mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 00:40:14 +01:00
🪨 feat: AWS Bedrock support (#3935)
* feat: Add BedrockIcon component to SVG library * feat: EModelEndpoint.bedrock * feat: first pass, bedrock chat. note: AgentClient is returning `agents` as conversation.endpoint * fix: declare endpoint in initialization step * chore: Update @librechat/agents dependency to version 1.4.5 * feat: backend content aggregation for agents/bedrock * feat: abort agent requests * feat: AWS Bedrock icons * WIP: agent provider schema parsing * chore: Update EditIcon props type * refactor(useGenerationsByLatest): make agents and bedrock editable * refactor: non-assistant message content, parts * fix: Bedrock response `sender` * fix: use endpointOption.model_parameters not endpointOption.modelOptions * fix: types for step handler * refactor: Update Agents.ToolCallDelta type * refactor: Remove unnecessary assignment of parentMessageId in AskController * refactor: remove unnecessary assignment of parentMessageId (agent request handler) * fix(bedrock/agents): message regeneration * refactor: dynamic form elements using react-hook-form Controllers * fix: agent icons/labels for messages * fix: agent actions * fix: use of new dynamic tags causing application crash * refactor: dynamic settings touch-ups * refactor: update Slider component to allow custom track class name * refactor: update DynamicSlider component styles * refactor: use Constants value for GLOBAL_PROJECT_NAME (enum) * feat: agent share global methods/controllers * fix: agents query * fix: `getResponseModel` * fix: share prompt a11y issue * refactor: update SharePrompt dialog theme styles * refactor: explicit typing for SharePrompt * feat: add agent roles/permissions * chore: update @librechat/agents dependency to version 1.4.7 for tool_call_ids edge case * fix(Anthropic): messages.X.content.Y.tool_use.input: Input should be a valid dictionary * fix: handle text parts with tool_call_ids and empty text * fix: role initialization * refactor: don't make instructions required * refactor: improve typing of Text part * fix: setShowStopButton for agents route * chore: remove params for now * fix: add streamBuffer and streamRate to help prevent 'Overloaded' errors from Anthropic API * refactor: remove console.log statement in ContentRender component * chore: typing, rename Context to Delete Button * chore(DeleteButton): logging * refactor(Action): make accessible * style(Action): improve a11y again * refactor: remove use/mention of mongoose sessions * feat: first pass, sharing agents * feat: visual indicator for global agent, remove author when serving to non-author * wip: params * chore: fix typing issues * fix(schemas): typing * refactor: improve accessibility of ListCard component and fix console React warning * wip: reset templates for non-legacy new convos * Revert "wip: params" This reverts commitf8067e91d4. * Revert "refactor: dynamic form elements using react-hook-form Controllers" This reverts commit2150c4815d. * fix(Parameters): types and parameter effect update to only update local state to parameters * refactor: optimize useDebouncedInput hook for better performance * feat: first pass, anthropic bedrock params * chore: paramEndpoints check for endpointType too * fix: maxTokens to use coerceNumber.optional(), * feat: extra chat model params * chore: reduce code repetition * refactor: improve preset title handling in SaveAsPresetDialog component * refactor: improve preset handling in HeaderOptions component * chore: improve typing, replace legacy dialog for SaveAsPresetDialog * feat: save as preset from parameters panel * fix: multi-search in select dropdown when using Option type * refactor: update default showDefault value to false in Dynamic components * feat: Bedrock presets settings * chore: config, fix agents schema, update config version * refactor: update AWS region variable name in bedrock options endpoint to BEDROCK_AWS_DEFAULT_REGION * refactor: update baseEndpointSchema in config.ts to include baseURL property * refactor: update createRun function to include req parameter and set streamRate based on provider * feat: availableRegions via config * refactor: remove unused demo agent controller file * WIP: title * Update @librechat/agents to version 1.5.0 * chore: addTitle.js to handle empty responseText * feat: support images and titles * feat: context token updates * Refactor BaseClient test to use expect.objectContaining * refactor: add model select, remove header options params, move side panel params below prompts * chore: update models list, catch title error * feat: model service for bedrock models (env) * chore: Remove verbose debug log in AgentClient class following stream * feat(bedrock): track token spend; fix: token rates, value key mapping for AWS models * refactor: handle streamRate in `handleLLMNewToken` callback * chore: AWS Bedrock example config in `.env.example` * refactor: Rename bedrockMeta to bedrockGeneral in settings.ts and use for AI21 and Amazon Bedrock providers * refactor: Update `.env.example` with AWS Bedrock model IDs URL and additional notes * feat: titleModel support for bedrock * refactor: Update `.env.example` with additional notes for AWS Bedrock model IDs
This commit is contained in:
Danny Avila
GitHub
parent
8c14360263
commit
d59b62174f
134 changed files with 3684 additions and 1213 deletions
|
|
@ -7,13 +7,13 @@ const openAIModels = {
|
|||
'gpt-4-32k': 32758, // -10 from max
|
||||
'gpt-4-32k-0314': 32758, // -10 from max
|
||||
'gpt-4-32k-0613': 32758, // -10 from max
|
||||
'gpt-4-1106': 127990, // -10 from max
|
||||
'gpt-4-0125': 127990, // -10 from max
|
||||
'gpt-4o': 127990, // -10 from max
|
||||
'gpt-4o-mini': 127990, // -10 from max
|
||||
'gpt-4o-2024-08-06': 127990, // -10 from max
|
||||
'gpt-4-turbo': 127990, // -10 from max
|
||||
'gpt-4-vision': 127990, // -10 from max
|
||||
'gpt-4-1106': 127500, // -500 from max
|
||||
'gpt-4-0125': 127500, // -500 from max
|
||||
'gpt-4o': 127500, // -500 from max
|
||||
'gpt-4o-mini': 127500, // -500 from max
|
||||
'gpt-4o-2024-08-06': 127500, // -500 from max
|
||||
'gpt-4-turbo': 127500, // -500 from max
|
||||
'gpt-4-vision': 127500, // -500 from max
|
||||
'gpt-3.5-turbo': 16375, // -10 from max
|
||||
'gpt-3.5-turbo-0613': 4092, // -5 from max
|
||||
'gpt-3.5-turbo-0301': 4092, // -5 from max
|
||||
|
|
@ -21,9 +21,15 @@ const openAIModels = {
|
|||
'gpt-3.5-turbo-16k-0613': 16375, // -10 from max
|
||||
'gpt-3.5-turbo-1106': 16375, // -10 from max
|
||||
'gpt-3.5-turbo-0125': 16375, // -10 from max
|
||||
};
|
||||
|
||||
const mistralModels = {
|
||||
'mistral-': 31990, // -10 from max
|
||||
llama3: 8187, // -5 from max
|
||||
'llama-3': 8187, // -5 from max
|
||||
'mistral-7b': 31990, // -10 from max
|
||||
'mistral-small': 31990, // -10 from max
|
||||
'mixtral-8x7b': 31990, // -10 from max
|
||||
'mistral-large-2402': 127500,
|
||||
'mistral-large-2407': 127500,
|
||||
};
|
||||
|
||||
const cohereModels = {
|
||||
|
|
@ -54,6 +60,7 @@ const googleModels = {
|
|||
|
||||
const anthropicModels = {
|
||||
'claude-': 100000,
|
||||
'claude-instant': 100000,
|
||||
'claude-2': 100000,
|
||||
'claude-2.1': 200000,
|
||||
'claude-3-haiku': 200000,
|
||||
|
|
@ -63,7 +70,38 @@ const anthropicModels = {
|
|||
'claude-3.5-sonnet': 200000,
|
||||
};
|
||||
|
||||
const aggregateModels = { ...openAIModels, ...googleModels, ...anthropicModels, ...cohereModels };
|
||||
const metaModels = {
|
||||
'llama2-13b': 4000,
|
||||
'llama2-70b': 4000,
|
||||
'llama3-8b': 8000,
|
||||
'llama3-70b': 8000,
|
||||
'llama3-1-8b': 127500,
|
||||
'llama3-1-70b': 127500,
|
||||
'llama3-1-405b': 127500,
|
||||
};
|
||||
|
||||
const ai21Models = {
|
||||
'ai21.j2-mid-v1': 8182, // -10 from max
|
||||
'ai21.j2-ultra-v1': 8182, // -10 from max
|
||||
'ai21.jamba-instruct-v1:0': 255500, // -500 from max
|
||||
};
|
||||
|
||||
const amazonModels = {
|
||||
'amazon.titan-text-lite-v1': 4000,
|
||||
'amazon.titan-text-express-v1': 8000,
|
||||
'amazon.titan-text-premier-v1:0': 31500, // -500 from max
|
||||
};
|
||||
|
||||
const bedrockModels = {
|
||||
...anthropicModels,
|
||||
...mistralModels,
|
||||
...cohereModels,
|
||||
...metaModels,
|
||||
...ai21Models,
|
||||
...amazonModels,
|
||||
};
|
||||
|
||||
const aggregateModels = { ...openAIModels, ...googleModels, ...bedrockModels };
|
||||
|
||||
const maxTokensMap = {
|
||||
[EModelEndpoint.azureOpenAI]: openAIModels,
|
||||
|
|
@ -72,6 +110,7 @@ const maxTokensMap = {
|
|||
[EModelEndpoint.custom]: aggregateModels,
|
||||
[EModelEndpoint.google]: googleModels,
|
||||
[EModelEndpoint.anthropic]: anthropicModels,
|
||||
[EModelEndpoint.bedrock]: bedrockModels,
|
||||
};
|
||||
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -20,18 +20,6 @@ describe('getModelMaxTokens', () => {
|
|||
);
|
||||
});
|
||||
|
||||
test('should return correct tokens for LLama 3 models', () => {
|
||||
expect(getModelMaxTokens('meta-llama/llama-3-8b')).toBe(
|
||||
maxTokensMap[EModelEndpoint.openAI]['llama-3'],
|
||||
);
|
||||
expect(getModelMaxTokens('meta-llama/llama-3-8b')).toBe(
|
||||
maxTokensMap[EModelEndpoint.openAI]['llama3'],
|
||||
);
|
||||
expect(getModelMaxTokens('llama-3-500b')).toBe(maxTokensMap[EModelEndpoint.openAI]['llama-3']);
|
||||
expect(getModelMaxTokens('llama3-70b')).toBe(maxTokensMap[EModelEndpoint.openAI]['llama3']);
|
||||
expect(getModelMaxTokens('llama3:latest')).toBe(maxTokensMap[EModelEndpoint.openAI]['llama3']);
|
||||
});
|
||||
|
||||
test('should return undefined for no match', () => {
|
||||
expect(getModelMaxTokens('unknown-model')).toBeUndefined();
|
||||
});
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue