{"id":29636535,"url":"https://github.com/activeloopai/activeloop-self-hosted-resources","last_synced_at":"2026-02-05T07:31:32.993Z","repository":{"id":303924520,"uuid":"1017218854","full_name":"activeloopai/activeloop-self-hosted-resources","owner":"activeloopai","description":"Official Helm charts for deploying Activeloop services on Kubernetes","archived":false,"fork":false,"pushed_at":"2025-12-25T07:43:49.000Z","size":10567,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-26T20:53:07.720Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Smarty","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/activeloopai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-07-10T07:50:45.000Z","updated_at":"2025-11-19T07:17:45.000Z","dependencies_parsed_at":"2025-07-10T14:55:13.918Z","dependency_job_id":"0c5e4ed8-b2ed-48ac-8200-5b6d75a0a835","html_url":"https://github.com/activeloopai/activeloop-self-hosted-resources","commit_stats":null,"previous_names":["activeloopai/activeloop-helm-charts","activeloopai/activeloop-self-hosted-resources"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/activeloopai/activeloop-self-hosted-resources","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/activeloopai%2Factiveloop-self-hosted-resources","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/activeloopai%2Factiveloop-self-hosted-resources/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/activeloopai%2Factiveloop-self-hosted-resources/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/activeloopai%2Factiveloop-self-hosted-resources/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/activeloopai","download_url":"https://codeload.github.com/activeloopai/activeloop-self-hosted-resources/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/activeloopai%2Factiveloop-self-hosted-resources/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29115528,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-05T05:31:32.482Z","status":"ssl_error","status_checked_at":"2026-02-05T05:31:29.075Z","response_time":65,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-07-21T17:05:05.459Z","updated_at":"2026-02-05T07:31:32.987Z","avatar_url":"https://github.com/activeloopai.png","language":"Smarty","funding_links":[],"categories":[],"sub_categories":[],"readme":"# activeloop-self-hosted-resources\n\n## Available Deployments\n\n### Activeloop Neohorizon\n\n- [K8s](./helm/activeloop-neohorizon/)\n- [docker-compose](./docker-compose/activeloop-neohorizon/)\n\n#### Parameters\n\n| Helm Parameter                                  | Environment Variable                            | Default Value                                                | Descriptoin                                                                       |\n| ----------------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------ | --------------------------------------------------------------------------------- |\n| deeplake_creds                                  | DEEPLAKE_CREDS                                  | -                                                            | Refer to [Deeplake storage credentials](./README.md#deeplake-storage-credentials) |\n| deeplake_root_dir                               | DEEPLAKE_ROOT_DIR                               | for `helm` required, for docker-compose: `/var/lib/deeplake` | storage path used by deeplake for data operations                                 |\n| postgres_database                               | POSTGRES_DATABASE                               | neohorizon                                                   | virtual database name to use by app,\u003c/br\u003e must be created beforehand              |\n| postgres_host                                   | POSTGRES_HOST                                   | k8s service host of postgres dependency                      | postgres database hostname (required)                                             |\n| postgres_password                               | POSTGRES_PASSWORD                               | postgres                                                     | postgres database user password                                                   |\n| postgres_user                                   | POSTGRES_USER                                   | postgres                                                     | postgres database username                                                        |\n| postgres_port                                   | POSTGRES_PORT                                   | 5432                                                         | postgres database port                                                            |\n| rabbitmq_url                                    | RABBITMQ_URL                                    | -                                                            | rabbitmq ampq url, default will be built from dependency installation (required)  |\n| al_api_token                                    | AL_API_TOKEN                                    | - (required)                                                 | api token to authenticate to deployed api                                         |\n| gemini_api_key                                  | GEMINI_API_KEY                                  | -                                                            | optional to run geminy requests                                                   |\n| openai_api_key                                  | OPENAI_API_KEY                                  | -                                                            | needed for query generation                                                       |\n| text_image__matrix_of_embeddings__ingestion_url | TEXT_IMAGE__MATRIX_OF_EMBEDDINGS__INGESTION_URL | -                                                            | should be full path to endpoint triton inference endpoint                         |\n| text_image__matrix_of_embeddings__query_url     | TEXT_IMAGE__MATRIX_OF_EMBEDDINGS__QUERY_URL     | -                                                            | should be full path to endpoint triton inference endpoint                         |\n| text_image__embedding__ingestion_url            | TEXT_IMAGE__EMBEDDING__INGESTION_URL            | -                                                            | should be full path to endpoint triton inference endpoint                         |\n| text_image__embedding__query_url                | TEXT_IMAGE__EMBEDDING__QUERY_URL                | -                                                            | should be full path to endpoint triton inference endpoint                         |\n| text__embedding__ingestion_url                  | TEXT__EMBEDDING__INGESTION_URL                  | -                                                            | should be full path to endpoint triton inference endpoint                         |\n| text__embedding__query_url                      | TEXT__EMBEDDING__QUERY_URL                      | -                                                            | should be full path to endpoint triton inference endpoint                         |\n\n#### Models usage\n\nNeohorizon works with triton served models for embedding generation both for queries and ingestion. Both helm chart and docker-compose are providing options to run models.\nHere are descriptions of models:\n\n##### Models that [Activeloop](chat.activeloop.ai) uses\n\n- **colnomic**: can be used for ingest/retrieval of images, suggested to provide at least **16GiB** RAM and **A100** GPU\n- **inf-retriever-v1**: can be used for ingest/retrieval of texts, suggested to provide at least **4GiB** RAM and **A10/L4** GPU\n- **doclayout_parser**: can be used to generate images for answers, suggested to provide at least **4GiB** RAM and **A10/L4** GPU\n\n##### Additional models we provide\n\n- **qwen_06B**: can be used for ingest/retrieval, suggested to provide at least **4GiB** RAM and **A10/L4** GPU\n\n\u003e Note. Any custom models can be used with neohorizon, only requirement is that models must be served with triton and full URLs must be set in deployment environment variables.\n\nFor both helm chart and docker-compose cases default configuration should be reviewed or adjusted to use models.\n\n- case 1: deployed only image model, then values override yaml would look like\n\n  ```yaml\n  ...\n  global:\n    config:\n      text_image__matrix_of_embeddings__ingestion_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text_image__matrix_of_embeddings__query_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text_image__embedding__ingestion_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text_image__embedding__query_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n  ...\n  models:\n    - name: models\n      load_models:\n        - colnomic\n  ```\n\n- case 2: deployed all models with single deployment\n\n  ```yaml\n  ...\n  global:\n    config:\n      text_image__matrix_of_embeddings__ingestion_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text_image__matrix_of_embeddings__query_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text_image__embedding__ingestion_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text_image__embedding__query_url: http://activeloop-neohorizon-models-svc/v2/models/colnomic/infer\n      text__embedding__ingestion_url: http://activeloop-neohorizon-models-svc/v2/models/inf-retriever-v1/infer\n      text__embedding__query_url: http://activeloop-neohorizon-models-svc/v2/models/inf-retriever-v1/infer\n  ...\n  models:\n    - name: models\n      load_models:\n        - colnomic\n        - inf-retriever-v1\n  ```\n\n- case 3: separate deployments for image and text\n\n  ```yaml\n  ...\n  global:\n    config:\n      text_image__matrix_of_embeddings__ingestion_url: http://activeloop-neohorizon-colnomic-svc/v2/models/colnomic/infer\n      text_image__matrix_of_embeddings__query_url: http://activeloop-neohorizon-colnomic-svc/v2/models/colnomic/infer\n      text_image__embedding__ingestion_url: http://activeloop-neohorizon-colnomic-svc/v2/models/colnomic/infer\n      text_image__embedding__query_url: http://activeloop-neohorizon-colnomic-svc/v2/models/colnomic/infer\n      text__embedding__ingestion_url: http://activeloop-neohorizon-text-svc/v2/models/inf-retriever-v1/infer\n      text__embedding__query_url: http://activeloop-neohorizon-text-svc/v2/models/inf-retriever-v1/infer\n  ...\n  models:\n    - name: colnomic\n      load_models:\n        - colnomic\n    ...\n    - name: text\n      load_models:\n        - inf-retriever-v1\n  ```\n\n#### Deeplake storage credentials\n\nIn the case cloud storage is used (s3, gs, azure blob storage) and underlaying infrastructure does not provide out of the box authentication to the storage,\nstatic credentials should be applied as enviornment variable so deeplake can do storge operations.\nTo give credentials to deeplake, use `DEEPLAKE_CREDS` environment variable or corresponding Cloud SKD Environment variables.\n`DEEPLAKE_CREDS` must be an string serialized dictionary with cloud credentials, examples below.\n\n- **AWS**:\n\n    ```jsonc\n    {\n      \"aws_access_key_id\": \"AWS_ACCESS_KEY_ID\",\n      \"aws_secret_access_key\": \"AWS_SECRET_ACCESS_KEY\",\n      \"aws_session_token\": \"AWS_SESSION_TOKEN\",          // Optional\n      \"endpoint_url\": \"https://s3.customerendpoint.com\", // OPTIONAL\n      \"region_name\": \"AWS_REGION\"                       // OPTIONAL\n    }\n    ```\n\n    or\n\n    ```jsonc\n    {\n      \"profile_name\": \"AWS_PROFILE\",\n      \"endpoint_url\": \"https://s3.customerendpoint.com\",  // OPTIONAL\n      \"region_name\": \"AWS_REGION\"                 // OPTIONAL\n    }\n    ```\n\n    or\n\n    ```jsonc\n    {\n      \"profile_name\": \"AWS_PROFILE\",\n      \"endpoint_url\": \"https://s3.customerendpoint.com\",  // OPTIONAL\n      \"region_name\": \"AWS_REGION\"                         // OPTIONAL\n    }\n    ```\n\n    or\n\n    ```jsonc\n    {\n      \"aws_role_arn\": \"AWS_ROLE_ARN\",\n      \"aws_session_name\": \"session-name-for-assume-role\",\n      \"aws_external_id\": \"external-id-for-assume-role\",\n      \"endpoint_url\": \"https://s3.customerendpoint.com\",  // OPTIONAL\n      \"region_name\": \"AWS_REGION\"                         // OPTIONAL\n    }\n\n- **AZURE**:\n\n  ```jsonc\n  {\n    \"azure_client_id\": \"AZURE_CLIENT_ID\",\n    \"azure_client_secret\": \"AZURE_CLIENT_SECRET\",\n    \"azure_tenant_id\": \"AZURE_TENANT\"\n  }\n  ```\n\n  or\n\n  ```jsonc\n  {\n    \"sas_token\": \"azure-storage-sas-token\"\n  }\n  ```\n\n  or\n\n  ```jsonc\n  {\n    \"account_name\": \"...\",\n    \"container_name\": \"...\",\n    \"account_key\": \"...\",\n  }\n  ```\n\n- **GCP**:\n\n  ```jsonc\n  {\n    \"json_credentials\": \"SERVICE_ACCOUNT_JSON_KEY\"\n  }\n  ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Factiveloopai%2Factiveloop-self-hosted-resources","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Factiveloopai%2Factiveloop-self-hosted-resources","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Factiveloopai%2Factiveloop-self-hosted-resources/lists"}