2023-12-14 07:49:27 -05:00
|
|
|
const { getResponseSender } = require('librechat-data-provider');
|
2023-12-10 14:54:13 -05:00
|
|
|
const { sendMessage, createOnProgress } = require('~/server/utils');
|
|
|
|
|
const { saveMessage, getConvoTitle, getConvo } = require('~/models');
|
|
|
|
|
const { createAbortController, handleAbortError } = require('~/server/middleware');
|
2023-12-14 07:49:27 -05:00
|
|
|
const { logger } = require('~/config');
|
2023-12-10 14:54:13 -05:00
|
|
|
|
2023-12-15 15:47:40 -05:00
|
|
|
const AskController = async (req, res, next, initializeClient, addTitle) => {
|
2023-12-10 14:54:13 -05:00
|
|
|
let {
|
|
|
|
|
text,
|
|
|
|
|
endpointOption,
|
|
|
|
|
conversationId,
|
💫 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
2024-01-03 09:22:48 -05:00
|
|
|
modelDisplayLabel,
|
2023-12-10 14:54:13 -05:00
|
|
|
parentMessageId = null,
|
|
|
|
|
overrideParentMessageId = null,
|
|
|
|
|
} = req.body;
|
2023-12-15 15:47:40 -05:00
|
|
|
|
2023-12-14 07:49:27 -05:00
|
|
|
logger.debug('[AskController]', { text, conversationId, ...endpointOption });
|
2023-12-15 15:47:40 -05:00
|
|
|
|
2023-12-10 14:54:13 -05:00
|
|
|
let metadata;
|
|
|
|
|
let userMessage;
|
|
|
|
|
let promptTokens;
|
|
|
|
|
let userMessageId;
|
|
|
|
|
let responseMessageId;
|
|
|
|
|
let lastSavedTimestamp = 0;
|
|
|
|
|
let saveDelay = 100;
|
💫 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
2024-01-03 09:22:48 -05:00
|
|
|
const sender = getResponseSender({
|
|
|
|
|
...endpointOption,
|
|
|
|
|
model: endpointOption.modelOptions.model,
|
|
|
|
|
modelDisplayLabel,
|
|
|
|
|
});
|
2023-12-15 15:47:40 -05:00
|
|
|
const newConvo = !conversationId;
|
2023-12-10 14:54:13 -05:00
|
|
|
const user = req.user.id;
|
|
|
|
|
|
2023-12-15 15:47:40 -05:00
|
|
|
const addMetadata = (data) => (metadata = data);
|
|
|
|
|
|
2023-12-10 14:54:13 -05:00
|
|
|
const getReqData = (data = {}) => {
|
|
|
|
|
for (let key in data) {
|
|
|
|
|
if (key === 'userMessage') {
|
|
|
|
|
userMessage = data[key];
|
|
|
|
|
userMessageId = data[key].messageId;
|
|
|
|
|
} else if (key === 'responseMessageId') {
|
|
|
|
|
responseMessageId = data[key];
|
|
|
|
|
} else if (key === 'promptTokens') {
|
|
|
|
|
promptTokens = data[key];
|
|
|
|
|
} else if (!conversationId && key === 'conversationId') {
|
|
|
|
|
conversationId = data[key];
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
};
|
|
|
|
|
|
2023-12-16 20:45:27 -05:00
|
|
|
let getText;
|
2023-12-10 14:54:13 -05:00
|
|
|
|
2023-12-16 20:45:27 -05:00
|
|
|
try {
|
|
|
|
|
const { client } = await initializeClient({ req, res, endpointOption });
|
2023-12-10 14:54:13 -05:00
|
|
|
|
2023-12-16 20:45:27 -05:00
|
|
|
const { onProgress: progressCallback, getPartialText } = createOnProgress({
|
|
|
|
|
onProgress: ({ text: partialText }) => {
|
|
|
|
|
const currentTimestamp = Date.now();
|
|
|
|
|
|
|
|
|
|
if (currentTimestamp - lastSavedTimestamp > saveDelay) {
|
|
|
|
|
lastSavedTimestamp = currentTimestamp;
|
|
|
|
|
saveMessage({
|
|
|
|
|
messageId: responseMessageId,
|
|
|
|
|
sender,
|
|
|
|
|
conversationId,
|
|
|
|
|
parentMessageId: overrideParentMessageId ?? userMessageId,
|
|
|
|
|
text: partialText,
|
|
|
|
|
model: client.modelOptions.model,
|
|
|
|
|
unfinished: true,
|
|
|
|
|
error: false,
|
|
|
|
|
user,
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (saveDelay < 500) {
|
|
|
|
|
saveDelay = 500;
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
});
|
2023-12-10 14:54:13 -05:00
|
|
|
|
2023-12-16 20:45:27 -05:00
|
|
|
getText = getPartialText;
|
|
|
|
|
|
|
|
|
|
const getAbortData = () => ({
|
|
|
|
|
sender,
|
|
|
|
|
conversationId,
|
|
|
|
|
messageId: responseMessageId,
|
|
|
|
|
parentMessageId: overrideParentMessageId ?? userMessageId,
|
|
|
|
|
text: getPartialText(),
|
|
|
|
|
userMessage,
|
|
|
|
|
promptTokens,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const { abortController, onStart } = createAbortController(req, res, getAbortData);
|
2023-12-10 14:54:13 -05:00
|
|
|
|
2023-12-15 15:47:40 -05:00
|
|
|
const messageOptions = {
|
2023-12-10 14:54:13 -05:00
|
|
|
user,
|
|
|
|
|
parentMessageId,
|
2023-12-15 15:47:40 -05:00
|
|
|
conversationId,
|
2023-12-10 14:54:13 -05:00
|
|
|
overrideParentMessageId,
|
2023-12-15 15:47:40 -05:00
|
|
|
getReqData,
|
|
|
|
|
onStart,
|
|
|
|
|
addMetadata,
|
|
|
|
|
abortController,
|
2023-12-10 14:54:13 -05:00
|
|
|
onProgress: progressCallback.call(null, {
|
|
|
|
|
res,
|
|
|
|
|
text,
|
2023-12-15 15:47:40 -05:00
|
|
|
parentMessageId: overrideParentMessageId || userMessageId,
|
2023-12-10 14:54:13 -05:00
|
|
|
}),
|
2023-12-15 15:47:40 -05:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
let response = await client.sendMessage(text, messageOptions);
|
|
|
|
|
|
|
|
|
|
if (overrideParentMessageId) {
|
|
|
|
|
response.parentMessageId = overrideParentMessageId;
|
|
|
|
|
}
|
2023-12-10 14:54:13 -05:00
|
|
|
|
|
|
|
|
if (metadata) {
|
|
|
|
|
response = { ...response, ...metadata };
|
|
|
|
|
}
|
|
|
|
|
|
2024-01-03 19:17:42 -05:00
|
|
|
response.endpoint = endpointOption.endpoint;
|
|
|
|
|
|
2023-12-15 15:47:40 -05:00
|
|
|
if (client.options.attachments) {
|
|
|
|
|
userMessage.files = client.options.attachments;
|
|
|
|
|
delete userMessage.image_urls;
|
2023-12-10 14:54:13 -05:00
|
|
|
}
|
|
|
|
|
|
2023-12-30 14:34:32 -05:00
|
|
|
if (!abortController.signal.aborted) {
|
|
|
|
|
sendMessage(res, {
|
|
|
|
|
title: await getConvoTitle(user, conversationId),
|
|
|
|
|
final: true,
|
|
|
|
|
conversation: await getConvo(user, conversationId),
|
|
|
|
|
requestMessage: userMessage,
|
|
|
|
|
responseMessage: response,
|
|
|
|
|
});
|
|
|
|
|
res.end();
|
|
|
|
|
|
|
|
|
|
await saveMessage({ ...response, user });
|
|
|
|
|
}
|
2023-12-10 14:54:13 -05:00
|
|
|
|
|
|
|
|
await saveMessage(userMessage);
|
|
|
|
|
|
2023-12-15 15:47:40 -05:00
|
|
|
if (addTitle && parentMessageId === '00000000-0000-0000-0000-000000000000' && newConvo) {
|
|
|
|
|
addTitle(req, {
|
|
|
|
|
text,
|
|
|
|
|
response,
|
|
|
|
|
client,
|
|
|
|
|
});
|
|
|
|
|
}
|
2023-12-10 14:54:13 -05:00
|
|
|
} catch (error) {
|
2023-12-16 20:45:27 -05:00
|
|
|
const partialText = getText && getText();
|
2023-12-10 14:54:13 -05:00
|
|
|
handleAbortError(res, req, error, {
|
|
|
|
|
partialText,
|
|
|
|
|
conversationId,
|
|
|
|
|
sender,
|
|
|
|
|
messageId: responseMessageId,
|
|
|
|
|
parentMessageId: userMessageId ?? parentMessageId,
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
module.exports = AskController;
|