andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Update LLM-Connections.md (#796)

Browse Source 
Revised to utilize Ollama from langchain.llms instead as the functionality from the other method simply doesn't work when delegating.

Co-authored-by: João Moura <joaomdmoura@gmail.com>
This commit is contained in:
JoePro
2024-06-30 22:22:38 -05:00
committed by GitHub
parent c027aa8bf6
commit 1bca6029fe
1 changed files with 9 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
docs/how-to/LLM-Connections.md
View File

@@ -50,54 +50,24 @@ Ollama is preferred for local LLM integration, offering customization and privac
### Setting Up Ollama ### Setting Up Ollama
- **Environment Variables Configuration**: To integrate Ollama, set the following environment variables: - **Environment Variables Configuration**: To integrate Ollama, set the following environment variables:
```sh ```sh
OPENAI_API_BASE='http://localhost:11434/v1' OPENAI_API_BASE='http://localhost:11434'
OPENAI_MODEL_NAME='openhermes' # Adjust based on available model OPENAI_MODEL_NAME='llama2' # Adjust based on available model
OPENAI_API_KEY='' OPENAI_API_KEY=''
``` ```
## Ollama Integration (ex. for using Llama 2 locally) ## Ollama Integration (ex. for using Llama 2 locally)
1. [Download Ollama](https://ollama.com/download). 1. [Download Ollama](https://ollama.com/download).
2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```. 2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.
3. Create a ModelFile similar the one below in your project directory. 3. Enjoy your free Llama2 model that powered up by excellent agents from crewai.
``` ```
FROM llama2
# Set parameters
PARAMETER temperature 0.8
PARAMETER stop Result
# Sets a custom system message to specify the behavior of the chat assistant
# Leaving it blank for now.
SYSTEM """"""
```
4. Create a script to get the base model, which in our case is llama2, and create a model on top of that with ModelFile above. PS: this will be ".sh" file.
```
#!/bin/zsh
# variables
model_name="llama2"
custom_model_name="crewai-llama2"
#get the base model
ollama pull $model_name
#create the model file
ollama create $custom_model_name -f ./Llama2ModelFile
```
5. Go into the directory where the script file and ModelFile is located and run the script.
6. Enjoy your free Llama2 model that is powered up by excellent agents from CrewAI.
```python
from crewai import Agent, Task, Crew from crewai import Agent, Task, Crew
from langchain_openai import ChatOpenAI from langchain.llms import Ollama
import os import os
os.environ["OPENAI_API_KEY"] = "NA" os.environ["OPENAI_API_KEY"] = "NA"
llm = ChatOpenAI( llm = Ollama(
model = "crewai-llama2", model = "llama2",
base_url = "http://localhost:11434/v1") base_url = "http://localhost:11434")
general_agent = Agent(role = "Math Professor", general_agent = Agent(role = "Math Professor",
goal = """Provide the solution to the students that are asking mathematical questions and give them the answer.""", goal = """Provide the solution to the students that are asking mathematical questions and give them the answer.""",