29473a72db
* WIP(backend/api): custom endpoint * WIP(frontend/client): custom endpoint * chore: adjust typedefs for configs * refactor: use data-provider for cache keys and rename enums and custom endpoint for better clarity and compatibility * feat: loadYaml utility * refactor: rename back to from and proof-of-concept for creating schemas from user-defined defaults * refactor: remove custom endpoint from default endpointsConfig as it will be exclusively managed by yaml config * refactor(EndpointController): rename variables for clarity * feat: initial load custom config * feat(server/utils): add simple `isUserProvided` helper * chore(types): update TConfig type * refactor: remove custom endpoint handling from model services as will be handled by config, modularize fetching of models * feat: loadCustomConfig, loadConfigEndpoints, loadConfigModels * chore: reorganize server init imports, invoke loadCustomConfig * refactor(loadConfigEndpoints/Models): return each custom endpoint as standalone endpoint * refactor(Endpoint/ModelController): spread config values after default (temporary) * chore(client): fix type issues * WIP: first pass for multiple custom endpoints - add endpointType to Conversation schema - add update zod schemas for both convo/presets to allow non-EModelEndpoint value as endpoint (also using type assertion) - use `endpointType` value as `endpoint` where mapping to type is necessary using this field - use custom defined `endpoint` value and not type for mapping to modelsConfig - misc: add return type to `getDefaultEndpoint` - in `useNewConvo`, add the endpointType if it wasn't already added to conversation - EndpointsMenu: use user-defined endpoint name as Title in menu - TODO: custom icon via custom config, change unknown to robot icon * refactor(parseConvo): pass args as an object and change where used accordingly; chore: comment out 'create schema' code * chore: remove unused availableModels field in TConfig type * refactor(parseCompactConvo): pass args as an object and change where used accordingly * feat: chat through custom endpoint * chore(message/convoSchemas): avoid saving empty arrays * fix(BaseClient/saveMessageToDatabase): save endpointType * refactor(ChatRoute): show Spinner if endpointsQuery or modelsQuery are still loading, which is apparent with slow fetching of models/remote config on first serve * fix(useConversation): assign endpointType if it's missing * fix(SaveAsPreset): pass real endpoint and endpointType when saving Preset) * chore: recorganize types order for TConfig, add `iconURL` * feat: custom endpoint icon support: - use UnknownIcon in all icon contexts - add mistral and openrouter as known endpoints, and add their icons - iconURL support * fix(presetSchema): move endpointType to default schema definitions shared between convoSchema and defaults * refactor(Settings/OpenAI): remove legacy `isOpenAI` flag * fix(OpenAIClient): do not invoke abortCompletion on completion error * feat: add responseSender/label support for custom endpoints: - use defaultModelLabel field in endpointOption - add model defaults for custom endpoints in `getResponseSender` - add `useGetSender` hook which uses EndpointsQuery to determine `defaultModelLabel` - include defaultModelLabel from endpointConfig in custom endpoint client options - pass `endpointType` to `getResponseSender` * feat(OpenAIClient): use custom options from config file * refactor: rename `defaultModelLabel` to `modelDisplayLabel` * refactor(data-provider): separate concerns from `schemas` into `parsers`, `config`, and fix imports elsewhere * feat: `iconURL` and extract environment variables from custom endpoint config values * feat: custom config validation via zod schema, rename and move to `./projectRoot/librechat.yaml` * docs: custom config docs and examples * fix(OpenAIClient/mistral): mistral does not allow singular system message, also add `useChatCompletion` flag to use openai-node for title completions * fix(custom/initializeClient): extract env var and use `isUserProvided` function * Update librechat.example.yaml * feat(InputWithLabel): add className props, and forwardRef * fix(streamResponse): handle error edge case where either messages or convos query throws an error * fix(useSSE): handle errorHandler edge cases where error response is and is not properly formatted from API, especially when a conversationId is not yet provided, which ensures stream is properly closed on error * feat: user_provided keys for custom endpoints * fix(config/endpointSchema): do not allow default endpoint values in custom endpoint `name` * feat(loadConfigModels): extract env variables and optimize fetching models * feat: support custom endpoint iconURL for messages and Nav * feat(OpenAIClient): add/dropParams support * docs: update docs with default params, add/dropParams, and notes to use config file instead of `OPENAI_REVERSE_PROXY` * docs: update docs with additional notes * feat(maxTokensMap): add mistral models (32k context) * docs: update openrouter notes * Update ai_setup.md * docs(custom_config): add table of contents and fix note about custom name * docs(custom_config): reorder ToC * Update custom_config.md * Add note about `max_tokens` field in custom_config.md
3.5 KiB
| title | description | weight |
|---|---|---|
| 💸 Free AI APIs | There are APIs offering free/free-trial access to AI APIs via reverse proxy... | -6 |
Free AI APIs
There are APIs offering free/free-trial access to AI APIs via reverse proxy.
Here is a well-maintained public list of Free AI APIs that may or may not be compatible with LibreChat
⚠️ OpenRouter is in a category of its own, and is highly recommended over the "free" services below. NagaAI and other 'free' API proxies tend to have intermittent issues, data leaks, and/or problems with the guidelines of the platforms they advertise on. Use the below at your own risk.
NagaAI
Since NagaAI works with LibreChat, and offers Llama2 along with OpenAI models, let's start with that one: NagaAI
⚠️ Never trust 3rd parties. Use at your own risk of privacy loss. Your data may be used for AI training at best or for nefarious reasons at worst; this is true in all cases, even with official endpoints: never give an LLM sensitive/identifying information. If something is free, you are the product. If errors arise, they are more likely to be due to the 3rd party, and not this project, as I test the official endpoints first and foremost.
You will get your API key from the discord server. The instructions are pretty clear when you join so I won't repeat them.
Once you have the API key, you should adjust your .env file like this:
##########################
# OpenAI Endpoint:
##########################
OPENAI_API_KEY=your-naga-ai-api-key
# Reverse proxy settings for OpenAI:
OPENAI_REVERSE_PROXY=https://api.naga.ac/v1/chat/completions
# OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-0301,text-davinci-003,gpt-4,gpt-4-0314,gpt-4-0613
Important: As of v0.6.6, it's recommend you use the librechat.yaml Configuration file (guide here) to add Reverse Proxies as separate endpoints.
Note: The OPENAI_MODELS variable is commented out so that the server can fetch nagaai/api/v1/models for all available models. Uncomment and adjust if you wish to specify which exact models you want to use.
It's worth noting that not all models listed by their API will work, with or without this project. The exact URL may also change, just make sure you include /v1/chat/completions in the reverse proxy URL if it ever changes.
You can set OPENAI_API_KEY=user_provided if you would like the user to add their own NagaAI API key, just be sure you specify the models with OPENAI_MODELS in this case since they won't be able to be fetched without an admin set API key.
That's it! You're all set. 🎉
Here's me using Llama2 via NagaAI
Plugins also work with this reverse proxy (OpenAI models). More info on plugins here
⚠️ Note: If you're having trouble, before creating a new issue, please search for similar ones on our #issues thread on our discord or our troubleshooting discussion on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.