zhouhongbo
/
JZ_QGNB
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '93107afa10'
${ noResults }
JZ_QGNB/DigitalHumanWeb/docs/self-hosting/environment-variables/model-provider.mdx

483 lines
15 KiB
Markdown
Raw Blame History Unescape Escape

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

---
title: LobeChat Model Service Providers - Environment Variables and Configuration
description: >-
Learn about the environment variables and configuration settings for various
model service providers like OpenAI, Google AI, AWS Bedrock, Ollama,
Perplexity AI, Anthropic AI, Mistral AI, Groq AI, OpenRouter AI, and 01.AI.
tags:
- Model Service Providers
- Environment Variables
---
# Model Providers
When deploying LobeChat, a rich set of environment variables related to model service providers is provided, allowing you to easily define the model service providers to be enabled in LobeChat.
## OpenAI
### `ENABLED_OPENAI`
- Type：Optional
- Description：Enables OpenAI as a model provider by default, turns off the OpenAI service when set to `0`
- Default：`1`
- Example：`0`
### `OPENAI_API_KEY`
- Type: Required
- Description: This is the API key you applied for on the OpenAI account page, you can check it out [here](https://platform.openai.com/api-keys)
- Default: -
- Example: `sk-xxxxxx...xxxxxx`
### `OPENAI_PROXY_URL`
- Type: Optional
- Description: If you manually configure the OpenAI interface proxy, you can use this configuration item to override the default OpenAI API request base URL
- Default: `https://api.openai.com/v1`
- Example: `https://api.chatanywhere.cn` or `https://aihubmix.com/v1`
<Callout type={'warning'}>
Please check the request suffix of your proxy service provider. Some proxy service providers may
add `/v1` to the request suffix, while others may not. If you find that the AI returns an empty
message during testing, try adding the `/v1` suffix and retry.
</Callout>
<Callout type={'info'}>
Whether to fill in `/v1` is closely related to the model service provider. For example, the
default address of openai is `api.openai.com/v1`. If your proxy forwards the `/v1` interface, you
can simply fill in `proxy.com`. However, if the model service provider directly forwards the
`api.openai.com` domain, then you need to add `/v1` to the URL yourself.
</Callout>
Related discussions:
- [Why is the return value blank after installing Docker, configuring environment variables?](https://github.com/lobehub/lobe-chat/discussions/623)
- [Reasons for errors when using third-party interfaces](https://github.com/lobehub/lobe-chat/discussions/734)
- [No response in chat after filling in the proxy server address](https://github.com/lobehub/lobe-chat/discussions/1065)
### `OPENAI_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-0125-preview=gpt-4-turbo`
The above example adds `qwen-7b-chat` and `glm-6b` to the model list, removes `gpt-3.5-turbo` from the list, and displays the name of `gpt-4-0125-preview` as `gpt-4-turbo`. If you want to disable all models first and then enable specific models, you can use `-all,+gpt-3.5-turbo`, which means only `gpt-3.5-turbo` will be enabled.
You can find all current model names in [modelProviders](https://github.com/lobehub/lobe-chat/tree/main/src/config/modelProviders).
## Azure OpenAI
If you need to use Azure OpenAI to provide model services, you can refer to the [Deploying with Azure OpenAI](/docs/self-hosting/examples/azure-openai) section for detailed steps. Here, we will list the environment variables related to Azure OpenAI.
### `AZURE_API_KEY`
- Type: Required
- Description: This is the API key you applied for on the Azure OpenAI account page
- Default: -
- Example: `c55168be3874490ef0565d9779ecd5a6`
### `AZURE_ENDPOINT`
- Type: Required
- Description: The endpoint of Azure OpenAI, you can find it in the Azure OpenAI account page
- Default: `-`
- Example: `https://docs-test-001.openai.azure.com`
### `AZURE_API_VERSION`
- Type: Required
- Description: The API version of Azure, following the format YYYY-MM-DD
- Default: `-`
- Example: `2023-02-01`, refer to [latest version](https://docs.microsoft.com/zh-cn/azure/developer/javascript/api-reference/es-modules/azure-sdk/ai-translation/translationconfiguration?view=azure-node-latest#api-version)
### `AZURE_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `id->deplymentName=displayName` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `gpt-35-turbo->my-deploy=GPT 3.5 Turbo` 或 `gpt-4-turbo->my-gpt4=GPT 4 Turbo<128000:vision:fc>`
## Google AI
### `GOOGLE_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the Google AI Platform to access Google AI services
- Default: -
- Example: `AIraDyDwcw254kwJaGjI9wwaHcdDCS__Vt3xQE`
### `GOOGLE_PROXY_URL`
- Type: Optional
- Description: If you manually configure the Google API proxy, you can use this configuration item to override the default Google API request base URL
- Default: `https://generativelanguage.googleapis.com`
- Example: `https://api.genai.gd.edu.kg/google`
### `GOOGLE_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+gemini-1.5-flash-latest,+gemini-1.5-pro-latest`
## Anthropic AI
### `ANTHROPIC_API_KEY`
- Type: Required
- Description: This is the API key you applied from Anthropic AI
- Default: -
- Example: `sk-ant-apixx-xxxxxxxxx-xxxxxxxxxxxxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-xxxxxxxx`
### `ANTHROPIC_PROXY_URL`
- Type: Optional
- Description: If you manually configure the Anthropic API proxy, you can use this configuration item to override the default Anthropic API request base URL
- Default: `https://api.anthropic.com`
- Example: `https://my-anthropic-proxy.com`
## AWS Bedrock
### `ENABLED_AWS_BEDROCK`
- Type：Optional
- Description：Enables AWS Bedrock as a model provider by default, turns on the AWS Bedrock service when set to `1`
- Default：`0`
- Example：`1`
### `AWS_ACCESS_KEY_ID`
- Type: Required
- Description: Access key ID for AWS service authentication
- Default: -
- Example: `AKIA5STVRLFSB4S9HWBR`
### `AWS_SECRET_ACCESS_KEY`
- Type: Required
- Description: Key for AWS service authentication
- Default: -
- Example: `Th3vXxLYpuKcv2BARktPSTPxx+jbSiFT6/0w7oEC`
### `AWS_REGION`
- Type: Optional
- Description: Region setting for AWS services
- Default: `us-east-1`
- Example: `us-east-1`
## DeepSeek AI
### `DEEPSEEK_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the DeepSeek AI service
- Default: -
- Example: `sk-xxxxxx...xxxxxx`
## OpenRouter AI
### `OPENROUTER_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the OpenRouter AI service
- Default: -
- Example: `sk-or-v1-xxxxxx...xxxxxx=`
### `OPENROUTER_MODEL_LIST`
- Type: Optional
- Description: Used to specify a custom OpenRouter model list. Model definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+01-ai/yi-34b-chat,+huggingfaceh4/zephyr-7b-beta`
## Github
### `GITHUB_TOKEN`
- Type: Required
- Description: This is your Personal access tokens you got for in the Github
- Default: `-`
- Example：`ghp_xxxxxx...xxxxxx=`
### `GITHUB_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+gpt-4o,+gpt-4o-mini`
## TogetherAI
### `TOGETHERAI_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the TogetherAI service
- Default: -
- Example: `xxxxxx...xxxxxx`
### `TOGETHERAI_MODEL_LIST`
- Type: Optional
- Description: Used to specify a custom TogetherAI model list. Model definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo,+meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`
## Fireworks AI
### `FIREWORKSAI_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the Fireworks AI service
- Default: `-`
- Example：`xxxxxx...xxxxxx`
### `FIREWORKSAI_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+accounts/fireworks/models/firefunction-v2,+accounts/fireworks/models/firefunction-v1`
## Ollama
### `ENABLED_OLLAMA`
- Type：Optional
- Description：Enables Ollama as a model provider by default, turns off the Ollama service when set to `0`
- Default：`1`
- Example：`0`
### `OLLAMA_PROXY_URL`
- Type: Required
- Description: Used to enable the Ollama service, setting this will display optional open-source language models in the language model list and can also specify custom language models
- Default: -
- Example: `http://127.0.0.1:11434`
### `OLLAMA_MODEL_LIST`
- Type: Optional
- Description: Used to specify a custom Ollama language model. Model definition syntax rules see [model-list][model-list]
- Default: -
- Example: `llama2:7B`
## Moonshot AI
### `MOONSHOT_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the Moonshot AI service
- Default: -
- Example: `Y2xpdGhpMzNhZXNoYjVtdnZjMWc6bXNrLWIxQlk3aDNPaXpBWnc0V1RaMDhSRmRFVlpZUWY=`
## Perplexity AI
### `PERPLEXITY_API_KEY`
- Type: Required
- Description: This is the API key you applied from Perplexity AI
- Default: -
- Example: `pplx-xxxxxx...xxxxxx`
### `PERPLEXITY_PROXY_URL`
- Type: Optional
- Description: If you manually configure the Perplexity API proxy, you can use this configuration item to override the default Perplexity API request base URL
- Default: `https://api.Perplexity.ai`
- Example: `https://my-Perplexity-proxy.com`
## Minimax AI
### `MINIMAX_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the Minimax AI service
- Default: -
- Example: `xxxxxx...xxxxxx`
## Mistral AI
### `MISTRAL_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the Mistral AI service
- Default: -
- Example: `xxxxxx...xxxxxx=`
## Groq AI
### `GROQ_API_KEY`
- Type: Required
- Description: This is the API key you applied from Groq AI
- Default: -
- Example: `gsk_xxxxxx...xxxxxx`
### `GROQ_PROXY_URL`
- Type: Optional
- Description: If you manually configure the Groq API proxy, you can use this configuration item to override the default Groq API request base URL
- Default: `https://api.groq.com/openai/v1`
- Example: `https://my-groq-proxy.com/v1`
### `GROQ_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+gemma2-9b-it,+llama-3.1-8b-instant`
## ZHIPU AI
### `ZHIPU_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the ZHIPU AI service
- Default: -
- Example: `4582d332441a313f5c2ed9824d1798ca.rC8EcTAhgbOuAuVT`
### `ZHIPU_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+glm-4-alltools,+glm-4-plus`
## 01.AI
### `ZEROONE_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the 01.AI service
- Default: -
- Example：`xxxxxx...xxxxxx`
### `ZEROONE_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+yi-large,+yi-large-rag`
## Qwen
### `QWEN_API_KEY`
- Type: Required
- Description: This is the DashScope API key you can obtain from Alibaba Cloud
- Default: -
- Example：`sk-xxxxx...xxxxx`
### `QWEN_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+qwen-turbo-latest,+qwen-plus-latest`
## Stepfun AI
### `STEPFUN_API_KEY`
- Type: Required
- Description: This is the DashScope API key you can obtain from Stepfun AI service
- Default: -
- Example：`sk-xxxxx...xxxxx`
## Novita AI
### `NOVITA_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the Novita AI service
- Default: -
- Example：`xxxxxx...xxxxxx`
### `NOVITA_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+meta-llama/llama-3.1-8b-instruct,+meta-llama/llama-3.1-70b-instruct`
## BAICHUAN
### `BAICHUAN_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the BAICHUAN service
- Default: -
- Example：`xxxxxx...xxxxxx`
## TAICHU
### `TAICHU_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the TAICHU service
- Default: -
- Example：`xxxxxx...xxxxxx`
## 360 AI
### `AI360_API_KEY`
- Type: Required
- Description: This is the API key you applied for in the 360 AI service
- Default: -
- Example：`xxxxxx...xxxxxx`
## Siliconflow
### `SILICONCLOUD_API_KEY`
- Type: Required
- Description: This is the API key you applied from Siliconflow service
- Default: -
- Example: `xxxxxx...xxxxxx`
### `SILICONCLOUD_PROXY_URL`
- Type: Optional
- Description: If you manually configure the Siliconflow API proxy, you can use this configuration item to override the default Siliconflow API request base URL
- Default: `https://api.siliconflow.cn/v1`
- Example: `https://my-siliconflow-proxy.com/v1`
### `SILICONCLOUD_MODEL_LIST`
- Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
- Default: `-`
- Example: `-all,+deepseek-ai/DeepSeek-V2.5,+Qwen/Qwen2.5-7B-Instruct`
## Upstage AI
### `UPSTAGE_API_KEY`
- Type: Required
- Description: This is the API key you applied from Upstage AI service
- Default: -
- Example: `xxxxxx...xxxxxx`
## Spark AI
### `SPARK_API_KEY`
- Type: Required
- Description: This is the API key you applied from Spark AI service
- Default: -
- Example: `xxxxxx...xxxxxx`
## A21 AI
### `AI21_API_KEY`
- Type: Required
- Description: This is the API key you applied from AI21_API_KEY service
- Default: -
- Example: `xxxxxx...xxxxxx`
[model-list]: /docs/self-hosting/advanced/model-list
Reference in New Issue View Git Blame Copy Permalink