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

better docs

Browse Source
This commit is contained in:
Lorenze Jay
2024-11-20 13:31:13 -08:00
parent 23276cbd76
commit 3c4504bd4f
1 changed files with 4 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/concepts/knowledge.mdx
View File

@@ -16,7 +16,7 @@ Additionally, we have specific tools for generate knowledge sources for strings,
Here's a simple example of how to use the Knowledge class:
```python
from crewai import Agent, Task, Crew, Knowledge, Process, LLM
from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
# Create a knowledge source
@@ -25,8 +25,7 @@ string_source = StringKnowledgeSource(
content=content, metadata={"preference": "personal"}
)
# Create a knowledge store with a list of sources and metadata
knowledge = Knowledge(sources=[string_source], metadata={"preference": "personal"})
llm = LLM(model="gpt-4o-mini", temperature=0)
# Create an agent with the knowledge store
agent = Agent(
@@ -48,7 +47,7 @@ crew = Crew(
tasks=[task],
verbose=True,
process=Process.sequential,
knowledge=True, # Enable knowledge
knowledge={"sources": [string_source], "metadata": {"preference": "personal"}}, # Enable knowledge by adding the sources here
)
result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
@@ -60,7 +59,6 @@ If you had sources from previous runs, you no longer need to declare the knowled
```python
from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
# Create a knowledge store with a list of sources and metadata
llm = LLM(model="gpt-4o-mini", temperature=0)
@@ -84,7 +82,7 @@ crew = Crew(
tasks=[task],
verbose=True,
process=Process.sequential,
knowledge=True, # Enable knowledge
knowledge={"sources": [string_source], "metadata": {"preference": "personal"}}, # Enable knowledge by adding the sources here
)
result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})