructions](https://build.nvidia.com/meta/llama-3_1-8b-instruct/deploy)
3. Configure your crewai local models: 3. Configure your crewai local models:
```python Code ```python Code
from crewai.llm import LLM from crewai.llm import LLM
@@ -441,7 +436,7 @@ In this section, you'll find detailed examples that help you select, configure,
config=self.agents_config['researcher'], # type: ignore[index] config=self.agents_config['researcher'], # type: ignore[index]
llm=local_nvidia_nim_llm llm=local_nvidia_nim_llm
) )
# ... # ...
``` ```
</Accordion> </Accordion>
@@ -637,19 +632,19 @@ CrewAI supports streaming responses from LLMs, allowing your application to rece
When streaming is enabled, responses are delivered in chunks as they're generated, creating a more responsive user experience. When streaming is enabled, responses are delivered in chunks as they're generated, creating a more responsive user experience.
</Tab> </Tab>
<Tab title="Event Handling"> <Tab title="Event Handling">
CrewAI emits events for each chunk received during streaming: CrewAI emits events for each chunk received during streaming:
```python ```python
from crewai import LLM from crewai import LLM
from crewai.utilities.events import EventHandler, LLMStreamChunkEvent from crewai.utilities.events import EventHandler, LLMStreamChunkEvent
class MyEventHandler(EventHandler): class MyEventHandler(EventHandler):
def on_llm_stream_chunk(self, event: LLMStreamChunkEvent): def on_llm_stream_chunk(self, event: LLMStreamChunkEvent):
# Process each chunk as it arrives # Process each chunk as it arrives
print(f"Received chunk: {event.chunk}") print(f"Received chunk: {event.chunk}")
# Register the event handler # Register the event handler
from crewai.utilities.events import crewai_event_bus from crewai.utilities.events import crewai_event_bus
crewai_event_bus.register_handler(MyEventHandler()) crewai_event_bus.register_handler(MyEventHandler())
@@ -785,7 +780,7 @@ 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 ```python
# Large context model # Large context model
llm = LLM(model="openai/gpt-4o") # 128K tokens llm = LLM(model="openai/gpt-4o") # 128K tokens

4
docs/installation.mdx
View File

@@ -71,6 +71,10 @@ If you haven't installed `uv` yet, follow **step 1** to quickly get it set up on
``` ```
</Warning> </Warning>
<Warning>
If you encounter the `chroma-hnswlib==0.7.6` build error (`fatal error C1083: Cannot open include file: 'float.h'`) on Windows, install (Visual Studio Build Tools)[https://visualstudio.microsoft.com/downloads/] with *Desktop development with C++*.
</Warning>
- To verify that `crewai` is installed, run: - To verify that `crewai` is installed, run:
```shell ```shell
uv tool list uv tool list

4
docs/tools/docxsearchtool.mdx
View File

@@ -22,7 +22,7 @@ streamlining the process of finding specific information within large document c
Install the crewai_tools package by running the following command in your terminal: Install the crewai_tools package by running the following command in your terminal:
```shell ```shell
pip install 'crewai[tools]' uv pip install docx2txt 'crewai[tools]'
``` ```
## Example ## Example
@@ -76,4 +76,4 @@ tool = DOCXSearchTool(
), ),
) )
) )
``` ```

20
docs/tools/ragtool.mdx
View File

@@ -143,12 +143,30 @@ config = {
"config": { "config": {
"model": "text-embedding-ada-002" "model": "text-embedding-ada-002"
} }
},
"vectordb": {
"provider": "elasticsearch",
"config": {
"collection_name": "my-collection",
"cloud_id": "deployment-name:xxxx",
"api_key": "your-key",
"verify_certs": False
}
},
"chunker": {
"chunk_size": 400,
"chunk_overlap": 100,
"length_function": "len",
"min_chunk_size": 0
} }
} }
rag_tool = RagTool(config=config, summarize=True) rag_tool = RagTool(config=config, summarize=True)
``` ```
## Conclusion The internal RAG tool utilizes the Embedchain adapter, allowing you to pass any configuration options that are supported by Embedchain.
You can refer to the [Embedchain documentation](https://docs.embedchain.ai/components/introduction) for details.
Make sure to review the configuration options available in the .yaml file.
## Conclusion
The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses. The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses.

2
src/crewai/cli/install_crew.py
View File

@@ -4,7 +4,7 @@ import click
# Be mindful about changing this. # Be mindful about changing this.
# on some enviorments we don't use this command but instead uv sync directly # on some environments we don't use this command but instead uv sync directly
# so if you expect this to support more things you will need to replicate it there # so if you expect this to support more things you will need to replicate it there
# ask @joaomdmoura if you are unsure # ask @joaomdmoura if you are unsure
def install_crew(proxy_options: list[str]) -> None: def install_crew(proxy_options: list[str]) -> None:

2
tests/cassettes/test_lite_agent_structured_output.yaml
View File

@@ -16,7 +16,7 @@ interactions:
answer MUST contain all the information requested in the following format: {\n \"summary\": answer MUST contain all the information requested in the following format: {\n \"summary\":
str,\n \"confidence\": int\n}\n\nIMPORTANT: Ensure the final output does not str,\n \"confidence\": int\n}\n\nIMPORTANT: Ensure the final output does not
include any code block markers like ```json or ```python."}, {"role": "user", include any code block markers like ```json or ```python."}, {"role": "user",
"content": "What is the population of Tokyo? Return your strucutred output in "content": "What is the population of Tokyo? Return your structured output in
JSON format with the following fields: summary, confidence"}], "model": "gpt-4o-mini", JSON format with the following fields: summary, confidence"}], "model": "gpt-4o-mini",
"stop": []}' "stop": []}'
headers: headers: