andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-11 00:58:30 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into devin/1744196072-add-huggingface-provider

Browse Source
This commit is contained in:
Devin AI
2025-04-14 13:28:49 +00:00
parent c435cbc2ef 10edde100e
commit 772189f4f5
28 changed files with 246 additions and 317 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/docs.json
View File

@@ -76,9 +76,7 @@
"concepts/testing",
"concepts/cli",
"concepts/tools",
"concepts/event-listener",
"concepts/langchain-tools",
"concepts/llamaindex-tools"
"concepts/event-listener"
]
},
{
@@ -97,7 +95,9 @@
"how-to/kickoff-async",
"how-to/kickoff-for-each",
"how-to/replay-tasks-from-latest-crew-kickoff",
"how-to/conditional-tasks"
"how-to/conditional-tasks",
"how-to/langchain-tools",
"how-to/llamaindex-tools"
]
},
{
@@ -196,6 +196,11 @@
"anchor": "Community",
"href": "https://community.crewai.com",
"icon": "discourse"
},
{
"anchor": "Tutorials",
"href": "https://www.youtube.com/@crewAIInc",
"icon": "youtube"
}
]
}

4
docs/guides/flows/first-flow.mdx
View File

@@ -263,6 +263,7 @@ Let's create our flow in the `main.py` file:
```python
#!/usr/bin/env python
import json
import os
from typing import List, Dict
from pydantic import BaseModel, Field
from crewai import LLM
@@ -341,6 +342,9 @@ class GuideCreatorFlow(Flow[GuideCreatorState]):
outline_dict = json.loads(response)
self.state.guide_outline = GuideOutline(**outline_dict)
# Ensure output directory exists before saving
os.makedirs("output", exist_ok=True)
# Save the outline to a file
with open("output/guide_outline.json", "w") as f:
json.dump(outline_dict, f, indent=2)

15
docs/installation.mdx
View File

@@ -4,6 +4,21 @@ description: Get started with CrewAI - Install, configure, and build your first
icon: wrench
---
## Video Tutorial
Watch this video tutorial for a step-by-step demonstration of the installation process:
<iframe
width="100%"
height="400"
src="https://www.youtube.com/embed/-kSOTtYzgEw"
title="CrewAI Installation Guide"
frameborder="0"
style={{ borderRadius: '10px' }}
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
allowfullscreen
></iframe>
## Text Tutorial
<Note>
**Python Version Requirements**

4
docs/tools/weaviatevectorsearchtool.mdx
View File

@@ -25,7 +25,7 @@ uv add weaviate-client
To effectively use the `WeaviateVectorSearchTool`, follow these steps:
1. **Package Installation**: Confirm that the `crewai[tools]` and `weaviate-client` packages are installed in your Python environment.
2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/connect) for instructions.
2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/manage-clusters/connect) for instructions.
3. **API Keys**: Obtain your Weaviate cluster URL and API key.
4. **OpenAI API Key**: Ensure you have an OpenAI API key set in your environment variables as `OPENAI_API_KEY`.
@@ -161,4 +161,4 @@ rag_agent = Agent(
## Conclusion
The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches.
The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches.