2024-05-21 20:53:55 +08:00
---
2025-03-03 15:42:39 +08:00
sidebar_position: 1
2024-05-21 20:53:55 +08:00
slug: /llm_api_key_setup
---
2024-10-30 16:56:55 +08:00
# Configure model API key
2024-05-21 20:53:55 +08:00
2024-10-30 16:56:55 +08:00
An API key is required for RAGFlow to interact with an online AI model. This guide provides information about setting your model API key in RAGFlow.
2024-05-21 20:53:55 +08:00
2024-10-30 16:56:55 +08:00
## Get model API key
2024-05-21 20:53:55 +08:00
2025-03-03 15:42:39 +08:00
RAGFlow supports most mainstream LLMs. Please refer to [Supported Models ](../../references/supported_models.mdx ) for a complete list of supported models. You will need to apply for your model API key online. Note that most LLM providers grant newly-created accounts trial credit, which will expire in a couple of months, or a promotional amount of free quota.
2024-05-21 20:53:55 +08:00
2024-06-11 13:52:27 +08:00
:::note
2024-10-30 19:40:39 +08:00
If you find your online LLM is not on the list, don't feel disheartened. The list is expanding, and you can [file a feature request ](https://github.com/infiniflow/ragflow/issues/new?assignees=&labels=feature+request&projects=&template=feature_request.yml&title=%5BFeature+Request%5D%3A+ ) with us! Alternatively, if you have customized or locally-deployed models, you can [bind them to RAGFlow using Ollama, Xinference, or LocalAI ](./deploy_local_llm.mdx ).
2024-06-11 13:52:27 +08:00
:::
2024-05-21 20:53:55 +08:00
2024-10-30 16:56:55 +08:00
## Configure model API key
2024-05-21 20:53:55 +08:00
2024-10-30 16:56:55 +08:00
You have two options for configuring your model API key:
2024-05-21 20:53:55 +08:00
2024-11-12 15:56:53 +01:00
- Configure it in **service_conf.yaml.template** before starting RAGFlow.
2024-12-07 11:04:36 +08:00
- Configure it on the **Model providers** page after logging into RAGFlow.
2024-05-21 20:53:55 +08:00
2024-10-30 16:56:55 +08:00
### Configure model API key before starting up RAGFlow
2024-06-11 13:52:27 +08:00
1. Navigate to ** ./docker/ragflow**.
2. Find entry **user_default_llm** :
- Update `factory` with your chosen LLM.
- Update `api_key` with yours.
- Update `base_url` if you use a proxy to connect to the remote service.
3. Reboot your system for your changes to take effect.
2025-03-21 16:50:20 +08:00
4. Log into RAGFlow.
2025-03-03 15:42:39 +08:00
_After logging into RAGFlow, you will find your chosen model appears under **Added models** on the **Model providers** page._
2024-06-11 13:52:27 +08:00
2024-10-30 16:56:55 +08:00
### Configure model API key after logging into RAGFlow
2024-06-11 13:52:27 +08:00
:::caution WARNING
2024-11-12 15:56:53 +01:00
After logging into RAGFlow, configuring your model API key through the **service_conf.yaml.template** file will no longer take effect.
2024-06-11 13:52:27 +08:00
:::
2024-12-07 11:04:36 +08:00
After logging into RAGFlow, you can *only* configure API Key on the **Model providers** page:
2024-06-11 13:52:27 +08:00
2024-12-07 11:04:36 +08:00
1. Click on your logo on the top right of the page ** >** **Model providers** .
2024-06-11 13:52:27 +08:00
2. Find your model card under **Models to be added** and click **Add the model** :

2024-10-30 16:56:55 +08:00
3. Paste your model API key.
2024-06-11 13:52:27 +08:00
4. Fill in your base URL if you use a proxy to connect to the remote service.
2024-06-11 18:42:58 +08:00
5. Click **OK** to confirm your changes.
2024-06-11 13:52:27 +08:00
:::note
2025-05-22 17:02:23 +08:00
To update an existing model API key:
2024-06-11 13:52:27 +08:00

:::