A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search
feat: change default tagging model to gpt-6-luna
Mohamed Bassemc381aa9b0bed
diff --git a/docs/docs/03-configuration/01-environment-variables.md b/docs/docs/03-configuration/01-environment-variables.mdindex 33c560bf..4cf22471 100644--- a/docs/docs/03-configuration/01-environment-variables.md+++ b/docs/docs/03-configuration/01-environment-variables.md@@ -103,7 +103,7 @@ Either `OPENAI_API_KEY` or `OLLAMA_BASE_URL` need to be set for automatic taggin| OLLAMA_BASE_URL | No | Not set | If you want to use ollama for local inference, set the address of ollama API here. || OLLAMA_KEEP_ALIVE | No | Not set | Controls how long the model will stay loaded into memory following the request (examples: "5m" for 5 minutes, "-1m" to keep the model loaded indefinitely, "0" to unload the model instantly after processing is complete). || SEMANTIC_SEARCH_ENABLED | No | true | Enables the hybrid and semantic bookmark search modes. **Experimental.** `EMBEDDING_ENABLE_AUTO_INDEXING` must also be enabled. |-| INFERENCE_TEXT_MODEL | No | gpt-5.6-luna | The model to use for text inference. You'll need to change this to some other model if you're using ollama. |+| INFERENCE_TEXT_MODEL | No | gpt-6-luna | The model to use for text inference. You'll need to change this to some other model if you're using ollama. || INFERENCE_IMAGE_MODEL | No | gpt-4o-mini | The model to use for image inference. You'll need to change this to some other model if you're using ollama and that model needs to support vision APIs (e.g. llava). || EMBEDDING_ENABLE_AUTO_INDEXING | No | enabled if using OpenAI | Whether bookmark embedding generation and vector indexing are enabled. This is enabled by default if you're using the default OpenAI settings (i.e. no Ollama, no OpenAI base URL override). Otherwise, you need to manually enable it after configuring the embedding model and its dimensions. || EMBEDDING_OPENAI_API_KEY | No | `OPENAI_API_KEY` | The API key used for OpenAI-compatible embedding requests. If unset, embedding requests use `OPENAI_API_KEY`. |diff --git a/docs/docs/06-administration/03-openai.md b/docs/docs/06-administration/03-openai.mdindex ff3a6cd9..2569ee63 100644--- a/docs/docs/06-administration/03-openai.md+++ b/docs/docs/06-administration/03-openai.md@@ -4,7 +4,7 @@ This service uses OpenAI for automatic tagging. This means that you'll incur som## Text Tagging-For text tagging, we use the `gpt-5.6-luna` model. This model is [extremely cheap](https://openai.com/business/pricing/#api). Cost per inference varies depending on the content size per article. Though, roughly, You'll be able to generate tags for almost 6000+ bookmarks for less than $1.+For text tagging, we use the `gpt-6-luna` model. This model is [extremely cheap](https://openai.com/business/pricing/#api). Cost per inference varies depending on the content size per article. Though, roughly, You'll be able to generate tags for almost 6000+ bookmarks for less than $1.## Image Taggingdiff --git a/packages/e2e_tests/setup/aimock/inference.json b/packages/e2e_tests/setup/aimock/inference.jsonindex 6d964a21..b0d8c884 100644--- a/packages/e2e_tests/setup/aimock/inference.json+++ b/packages/e2e_tests/setup/aimock/inference.json@@ -395,7 +395,7 @@},{"match": {- "model": "gpt-5.6-luna",+ "model": "gpt-6-luna","responseFormat": "json_schema","userMessage": "automatic tagging for a read-it-later/bookmarking app"},@@ -405,7 +405,7 @@},{"match": {- "model": "gpt-5.6-luna",+ "model": "gpt-6-luna","userMessage": "Summarize the following content responding ONLY with the summary."},"response": {diff --git a/packages/shared/config.ts b/packages/shared/config.tsindex 41a12c4b..212ffe68 100644--- a/packages/shared/config.ts+++ b/packages/shared/config.ts@@ -88,7 +88,7 @@ const allEnv = z.object({SEMANTIC_SEARCH_ENABLED: stringBool("true"),INFERENCE_JOB_TIMEOUT_SEC: z.coerce.number().default(30),INFERENCE_FETCH_TIMEOUT_SEC: z.coerce.number().default(300),- INFERENCE_TEXT_MODEL: z.string().default("gpt-5.6-luna"),+ INFERENCE_TEXT_MODEL: z.string().default("gpt-6-luna"),INFERENCE_IMAGE_MODEL: z.string().default("gpt-4o-mini"),EMBEDDING_ENABLE_AUTO_INDEXING: optionalStringBool(),EMBEDDING_OPENAI_API_KEY: z.string().optional(),