zack3d/big-agi
1
0
Fork 0
mirror of https://github.com/enricoros/big-AGI.git synced 2026-05-10 21:50:14 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'refs/heads/main' into feature-multipart

Browse Source
This commit is contained in:
Enrico Ros
2024-06-20 12:28:53 -07:00
parent d1ac9adc7e 9af1a6a16b
commit 8b2b88c7cb
7 changed files with 106 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+8 -10
View File
@@ -21,17 +21,15 @@ Or fork & run on Vercel
[//]: # (big-AGI is an open book; see the **[ready-to-ship and future ideas](https://github.com/users/enricoros/projects/4/views/2)** in our open roadmap)
### What's New in 1.16.2 · Jun 7, 2024 (minor release)
### What's New in 1.16.1...1.16.3 · Jun 20, 2024 (patch releases)
- Improve web downloads, as text, markdwon, or HTML
- Proper support for Gemini models
- Added the latest Mistral model
- Tokenizer support for gpt-4o
- Updates to Beam
### What's New in 1.16.1 · May 13, 2024 (minor release)
- Support for the new OpenAI GPT-4o 2024-05-13 model
- 1.16.3: Anthropic Claude 3.5 Sonnet model support
- 1.16.2: Improve web downloads, as text, markdwon, or HTML
- 1.16.2: Proper support for Gemini models
- 1.16.2: Added the latest Mistral model
- 1.16.2: Tokenizer support for gpt-4o
- 1.16.2: Updates to Beam
- 1.16.1: Support for the new OpenAI GPT-4o 2024-05-13 model
### What's New in 1.16.0 · May 9, 2024 · Crystal Clear
docs/changelog.md
+8 -10
View File
@@ -10,17 +10,15 @@ by release.
- milestone: [1.17.0](https://github.com/enricoros/big-agi/milestone/17)
- work in progress: [big-AGI open roadmap](https://github.com/users/enricoros/projects/4/views/2), [help here](https://github.com/users/enricoros/projects/4/views/4)
### What's New in 1.16.2 · Jun 7, 2024 (minor release)
### What's New in 1.16.1...1.16.3 · Jun 20, 2024 (patch releases)
- Improve web downloads, as text, markdwon, or HTML
- Proper support for Gemini models
- Added the latest Mistral model
- Tokenizer support for gpt-4o
- Updates to Beam
### What's New in 1.16.1 · May 13, 2024 (minor release)
- Support for the new OpenAI GPT-4o 2024-05-13 model
- 1.16.3: Anthropic Claude 3.5 Sonnet model support
- 1.16.2: Improve web downloads, as text, markdwon, or HTML
- 1.16.2: Proper support for Gemini models
- 1.16.2: Added the latest Mistral model
- 1.16.2: Tokenizer support for gpt-4o
- 1.16.2: Updates to Beam
- 1.16.1: Support for the new OpenAI GPT-4o 2024-05-13 model
### What's New in 1.16.0 · May 9, 2024 · Crystal Clear
src/apps/news/news.data.tsx
+3 -2
View File
@@ -61,7 +61,7 @@ export const NewsItems: NewsItem[] = [
]
}*/
{
versionCode: '1.16.2',
versionCode: '1.16.3',
versionName: 'Crystal Clear',
versionDate: new Date('2024-06-07T05:00:00Z'),
// versionDate: new Date('2024-05-13T19:00:00Z'),
@@ -77,8 +77,9 @@ export const NewsItems: NewsItem[] = [
{ text: <>More: <B issue={517}>code soft-wrap</B>, selection toolbar, <B issue={507}>3x faster</B> on Apple silicon</>, issue: 507 },
{ text: <>Updated <B>Anthropic</B>*, <B>Groq</B>, <B>Ollama</B>, <B>OpenAI</B>*, <B>OpenRouter</B>*, and <B>Perplexity</B></> },
{ text: <>Developers: update LLMs data structures</>, dev: true },
{ text: <>1.16.1: Support for <B>OpenAI</B> <B href='https://openai.com/index/hello-gpt-4o/'>GPT-4o</B> (refresh your OpenAI models)</> },
{ text: <>1.16.1: Support for <B>OpenAI</B> <B href='https://openai.com/index/hello-gpt-4o/'>GPT-4o</B></> },
{ text: <>1.16.2: Proper <B>Gemini</B> support, <B>HTML/Markdown</B> downloads, and latest <B>Mistral</B></> },
{ text: <>1.16.3: Support for <B href='https://www.anthropic.com/news/claude-3-5-sonnet'>Claude 3.5 Sonnet</B> (refresh your <B>Anthropic</B> models)</> },
],
},
{
src/apps/news/news.version.tsx
+1 -1
View File
@@ -7,7 +7,7 @@ import { useAppStateStore } from '~/common/state/store-appstate';
// update this variable every time you want to broadcast a new version to clients
export const incrementalNewsVersion: number = 16.1; // not notifying for 16.2
export const incrementalNewsVersion: number = 16.1; // not notifying for 16.3
interface NewsState {
src/modules/llms/models-modal/LLMOptionsModal.tsx
+3 -2
View File
@@ -1,4 +1,5 @@
import * as React from 'react';
import TimeAgo from 'react-timeago';
import { shallow } from 'zustand/shallow';
import { Box, Button, ButtonGroup, Divider, FormControl, Input, Switch, Tooltip, Typography } from '@mui/joy';
@@ -132,10 +133,10 @@ export function LLMOptionsModal(props: { id: DLLMId, onClose: () => void }) {
llm id: {llm.id}<br />
context tokens: <b>{llm.contextTokens ? llm.contextTokens.toLocaleString() : 'not provided'}</b>{` · `}
max output tokens: <b>{llm.maxOutputTokens ? llm.maxOutputTokens.toLocaleString() : 'not provided'}</b><br />
{!!llm.created && <>created: {(new Date(llm.created * 1000)).toLocaleString()}<br /></>}
{!!llm.created && <>created: <TimeAgo date={new Date(llm.created * 1000)} /><br /></>}
{/*· tags: {llm.tags.join(', ')}*/}
{!!llm.pricing && <>pricing: $<b>{llm.pricing.chatIn || '(unk) '}</b>/M in, $<b>{llm.pricing.chatOut || '(unk) '}</b>/M out<br /></>}
{!!llm.benchmark && <>benchmark: <b>{llm.benchmark.cbaElo?.toLocaleString() || '(unk) '}</b> CBA Elo<br /></>}
{/*{!!llm.benchmark && <>benchmark: <b>{llm.benchmark.cbaElo?.toLocaleString() || '(unk) '}</b> CBA Elo<br /></>}*/}
config: {JSON.stringify(llm.options)}
</Typography>
</Box>}
src/modules/llms/server/anthropic/anthropic.models.ts
+81 -28
View File
@@ -4,14 +4,64 @@ import { LLM_IF_OAI_Chat, LLM_IF_OAI_Vision } from '../../store-llms';
const roundTime = (date: string) => Math.round(new Date(date).getTime() / 1000);
export const hardcodedAnthropicModels: ModelDescriptionSchema[] = [
// Claude-3 models - https://docs.anthropic.com/claude/docs/models-overview#model-comparison
export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: boolean })[] = [
// Claude 3.5 models - https://docs.anthropic.com/en/docs/about-claude/models
// {
// id: 'claude-3.5-opus', // ...
// label: 'Claude 3.5 Opus',
// created: roundTime(?),
// description: ?,
// contextWindow: 200000 ?, // Characters
// maxCompletionTokens: 4096 ?,
// trainingDataCutoff: ?,
// interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
// pricing: { chatIn: 15, chatOut: 75 },
// benchmark: {
// cbaElo: 1256, // Placeholder
// cbaMmlu: 86.8, // Placeholder
// },
// },
{
id: 'claude-3-opus-20240229',
id: 'claude-3-5-sonnet-20240620',
label: 'Claude 3.5 Sonnet',
created: roundTime('2024-06-20 06:00'),
description: 'The most intelligent Claude model',
contextWindow: 200000, // Characters
maxCompletionTokens: 4096,
trainingDataCutoff: 'Apr 2024',
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
pricing: { chatIn: 3, chatOut: 15 },
benchmark: {
heCode: 92.0,
vqaMmmu: 68.3,
// TODO: Update with official benchmarks when available
cbaElo: 1256 - 1, // Placeholder
cbaMmlu: 86.8 - 1, // Placeholder
},
},
// {
// id: 'claude-3.5-haiku', // ...
// label: 'Claude 3.5 Haiku',
// created: roundTime(?),
// description: ?,
// contextWindow: 200000 ?, // Characters
// maxCompletionTokens: 4096 ?,
// trainingDataCutoff: ?,
// interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
// pricing: { chatIn: 0.25, chatOut: 1.25 },
// benchmark: {
// cbaElo: 1181, // Placeholder
// cbaMmlu: 75.2, // Placeholder
// },
// },
// Claude 3 models
{
id: 'claude-3-opus', // claude-3-opus-20240229
label: 'Claude 3 Opus',
created: roundTime('2024-02-29'),
description: 'Most powerful model for highly complex tasks',
description: 'Powerful model for complex tasks',
contextWindow: 200000,
maxCompletionTokens: 4096,
trainingDataCutoff: 'Aug 2023',
@@ -20,22 +70,23 @@ export const hardcodedAnthropicModels: ModelDescriptionSchema[] = [
benchmark: { cbaElo: 1256, cbaMmlu: 86.8 },
},
{
id: 'claude-3-sonnet-20240229',
id: 'claude-3-sonnet', // claude-3-sonnet-20240229
label: 'Claude 3 Sonnet',
created: roundTime('2024-02-29'),
description: 'Ideal balance of intelligence and speed for enterprise workloads',
description: 'Balance of speed, cost, and performance',
contextWindow: 200000,
maxCompletionTokens: 4096,
trainingDataCutoff: 'Aug 2023',
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
pricing: { chatIn: 3, chatOut: 15 },
benchmark: { cbaElo: 1203, cbaMmlu: 79 },
hidden: true,
},
{
id: 'claude-3-haiku-20240307',
id: 'claude-3-haiku', // claude-3-haiku-20240307
label: 'Claude 3 Haiku',
created: roundTime('2024-03-07'),
description: 'Fastest and most compact model for near-instant responsiveness',
description: 'Fastest, most cost-effective model',
contextWindow: 200000,
maxCompletionTokens: 4096,
trainingDataCutoff: 'Aug 2023',
@@ -55,6 +106,7 @@ export const hardcodedAnthropicModels: ModelDescriptionSchema[] = [
interfaces: [LLM_IF_OAI_Chat],
pricing: { chatIn: 8, chatOut: 24 },
benchmark: { cbaElo: 1119 },
hidden: true,
},
{
id: 'claude-2.0',
@@ -77,25 +129,26 @@ export const hardcodedAnthropicModels: ModelDescriptionSchema[] = [
maxCompletionTokens: 4096,
interfaces: [LLM_IF_OAI_Chat],
pricing: { chatIn: 0.8, chatOut: 2.4 },
},
{
id: 'claude-instant-1.1',
label: 'Claude Instant 1.1',
created: roundTime('2023-03-14'),
description: 'Precise and fast',
contextWindow: 100000,
maxCompletionTokens: 2048,
interfaces: [LLM_IF_OAI_Chat],
hidden: true,
},
{
id: 'claude-1.3',
label: 'Claude 1.3',
created: roundTime('2023-03-14'),
description: 'Claude 1.3 is the latest version of Claude v1',
contextWindow: 100000,
maxCompletionTokens: 4096,
interfaces: [LLM_IF_OAI_Chat],
hidden: true,
},
// {
// id: 'claude-instant-1.1',
// label: 'Claude Instant 1.1',
// created: roundTime('2023-03-14'),
// description: 'Precise and fast',
// contextWindow: 100000,
// maxCompletionTokens: 2048,
// interfaces: [LLM_IF_OAI_Chat],
// hidden: true,
// },
// {
// id: 'claude-1.3',
// label: 'Claude 1.3',
// created: roundTime('2023-03-14'),
// description: 'Claude 1.3 is the latest version of Claude v1',
// contextWindow: 100000,
// maxCompletionTokens: 4096,
// interfaces: [LLM_IF_OAI_Chat],
// hidden: true,
// },
];
src/modules/llms/server/llm.server.types.ts
+2
View File
@@ -12,6 +12,8 @@ const pricingSchema = z.object({
const benchmarkSchema = z.object({
cbaElo: z.number().optional(),
cbaMmlu: z.number().optional(),
heCode: z.number().optional(), // HumanEval, code, 0-shot
vqaMmmu: z.number().optional(), // Visual Question Answering, MMMU, 0-shot
});
// const rateLimitsSchema = z.object({