diff options
Diffstat (limited to '')
| -rw-r--r-- | docs/docs/03-configuration/02-different-ai-providers.md (renamed from docs/versioned_docs/version-v0.25.0/14-Guides/05-different-ai-providers.md) | 48 | ||||
| -rw-r--r-- | docs/versioned_docs/version-v0.25.0/14-Guides/01-legacy-container-upgrade.md | 66 | ||||
| -rw-r--r-- | docs/versioned_docs/version-v0.25.0/14-Guides/02-search-query-language.md | 71 | ||||
| -rw-r--r-- | docs/versioned_docs/version-v0.25.0/14-Guides/04-hoarder-to-karakeep-migration.md | 28 | ||||
| -rw-r--r-- | docs/versioned_docs/version-v0.30.0/05-integrations/05-singlefile.md (renamed from docs/versioned_docs/version-v0.25.0/14-Guides/03-singlefile.md) | 0 |
5 files changed, 48 insertions, 165 deletions
diff --git a/docs/versioned_docs/version-v0.25.0/14-Guides/05-different-ai-providers.md b/docs/docs/03-configuration/02-different-ai-providers.md index 33408c00..7d1a4589 100644 --- a/docs/versioned_docs/version-v0.25.0/14-Guides/05-different-ai-providers.md +++ b/docs/docs/03-configuration/02-different-ai-providers.md @@ -18,6 +18,28 @@ OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Ollama is a local LLM provider that you can use to run your own LLM server. You'll need to pass ollama's address to karakeep and you need to ensure that it's accessible from within the karakeep container (e.g. no localhost addresses). +Ollama provides two API endpoints: + +1. **OpenAI-compatible API (Recommended)** - Uses the `/v1` chat endpoint which handles message formatting automatically +2. **Native Ollama API** - Requires manual formatting for some models + +### Option 1: OpenAI-compatible API (Recommended) + +This approach uses Ollama's OpenAI-compatible endpoint and is more reliable with various models: + +``` +OPENAI_API_KEY=ollama +OPENAI_BASE_URL=http://ollama.mylab.com:11434/v1 + +# Make sure to pull the models in ollama first. Example models: +INFERENCE_TEXT_MODEL=gemma3 +INFERENCE_IMAGE_MODEL=llava +``` + +### Option 2: Native Ollama API + +Alternatively, you can use the native Ollama API: + ``` # MAKE SURE YOU DON'T HAVE OPENAI_API_KEY set, otherwise it takes precedence. @@ -31,6 +53,10 @@ INFERENCE_IMAGE_MODEL=llava # INFERENCE_OUTPUT_SCHEMA=plain ``` +:::tip +If you experience issues with certain models (especially OpenAI's gpt-oss models or other models requiring specific chat formats), try using the OpenAI-compatible API endpoint instead. +::: + ## Gemini Gemini has an OpenAI-compatible API. You need to get an api key from Google AI Studio. @@ -64,3 +90,25 @@ OPENAI_API_KEY: Your Perplexity API Key INFERENCE_TEXT_MODEL: sonar-pro INFERENCE_IMAGE_MODEL: sonar-pro ``` + +## Azure + +Azure has an OpenAI-compatible API. + +You can get your API key from the Overview page of the Azure AI Foundry Portal or via "Keys + Endpoints" on the resource in the Azure Portal. + +:::warning +The [model name is the deployment name](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/switching-endpoints#keyword-argument-for-model) you specified when deploying the model, which may differ from the base model name. +::: + +``` +# Deployed via Azure AI Foundry: +OPENAI_BASE_URL=https://{your-azure-ai-foundry-resource-name}.cognitiveservices.azure.com/openai/v1/ + +# Deployed via Azure OpenAI Service: +OPENAI_BASE_URL=https://{your-azure-openai-resource-name}.openai.azure.com/openai/v1/ + +OPENAI_API_KEY=YOUR_API_KEY +INFERENCE_TEXT_MODEL=YOUR_DEPLOYMENT_NAME +INFERENCE_IMAGE_MODEL=YOUR_DEPLOYMENT_NAME +``` diff --git a/docs/versioned_docs/version-v0.25.0/14-Guides/01-legacy-container-upgrade.md b/docs/versioned_docs/version-v0.25.0/14-Guides/01-legacy-container-upgrade.md deleted file mode 100644 index d95c1c1e..00000000 --- a/docs/versioned_docs/version-v0.25.0/14-Guides/01-legacy-container-upgrade.md +++ /dev/null @@ -1,66 +0,0 @@ -# Legacy Container Upgrade - -Karakeep's 0.16 release consolidated the web and worker containers into a single container and also dropped the need for the redis container. The legacy containers will stop being supported soon, to upgrade to the new container do the following: - -1. Remove the redis container and its volume if it had one. -2. Move the environment variables that you've set exclusively to the `workers` container to the `web` container. -3. Delete the `workers` container. -4. Rename the web container image from `hoarder-app/hoarder-web` to `hoarder-app/hoarder`. - -```diff -diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml -index cdfc908..6297563 100644 ---- a/docker/docker-compose.yml -+++ b/docker/docker-compose.yml -@@ -1,7 +1,7 @@ - version: "3.8" - services: - web: -- image: ghcr.io/hoarder-app/hoarder-web:${KARAKEEP_VERSION:-release} -+ image: ghcr.io/karakeep-app/karakeep:${KARAKEEP_VERSION:-release} - restart: unless-stopped - volumes: - - data:/data -@@ -10,14 +10,10 @@ services: - env_file: - - .env - environment: -- REDIS_HOST: redis - MEILI_ADDR: http://meilisearch:7700 -+ BROWSER_WEB_URL: http://chrome:9222 -+ # OPENAI_API_KEY: ... - DATA_DIR: /data -- redis: -- image: redis:7.2-alpine -- restart: unless-stopped -- volumes: -- - redis:/data - chrome: - image: gcr.io/zenika-hub/alpine-chrome:123 - restart: unless-stopped -@@ -37,24 +33,7 @@ services: - MEILI_NO_ANALYTICS: "true" - volumes: - - meilisearch:/meili_data -- workers: -- image: ghcr.io/hoarder-app/hoarder-workers:${KARAKEEP_VERSION:-release} -- restart: unless-stopped -- volumes: -- - data:/data -- env_file: -- - .env -- environment: -- REDIS_HOST: redis -- MEILI_ADDR: http://meilisearch:7700 -- BROWSER_WEB_URL: http://chrome:9222 -- DATA_DIR: /data -- # OPENAI_API_KEY: ... -- depends_on: -- web: -- condition: service_started - - volumes: -- redis: - meilisearch: - data: -``` diff --git a/docs/versioned_docs/version-v0.25.0/14-Guides/02-search-query-language.md b/docs/versioned_docs/version-v0.25.0/14-Guides/02-search-query-language.md deleted file mode 100644 index be9739b4..00000000 --- a/docs/versioned_docs/version-v0.25.0/14-Guides/02-search-query-language.md +++ /dev/null @@ -1,71 +0,0 @@ -# Search Query Language - -Karakeep provides a search query language to filter and find bookmarks. Here are all the supported qualifiers and how to use them: - -## Basic Syntax - -- Use spaces to separate multiple conditions (implicit AND) -- Use `and`/`or` keywords for explicit boolean logic -- Use parentheses `()` for grouping conditions -- Prefix qualifiers with `-` to negate them - -## Qualifiers - -Here's a comprehensive table of all supported qualifiers: - -| Qualifier | Description | Example Usage | -| -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------- | -| `is:fav` | Favorited bookmarks | `is:fav` | -| `is:archived` | Archived bookmarks | `-is:archived` | -| `is:tagged` | Bookmarks that has one or more tags | `is:tagged` | -| `is:inlist` | Bookmarks that are in one or more lists | `is:inlist` | -| `is:link`, `is:text`, `is:media` | Bookmarks that are of type link, text or media | `is:link` | -| `url:<value>` | Match bookmarks with URL substring | `url:example.com` | -| `#<tag>` | Match bookmarks with specific tag | `#important` | -| | Supports quoted strings for tags with spaces | `#"work in progress"` | -| `list:<name>` | Match bookmarks in specific list | `list:reading` | -| | Supports quoted strings for list names with spaces | `list:"to review"` | -| `after:<date>` | Bookmarks created on or after date (YYYY-MM-DD) | `after:2023-01-01` | -| `before:<date>` | Bookmarks created on or before date (YYYY-MM-DD) | `before:2023-12-31` | -| `feed:<name>` | Bookmarks imported from a particular rss feed | `feed:Hackernews` | -| `age:<time-range>` | Match bookmarks based on how long ago they were created. Use `<` or `>` to indicate the maximum / minimum age of the bookmarks. Supported units: `d` (days), `w` (weeks), `m` (months), `y` (years). | `age:<1d` `age:>2w` `age:<6m` `age:>3y` | - -### Examples - -```plaintext -# Find favorited bookmarks from 2023 that are tagged "important" -is:fav after:2023-01-01 before:2023-12-31 #important - -# Find archived bookmarks that are either in "reading" list or tagged "work" -is:archived and (list:reading or #work) - -# Find bookmarks that are not tagged or not in any list --is:tagged or -is:inlist -``` - -## Combining Conditions - -You can combine multiple conditions using boolean logic: - -```plaintext -# Find favorited bookmarks from 2023 that are tagged "important" -is:fav after:2023-01-01 before:2023-12-31 #important - -# Find archived bookmarks that are either in "reading" list or tagged "work" -is:archived and (list:reading or #work) - -# Find bookmarks that are not favorited and not archived --is:fav -is:archived -``` - -## Text Search - -Any text not part of a qualifier will be treated as a full-text search: - -```plaintext -# Search for "machine learning" in bookmark content -machine learning - -# Combine text search with qualifiers -machine learning is:fav -``` diff --git a/docs/versioned_docs/version-v0.25.0/14-Guides/04-hoarder-to-karakeep-migration.md b/docs/versioned_docs/version-v0.25.0/14-Guides/04-hoarder-to-karakeep-migration.md deleted file mode 100644 index 289a091c..00000000 --- a/docs/versioned_docs/version-v0.25.0/14-Guides/04-hoarder-to-karakeep-migration.md +++ /dev/null @@ -1,28 +0,0 @@ -# Hoarder to Karakeep Migration - -Hoarder is rebranding to Karakeep. Due to github limitations, the old docker image might not be getting new updates after the rebranding. You might need to update your docker image to point to the new karakeep image instead by applying the following change in the docker compose file. - -```diff -diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml -index cdfc908..6297563 100644 ---- a/docker/docker-compose.yml -+++ b/docker/docker-compose.yml -@@ -1,7 +1,7 @@ - version: "3.8" - services: - web: -- image: ghcr.io/hoarder-app/hoarder:${HOARDER_VERSION:-release} -+ image: ghcr.io/karakeep-app/karakeep:${HOARDER_VERSION:-release} -``` - -You can also change the `HOARDER_VERSION` environment variable but if you do so remember to change it in the `.env` file as well. - -## Migrating a Baremetal Installation - -If you previously used the [Debian/Ubuntu install script](https://docs.karakeep.app/Installation/debuntu) to install Hoarder, there is an option to migrate your installation to Karakeep. - -```bash -bash karakeep-linux.sh migrate -``` - -This will migrate your installation with no user input required. After the migration, the script will also check for an update. diff --git a/docs/versioned_docs/version-v0.25.0/14-Guides/03-singlefile.md b/docs/versioned_docs/version-v0.30.0/05-integrations/05-singlefile.md index c0f4e174..c0f4e174 100644 --- a/docs/versioned_docs/version-v0.25.0/14-Guides/03-singlefile.md +++ b/docs/versioned_docs/version-v0.30.0/05-integrations/05-singlefile.md |