Merge branch 'enricoros:main' into main

kantega · Sep 16, 2024 · 8043f5e · 8043f5e
2 parents 3bdd7bd + fce21ad
commit 8043f5e
Show file tree

Hide file tree

Showing 9 changed files with 174 additions and 86 deletions.
diff --git a/README.md b/README.md
@@ -11,18 +11,19 @@ Stay ahead of the curve with big-AGI. 🚀 Pros & Devs love big-AGI. 🤖
 
 [![Official Website](https://img.shields.io/badge/BIG--AGI.com-%23096bde?style=for-the-badge&logo=vercel&label=launch)](https://big-agi.com)
 
+> 🚀 Big-AGI 2 is launching Q4 2024. Be the first to experience it before the public release.
+>
+> 👉 [Apply for Early Access](https://y2rjg0zillz.typeform.com/to/FDggwwZv?utm_source=github&utm_medium=readme&utm_campaign=ba20)
+
 Or fork & run on Vercel
 
 [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fenricoros%2Fbig-AGI&env=OPENAI_API_KEY&envDescription=Backend%20API%20keys%2C%20optional%20and%20may%20be%20overridden%20by%20the%20UI.&envLink=https%3A%2F%2Fgithub.com%2Fenricoros%2Fbig-AGI%2Fblob%2Fmain%2Fdocs%2Fenvironment-variables.md&project-name=big-AGI)
 
-## 👉 [roadmap](https://github.com/users/enricoros/projects/4/views/2) 👉 [installation](docs/installation.md) 👉 [documentation](docs/README.md)
-
-> Note: bigger better features (incl. Beam-2) are being cooked outside of `main`.
-
-[//]: # (big-AGI is an open book; see the **[ready-to-ship and future ideas]&#40;https://github.com/users/enricoros/projects/4/views/2&#41;** in our open roadmap)
+### Quick links: 👉 [roadmap](https://github.com/users/enricoros/projects/4/views/2) 👉 [installation](docs/installation.md) 👉 [documentation](docs/README.md)
 
-### What's New in 1.16.1...1.16.7 · Aug 7, 2024 (patch releases)
+### What's New in 1.16.1...1.16.8 · Sep 13, 2024 (patch releases)
 
+- 1.16.8: OpenAI ChatGPT-4o Latest (o1-preview and o1-mini are supported in Big-AGI 2)
 - 1.16.7: OpenAI support for GPT-4o 2024-08-06
 - 1.16.6: Groq support for Llama 3.1 models
 - 1.16.5: GPT-4o Mini support

diff --git a/docs/changelog.md b/docs/changelog.md
@@ -10,8 +10,9 @@ 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 1.16.1...1.16.7 · Aug 7, 2024 (patch releases)
+### What's New in 1.16.1...1.16.8 · Sep 13, 2024 (patch releases)
 
+- 1.16.8: OpenAI ChatGPT-4o Latest (o1-preview and o1-mini are supported in Big-AGI 2)
 - 1.16.7: OpenAI support for GPT-4o 2024-08-06
 - 1.16.6: Groq support for Llama 3.1 models
 - 1.16.5: GPT-4o Mini support

diff --git a/docs/environment-variables.md b/docs/environment-variables.md
@@ -99,7 +99,7 @@ requiring the user to enter an API key
 | `LOCALAI_API_HOST`          | Sets the URL of the LocalAI server, or defaults to http://127.0.0.1:8080                                                      | Optional                                                          |
 | `LOCALAI_API_KEY`           | The (Optional) API key for LocalAI                                                                                            | Optional                                                          |
 | `MISTRAL_API_KEY`           | The API key for Mistral                                                                                                       | Optional                                                          |
-| `OLLAMA_API_HOST`           | Changes the backend host for the Ollama vendor. See [config-local-ollama.md](config-local-ollama)                             |                                                                   |
+| `OLLAMA_API_HOST`           | Changes the backend host for the Ollama vendor. See [config-local-ollama.md](config-local-ollama.md)                          |                                                                   |
 | `OPENROUTER_API_KEY`        | The API key for OpenRouter                                                                                                    | Optional                                                          |
 | `PERPLEXITY_API_KEY`        | The API key for Perplexity                                                                                                    | Optional                                                          |
 | `TOGETHERAI_API_KEY`        | The API key for Together AI                                                                                                   | Optional                                                          |

diff --git a/src/apps/news/AppNews.tsx b/src/apps/news/AppNews.tsx
@@ -14,6 +14,7 @@ import { capitalizeFirstLetter } from '~/common/util/textUtils';
 
 import { NewsItems } from './news.data';
 import { beamNewsCallout } from './beam.data';
+import { bigAgi2NewsCallout } from './bigAgi2.data';
 
 
 // number of news items to show by default, before the expander
@@ -110,6 +111,13 @@ export function AppNews() {
             const addPadding = false; //!firstCard; // || showExpander;
             return <React.Fragment key={idx}>
 
+              {/* Inject the Big-AGI 2.0 item here*/}
+              {idx === 0 && (
+                <Box sx={{ mb: 3 }}>
+                  {bigAgi2NewsCallout}
+                </Box>
+              )}
+
               {/* Inject the Beam item here*/}
               {idx === 2 && (
                 <Box sx={{ mb: 3 }}>

diff --git a/src/apps/news/beam.data.tsx b/src/apps/news/beam.data.tsx
@@ -2,7 +2,6 @@ import * as React from 'react';
 
 import { Button, Card, CardContent, Grid, Typography } from '@mui/joy';
 import LaunchIcon from '@mui/icons-material/Launch';
-import ThumbUpRoundedIcon from '@mui/icons-material/ThumbUpRounded';
 
 import { Link } from '~/common/components/Link';
 

diff --git a/src/apps/news/bigAgi2.data.tsx b/src/apps/news/bigAgi2.data.tsx
@@ -0,0 +1,40 @@
+import * as React from 'react';
+
+import { Button, Card, CardContent, Grid, Typography } from '@mui/joy';
+import AccessTimeIcon from '@mui/icons-material/AccessTime';
+import LaunchIcon from '@mui/icons-material/Launch';
+
+import { Link } from '~/common/components/Link';
+
+
+const bigAgi2SurveyUrl = 'https://y2rjg0zillz.typeform.com/to/FDggwwZv?utm_source=github&utm_medium=callout&utm_campaign=ba20';
+
+export const bigAgi2NewsCallout =
+  <Card variant='solid' invertedColors>
+    <CardContent sx={{ gap: 2 }}>
+      <Typography level='title-lg'>
+        Big-AGI 2.0 - In Development
+      </Typography>
+      <Typography level='body-sm'>
+        We&apos;re building the next version of Big-AGI with your needs in mind. New features, better performance, enhanced AI interactions. Help us shape it.
+      </Typography>
+      <Grid container spacing={1}>
+        <Grid xs={12} sm={7}>
+          <Button
+            fullWidth variant='soft' color='primary' endDecorator={<LaunchIcon />}
+            component={Link} href={bigAgi2SurveyUrl} noLinkStyle target='_blank'
+          >
+            Apply for Early Access
+          </Button>
+        </Grid>
+        <Grid xs={12} sm={5} sx={{ display: 'flex', flexAlign: 'center', justifyContent: 'center' }}>
+          <Button
+            fullWidth variant='outlined' color='primary' startDecorator={<AccessTimeIcon />}
+            disabled
+          >
+            Coming Fall 2024
+          </Button>
+        </Grid>
+      </Grid>
+    </CardContent>
+  </Card>;
diff --git a/src/apps/news/news.data.tsx b/src/apps/news/news.data.tsx
@@ -61,7 +61,7 @@ export const NewsItems: NewsItem[] = [
     ]
   }*/
   {
-    versionCode: '1.16.7',
+    versionCode: '1.16.8',
     versionName: 'Crystal Clear',
     versionDate: new Date('2024-06-07T05:00:00Z'),
     // versionDate: new Date('2024-05-13T19:00:00Z'),
@@ -83,7 +83,9 @@ export const NewsItems: NewsItem[] = [
       { text: <>1.16.4: <B>8192 tokens</B> support for Claude 3.5 Sonnet</> },
       { text: <>1.16.5: OpenAI <B>GPT-4o Mini</B> support</> },
       { text: <>1.16.6: Groq <B>Llama 3.1</B> support</> },
-      { text: <>1.16.7: Gpt-4o  <B>2024-08-06</B></> },
+      { text: <>1.16.7: Gpt-4o <B>2024-08-06</B></> },
+      { text: <>1.16.8: <B>ChatGPT-4o</B> latest</> },
+      { text: <>OpenAI <B>o1</B> and newer models require Big-AGI 2. <B href='https://y2rjg0zillz.typeform.com/to/FDggwwZv?utm_source=github&utm_medium=news116&utm_campaign=ba20'>Sign up here</B></> },
     ],
   },
   {

diff --git a/src/apps/news/news.version.tsx b/src/apps/news/news.version.tsx
@@ -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 1.16.7
+export const incrementalNewsVersion: number = 16.1; // not notifying for 1.16.8
 
 
 interface NewsState {

diff --git a/src/modules/llms/server/openai/models.data.ts b/src/modules/llms/server/openai/models.data.ts
@@ -12,34 +12,7 @@ import { wireTogetherAIListOutputSchema } from './togetherai.wiretypes';
 // https://platform.openai.com/docs/models
 const _knownOpenAIChatModels: ManualMappings = [
 
-  // GPT-4o mini
-  {
-    idPrefix: 'gpt-4o-mini-2024-07-18',
-    label: 'GPT-4o Mini (2024-07-18)',
-    description: 'Affordable model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo.',
-    contextWindow: 128000,
-    maxCompletionTokens: 16384,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
-    pricing: { chatIn: 0.15, chatOut: 0.60 },
-    benchmark: { cbaElo: 1277, cbaMmlu: 82.0 },
-  },
-  {
-    idPrefix: 'gpt-4o-mini',
-    label: 'GPT-4o mini',
-    description: 'Currently points to gpt-4o-mini-2024-07-18.',
-    symLink: 'gpt-4o-mini-2024-07-18',
-    hidden: true,
-    // copied from symlinked
-    contextWindow: 128000,
-    maxCompletionTokens: 16384,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
-    pricing: { chatIn: 0.15, chatOut: 0.60 },
-    benchmark: { cbaElo: 1277, cbaMmlu: 82.0 },
-  },
-
-  // GPT-4o -> 2024-05-13 (will be update to 2024-08-06 in the future (3 weeks notice))
+  // GPT-4o -> 2024-05-13 (Starting October 2nd, 2024, gpt-4o will point to the gpt-4o-2024-08-06 snapshot)
   {
     idPrefix: 'gpt-4o',
     label: 'GPT-4o',
@@ -62,14 +35,14 @@ const _knownOpenAIChatModels: ManualMappings = [
     contextWindow: 128000,
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json], // + Structured Outputs?
     pricing: { chatIn: 2.5, chatOut: 10 },
     benchmark: { cbaElo: 1286 + 1 },
   },
   {
     idPrefix: 'gpt-4o-2024-05-13',
     label: 'GPT-4o (2024-05-13)',
-    description: 'Advanced, multimodal flagship model that’s cheaper and faster than GPT-4 Turbo.',
+    description: 'Advanced, multimodal flagship model that\'s cheaper and faster than GPT-4 Turbo.',
     contextWindow: 128000,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Oct 2023',
@@ -78,6 +51,98 @@ const _knownOpenAIChatModels: ManualMappings = [
     benchmark: { cbaElo: 1286 },
     hidden: true,
   },
+  {
+    idPrefix: 'chatgpt-4o-latest',
+    label: 'ChatGPT-4o Latest',
+    description: 'Intended for research and evaluation. Dynamic model continuously updated to the current version of GPT-4o in ChatGPT.',
+    contextWindow: 128000,
+    maxCompletionTokens: 16384,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    pricing: { chatIn: 5, chatOut: 15 },
+  },
+
+  // GPT-4o mini
+  {
+    idPrefix: 'gpt-4o-mini',
+    label: 'GPT-4o mini',
+    description: 'Currently points to gpt-4o-mini-2024-07-18.',
+    symLink: 'gpt-4o-mini-2024-07-18',
+    hidden: true,
+    // copied from symlinked
+    contextWindow: 128000,
+    maxCompletionTokens: 16384,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    pricing: { chatIn: 0.15, chatOut: 0.60 },
+    benchmark: { cbaElo: 1277, cbaMmlu: 82.0 },
+  },
+  {
+    idPrefix: 'gpt-4o-mini-2024-07-18',
+    label: 'GPT-4o Mini (2024-07-18)',
+    description: 'Affordable model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo.',
+    contextWindow: 128000,
+    maxCompletionTokens: 16384,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    pricing: { chatIn: 0.15, chatOut: 0.60 },
+  },
+
+  // o1-preview
+  {
+    idPrefix: 'o1-preview',
+    label: 'o1 Preview',
+    description: 'Supported in Big-AGI 2. Points to the most recent snapshot of the o1 model: o1-preview-2024-09-12',
+    symLink: 'o1-preview-2024-09-12',
+    hidden: true,
+    // copied from symlinked
+    contextWindow: 128000,
+    maxCompletionTokens: 32768,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
+    pricing: { chatIn: 15, chatOut: 60 },
+    isPreview: true,
+  },
+  {
+    hidden: true, // we can't support it in Big-AGI 1
+    idPrefix: 'o1-preview-2024-09-12',
+    label: 'o1 Preview (2024-09-12)',
+    description: 'Supported in Big-AGI 2. New reasoning model for complex tasks that require broad general knowledge.',
+    contextWindow: 128000,
+    maxCompletionTokens: 32768,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
+    pricing: { chatIn: 15, chatOut: 60 },
+    isPreview: true,
+  },
+
+  // o1-mini
+  {
+    idPrefix: 'o1-mini',
+    label: 'o1 Mini',
+    description: 'Supported in Big-AGI 2. Points to the most recent o1-mini snapshot: o1-mini-2024-09-12',
+    symLink: 'o1-mini-2024-09-12',
+    hidden: true,
+    // copied from symlinked
+    contextWindow: 128000,
+    maxCompletionTokens: 65536,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
+    pricing: { chatIn: 3, chatOut: 12 },
+    isPreview: true,
+  },
+  {
+    hidden: true, // we can't support it in Big-AGI 1
+    idPrefix: 'o1-mini-2024-09-12',
+    label: 'o1 Mini (2024-09-12)',
+    description: 'Supported in Big-AGI 2. Fast, cost-efficient reasoning model tailored to coding, math, and science use cases.',
+    contextWindow: 128000,
+    maxCompletionTokens: 65536,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
+    pricing: { chatIn: 3, chatOut: 12 },
+    isPreview: true,
+  },
 
   // GPT4 Turbo with Vision -> 2024-04-09
   {
@@ -108,7 +173,7 @@ const _knownOpenAIChatModels: ManualMappings = [
 
   // GPT4 Turbo Previews
   {
-    idPrefix: 'gpt-4-turbo-preview', // GPT-4 Turbo preview model -> 0125
+    idPrefix: 'gpt-4-turbo-preview',
     label: 'GPT-4 Preview Turbo',
     description: 'GPT-4 Turbo preview model. Currently points to gpt-4-0125-preview.',
     symLink: 'gpt-4-0125-preview',
@@ -123,7 +188,7 @@ const _knownOpenAIChatModels: ManualMappings = [
     benchmark: { cbaElo: 1245 },
   },
   {
-    idPrefix: 'gpt-4-0125-preview', // GPT-4 Turbo preview model
+    idPrefix: 'gpt-4-0125-preview',
     label: 'GPT-4 Turbo (0125)',
     description: 'GPT-4 Turbo preview model intended to reduce cases of "laziness" where the model doesn\'t complete a task.',
     contextWindow: 128000,
@@ -147,34 +212,6 @@ const _knownOpenAIChatModels: ManualMappings = [
     hidden: true,
   },
 
-  // GPT4 Vision Previews
-  {
-    idPrefix: 'gpt-4-vision-preview', // GPT-4 Turbo vision preview
-    label: 'GPT-4 Preview Vision',
-    description: 'GPT-4 model with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. This is a preview model, we recommend developers to now use gpt-4-turbo which includes vision capabilities. Currently points to gpt-4-1106-vision-preview.',
-    symLink: 'gpt-4-1106-vision-preview',
-    // copied from symlinked
-    isPreview: true,
-    contextWindow: 128000,
-    maxCompletionTokens: 4096,
-    trainingDataCutoff: 'Apr 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 10, chatOut: 30 },
-    hidden: true, // Deprecated in favor of gpt-4-turbo
-  },
-  {
-    idPrefix: 'gpt-4-1106-vision-preview',
-    label: 'GPT-4 Preview Vision (1106)',
-    description: 'GPT-4 model with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. This is a preview model, we recommend developers to now use gpt-4-turbo which includes vision capabilities. Returns a maximum of 4,096 output tokens.',
-    isPreview: true,
-    contextWindow: 128000,
-    maxCompletionTokens: 4096,
-    trainingDataCutoff: 'Apr 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 10, chatOut: 30 },
-    hidden: true, // Deprecated in favor of gpt-4-turbo
-  },
-
 
   // GPT4-32k's
   {
@@ -248,20 +285,8 @@ const _knownOpenAIChatModels: ManualMappings = [
     isLegacy: true,
   },
 
-
-  // 3.5-Turbo-Instruct (Not for Chat)
-  {
-    idPrefix: 'gpt-3.5-turbo-instruct',
-    label: '3.5-Turbo Instruct',
-    description: 'Similar capabilities as GPT-3 era models. Compatible with legacy Completions endpoint and not Chat Completions.',
-    contextWindow: 4097,
-    trainingDataCutoff: 'Sep 2021',
-    interfaces: [/* NO: LLM_IF_OAI_Chat,*/ LLM_IF_OAI_Complete],
-    pricing: { chatIn: 1.5, chatOut: 2 },
-    hidden: true,
-  },
-
-  // 3.5-Turbo's (16ks)
+  // 3.5-Turbo
+  // As of July 2024, gpt-4o-mini should be used in place of gpt-3.5-turbo, as it is cheaper, more capable, multimodal, and just as fast.
   {
     idPrefix: 'gpt-3.5-turbo-0125',
     label: '3.5-Turbo (0125)',
@@ -300,6 +325,18 @@ const _knownOpenAIChatModels: ManualMappings = [
     benchmark: { cbaElo: 1105 },
   },
 
+  // 3.5-Turbo-Instruct (Not for Chat)
+  {
+    idPrefix: 'gpt-3.5-turbo-instruct',
+    label: '3.5-Turbo Instruct',
+    description: 'Similar capabilities as GPT-3 era models. Compatible with legacy Completions endpoint and not Chat Completions.',
+    contextWindow: 4097,
+    trainingDataCutoff: 'Sep 2021',
+    interfaces: [/* NO: LLM_IF_OAI_Chat,*/ LLM_IF_OAI_Complete],
+    pricing: { chatIn: 1.5, chatOut: 2 },
+    hidden: true,
+  },
+
 
   // Azure variants - because someone forgot the dot
   {