💫 feat: Config File & Custom Endpoints (#1474)

* 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
This commit is contained in:
Danny Avila 2024-01-03 09:22:48 -05:00 committed by GitHub
parent 3f98f92d4c
commit 29473a72db
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
100 changed files with 2146 additions and 627 deletions

View file

@ -0,0 +1,186 @@
import { z } from 'zod';
import { EModelEndpoint, eModelEndpointSchema } from './schemas';
export const endpointSchema = z.object({
name: z.string().refine((value) => !eModelEndpointSchema.safeParse(value).success, {
message: `Value cannot be one of the default endpoint (EModelEndpoint) values: ${Object.values(
EModelEndpoint,
).join(', ')}`,
}),
apiKey: z.string(),
baseURL: z.string(),
models: z.object({
default: z.array(z.string()).min(1),
fetch: z.boolean().optional(),
}),
titleConvo: z.boolean().optional(),
titleMethod: z.union([z.literal('completion'), z.literal('functions')]).optional(),
titleModel: z.string().optional(),
summarize: z.boolean().optional(),
summaryModel: z.string().optional(),
forcePrompt: z.boolean().optional(),
modelDisplayLabel: z.string().optional(),
});
export const configSchema = z.object({
version: z.string(),
cache: z.boolean(),
endpoints: z
.object({
custom: z.array(endpointSchema.partial()),
})
.strict(),
});
export enum KnownEndpoints {
mistral = 'mistral',
openrouter = 'openrouter',
}
export const defaultEndpoints: EModelEndpoint[] = [
EModelEndpoint.openAI,
EModelEndpoint.assistant,
EModelEndpoint.azureOpenAI,
EModelEndpoint.bingAI,
EModelEndpoint.chatGPTBrowser,
EModelEndpoint.gptPlugins,
EModelEndpoint.google,
EModelEndpoint.anthropic,
EModelEndpoint.custom,
];
export const alternateName = {
[EModelEndpoint.openAI]: 'OpenAI',
[EModelEndpoint.assistant]: 'Assistants',
[EModelEndpoint.azureOpenAI]: 'Azure OpenAI',
[EModelEndpoint.bingAI]: 'Bing',
[EModelEndpoint.chatGPTBrowser]: 'ChatGPT',
[EModelEndpoint.gptPlugins]: 'Plugins',
[EModelEndpoint.google]: 'Google',
[EModelEndpoint.anthropic]: 'Anthropic',
[EModelEndpoint.custom]: 'Custom',
};
export const defaultModels = {
[EModelEndpoint.google]: [
'gemini-pro',
'gemini-pro-vision',
'chat-bison',
'chat-bison-32k',
'codechat-bison',
'codechat-bison-32k',
'text-bison',
'text-bison-32k',
'text-unicorn',
'code-gecko',
'code-bison',
'code-bison-32k',
],
[EModelEndpoint.anthropic]: [
'claude-2.1',
'claude-2',
'claude-1.2',
'claude-1',
'claude-1-100k',
'claude-instant-1',
'claude-instant-1-100k',
],
[EModelEndpoint.openAI]: [
'gpt-3.5-turbo-16k-0613',
'gpt-3.5-turbo-16k',
'gpt-4-1106-preview',
'gpt-3.5-turbo',
'gpt-3.5-turbo-1106',
'gpt-4-vision-preview',
'gpt-4',
'gpt-3.5-turbo-instruct-0914',
'gpt-3.5-turbo-0613',
'gpt-3.5-turbo-0301',
'gpt-3.5-turbo-instruct',
'gpt-4-0613',
'text-davinci-003',
'gpt-4-0314',
],
};
export const EndpointURLs: { [key in EModelEndpoint]: string } = {
[EModelEndpoint.openAI]: `/api/ask/${EModelEndpoint.openAI}`,
[EModelEndpoint.bingAI]: `/api/ask/${EModelEndpoint.bingAI}`,
[EModelEndpoint.google]: `/api/ask/${EModelEndpoint.google}`,
[EModelEndpoint.custom]: `/api/ask/${EModelEndpoint.custom}`,
[EModelEndpoint.anthropic]: `/api/ask/${EModelEndpoint.anthropic}`,
[EModelEndpoint.gptPlugins]: `/api/ask/${EModelEndpoint.gptPlugins}`,
[EModelEndpoint.azureOpenAI]: `/api/ask/${EModelEndpoint.azureOpenAI}`,
[EModelEndpoint.chatGPTBrowser]: `/api/ask/${EModelEndpoint.chatGPTBrowser}`,
[EModelEndpoint.assistant]: '/api/assistants/chat',
};
export const modularEndpoints = new Set<EModelEndpoint | string>([
EModelEndpoint.gptPlugins,
EModelEndpoint.anthropic,
EModelEndpoint.google,
EModelEndpoint.openAI,
EModelEndpoint.azureOpenAI,
EModelEndpoint.custom,
]);
export const supportsFiles = {
[EModelEndpoint.openAI]: true,
[EModelEndpoint.google]: true,
[EModelEndpoint.assistant]: true,
[EModelEndpoint.azureOpenAI]: true,
[EModelEndpoint.custom]: true,
};
export const supportsBalanceCheck = {
[EModelEndpoint.openAI]: true,
[EModelEndpoint.azureOpenAI]: true,
[EModelEndpoint.gptPlugins]: true,
[EModelEndpoint.custom]: true,
};
export const visionModels = ['gpt-4-vision', 'llava-13b', 'gemini-pro-vision'];
/**
* Enum for cache keys.
*/
export enum CacheKeys {
/**
* Key for the config store namespace.
*/
CONFIG_STORE = 'configStore',
/**
* Key for the plugins cache.
*/
PLUGINS = 'plugins',
/**
* Key for the model config cache.
*/
MODELS_CONFIG = 'modelsConfig',
/**
* Key for the default endpoint config cache.
*/
ENDPOINT_CONFIG = 'endpointsConfig',
/**
* Key for the custom config cache.
*/
CUSTOM_CONFIG = 'customConfig',
/**
* Key for the override config cache.
*/
OVERRIDE_CONFIG = 'overrideConfig',
}
/**
* Enum for authentication keys.
*/
export enum AuthKeys {
/**
* Key for the Service Account to use Vertex AI.
*/
GOOGLE_SERVICE_KEY = 'GOOGLE_SERVICE_KEY',
/**
* API key to use Google Generative AI.
*/
GOOGLE_API_KEY = 'GOOGLE_API_KEY',
}