1.16.9 Release

.github/workflows/docker-image.yml

@@ -51,8 +51,7 @@ jobs:
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           tags: |
-            type=raw,value=development,enable=${{ github.ref == 'refs/heads/main' }}
-            type=raw,value=stable,enable=${{ github.ref == 'refs/heads/main-stable' }}
+            type=raw,value=stable,enable=${{ github.ref == 'refs/heads/v1-stable' }}
             type=ref,event=tag  # Use the tag name as a tag for tag builds
             type=semver,pattern={{version}}  # Generate semantic versioning tags for tag builds
             type=sha # Just in case none of the above applies

README.md

@@ -19,11 +19,23 @@ 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)
 
+### New Version
+
+This repository contains two main versions:
+
+- Big-AGI 2: next-generation, bringing the most advanced AI experience
+  - `v2-dev`: V2 development branch, the exciting one, future default
+- Big-AGI Stable: as deployed on big-agi.com
+  - `v1-stable`: Current stable version & Docker 'latest' tag
+
+Note: After the V2 release in Q4, `v2/dev` will become the default branch and `v1/dev` will reach EOL.
+
 ### 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...1.16.8 · Sep 13, 2024 (patch releases)
+### What's New in 1.16.1...1.16.9 · Jan 21, 2025 (patch releases)
 
-- 1.16.8: OpenAI ChatGPT-4o Latest (o1-preview and o1-mini are supported in Big-AGI 2)
+- 1.16.9: Docker Gemini fix (R1 models are supported in Big-AGI 2)
+- 1.16.8: OpenAI ChatGPT-4o Latest (o1 models 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

docs/changelog.md

@@ -10,9 +10,10 @@ 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...1.16.8 · Sep 13, 2024 (patch releases)
+### What's New in 1.16.1...1.16.9 · Jan 21, 2025 (patch releases)
 
-- 1.16.8: OpenAI ChatGPT-4o Latest (o1-preview and o1-mini are supported in Big-AGI 2)
+- 1.16.9: Docker Gemini fix (R1 models are supported in Big-AGI 2)
+- 1.16.8: OpenAI ChatGPT-4o Latest (o1 models 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

package-lock.json

@@ -79,7 +79,7 @@
         "typescript": "^5.4.5"
       },
       "engines": {
-        "node": "^20.0.0 || ^18.0.0"
+        "node": "^22.0.0 || ^20.0.0 || ^18.0.0"
       }
     },
     "node_modules/@babel/code-frame": {

package.json

@@ -88,6 +88,6 @@
     "typescript": "^5.4.5"
   },
   "engines": {
-    "node": "^20.0.0 || ^18.0.0"
+    "node": "^22.0.0 || ^20.0.0 || ^18.0.0"
   }
 }

src/apps/news/news.data.tsx

@@ -61,7 +61,7 @@ export const NewsItems: NewsItem[] = [
     ]
   }*/
   {
-    versionCode: '1.16.8',
+    versionCode: '1.16.9',
     versionName: 'Crystal Clear',
     versionDate: new Date('2024-06-07T05:00:00Z'),
     // versionDate: new Date('2024-05-13T19:00:00Z'),
@@ -85,7 +85,8 @@ export const NewsItems: NewsItem[] = [
       { text: <>1.16.6: Groq <B>Llama 3.1</B> support</> },
       { text: <>1.16.7: Gpt-4o <B>2024-08-06</B></> },
       { text: <>1.16.8: <B>ChatGPT-4o</B> latest</> },
-      { text: <>OpenAI <B>o1</B> and newer models require Big-AGI 2. <B href='https://y2rjg0zillz.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=news&utm_campaign=ea2'>Sign up here</B></> },
+      { text: <>1.16.9: <B>Gemini</B> fixes</> },
+      { text: <>OpenAI <B>o1</B>, DeepSeek R1, and newer models require Big-AGI 2. <B href='https://y2rjg0zillz.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=news&utm_campaign=ea2'>Sign up here</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 1.16.8
+export const incrementalNewsVersion: number = 16.1; // not notifying for 1.16.9
 
 
 interface NewsState {

src/modules/llms/server/anthropic/anthropic.models.ts

@@ -22,8 +22,20 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
   //   },
   // },
   {
-    id: 'claude-3-5-sonnet-20240620',
+    id: 'claude-3-5-sonnet-20241022',
     label: 'Claude 3.5 Sonnet',
+    created: roundTime('2024-10-22 06:00'),
+    description: 'Most intelligent Claude model to date',
+    contextWindow: 200000, // Characters
+    maxCompletionTokens: 8192,
+    trainingDataCutoff: 'Apr 2024',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
+    pricing: { chatIn: 3, chatOut: 15 },
+    benchmark: { cbaElo: 1269, cbaMmlu: 88.7 }, // moved from 3.5 Sonnet (Previous Version), TO UPDATE!!
+  },
+  {
+    id: 'claude-3-5-sonnet-20240620',
+    label: 'Claude 3.5 Sonnet (Previous)',
     created: roundTime('2024-06-20 06:00'),
     description: 'The most intelligent Claude model',
     contextWindow: 200000, // Characters
@@ -31,13 +43,8 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
     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
-    },
+    benchmark: { cbaElo: 1269 - 0.1, cbaMmlu: 88.7 - 0.1 },
+    hidden: true,
   },
   // {
   //   id: 'claude-3.5-haiku', // ...
@@ -81,6 +88,7 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
     pricing: { chatIn: 3, chatOut: 15 },
     benchmark: { cbaElo: 1203, cbaMmlu: 79 },
     hidden: true,
+    isLegacy: true,
   },
   {
     id: 'claude-3-haiku-20240307',
@@ -131,24 +139,4 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
     pricing: { chatIn: 0.8, chatOut: 2.4 },
     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/gemini/gemini.wiretypes.ts

@@ -9,6 +9,21 @@ export const geminiModelsStreamGenerateContentPath = '/v1beta/{model=models/*}:s
 
 
 // models.list = /v1beta/models
+const Methods_enum = z.enum([
+  'bidiGenerateContent', // appeared on 2024-12, see https://github.com/enricoros/big-AGI/issues/700
+  'createCachedContent', // appeared on 2024-06-10, see https://github.com/enricoros/big-AGI/issues/565
+  'countMessageTokens',
+  'countTextTokens',
+  'countTokens',
+  'createTunedModel',
+  'createTunedTextModel',
+  'embedContent',
+  'embedText',
+  'generateAnswer',
+  'generateContent',
+  'generateMessage',
+  'generateText',
+]);
 
 const geminiModelSchema = z.object({
   name: z.string(),
@@ -17,20 +32,7 @@ const geminiModelSchema = z.object({
   description: z.string(),
   inputTokenLimit: z.number().int().min(1),
   outputTokenLimit: z.number().int().min(1),
-  supportedGenerationMethods: z.array(z.enum([
-    'createCachedContent', // appeared on 2024-06-10, see https://github.com/enricoros/big-AGI/issues/565
-    'countMessageTokens',
-    'countTextTokens',
-    'countTokens',
-    'createTunedModel',
-    'createTunedTextModel',
-    'embedContent',
-    'embedText',
-    'generateAnswer',
-    'generateContent',
-    'generateMessage',
-    'generateText',
-  ])),
+  supportedGenerationMethods: z.array(z.union([Methods_enum, z.string()])), // relaxed with z.union to not break on expansion
   temperature: z.number().optional(),
   topP: z.number().optional(),
   topK: z.number().optional(),
@@ -172,7 +174,7 @@ export const geminiGeneratedContentResponseSchema = z.object({
   // either all requested candidates are returned or no candidates at all
   // no candidates are returned only if there was something wrong with the prompt (see promptFeedback)
   candidates: z.array(z.object({
-    index: z.number(),
+    index: z.number().optional(),
     content: geminiContentSchema.optional(), // this can be missing if the finishReason is not 'MAX_TOKENS'
     finishReason: geminiFinishReasonSchema.optional(),
     safetyRatings: z.array(geminiSafetyRatingSchema).optional(), // undefined when finishReason is 'RECITATION'

src/modules/llms/server/openai/models.data.ts

@@ -16,16 +16,16 @@ const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'gpt-4o',
     label: 'GPT-4o',
-    description: 'Currently points to gpt-4o-2024-05-13.',
-    symLink: 'gpt-4o-2024-05-13',
+    description: 'Points to gpt-4o-2024-08-06 starting on Oct 2, 2024.',
+    symLink: 'gpt-4o-2024-08-06',
     hidden: true,
     // copied from symlinked
     contextWindow: 128000,
-    maxCompletionTokens: 4096,
+    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 },
-    benchmark: { cbaElo: 1286 },
+    pricing: { chatIn: 2.5, chatOut: 10 },
+    benchmark: { cbaElo: 1286 + 1 },
   },
   {
     isLatest: true,