{"id":48765451,"url":"https://github.com/databendlabs/databend-aiserver","last_synced_at":"2026-04-13T07:49:28.692Z","repository":{"id":326338107,"uuid":"1081585194","full_name":"databendlabs/databend-aiserver","owner":"databendlabs","description":"Databend AI Server extends data warehouse with AI-ready UDFs, seamlessly fusing object storage, embeddings, and SQL pipelines.","archived":false,"fork":false,"pushed_at":"2025-11-28T07:22:45.000Z","size":4012,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-13T07:49:21.993Z","etag":null,"topics":["ai","pipeline","udf","warehouse"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/databendlabs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-10-23T01:51:01.000Z","updated_at":"2025-11-28T07:22:49.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/databendlabs/databend-aiserver","commit_stats":null,"previous_names":["databendlabs/databend-aiserver"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/databendlabs/databend-aiserver","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databendlabs%2Fdatabend-aiserver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databendlabs%2Fdatabend-aiserver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databendlabs%2Fdatabend-aiserver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databendlabs%2Fdatabend-aiserver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/databendlabs","download_url":"https://codeload.github.com/databendlabs/databend-aiserver/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databendlabs%2Fdatabend-aiserver/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31744404,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T06:26:45.479Z","status":"ssl_error","status_checked_at":"2026-04-13T06:26:44.645Z","response_time":93,"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":["ai","pipeline","udf","warehouse"],"created_at":"2026-04-13T07:49:27.676Z","updated_at":"2026-04-13T07:49:28.677Z","avatar_url":"https://github.com/databendlabs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# databend-aiserver\n\n[Databend](https://github.com/databendlabs/databend) AI Server extends any data warehouse with AI-ready UDFs, seamlessly fusing object storage, embeddings, and SQL pipelines.\n\n## Quickstart\n\n```bash\nuv sync\nuv run databend-aiserver --port 8815\n```\n\n## AI Functions\n\n| Function | Signature | Purpose | Output |\n| :--- | :--- | :--- | :--- |\n| **ai_list_files** | `(stage_location, max_files)` | List objects in a stage for inspection/sampling. | Table with file details (`path`, `size`, etc.) |\n| **ai_embed_1024** | `(text)` | Generate 1024-dim embeddings (default: Qwen). | `VECTOR(1024)` |\n| **ai_parse_document** | `(stage_location, path)` | Parse docs (PDF, DOCX, Images, etc.) to Markdown. | `VARIANT` (pages, metadata) |\n\n## Usage\n\n### 1. Register Functions in Databend\n\n```sql\nCREATE OR REPLACE FUNCTION ai_list_files(stage_location STAGE_LOCATION, pattern VARCHAR, max_files INT)\nRETURNS TABLE (stage_name VARCHAR, path VARCHAR, uri VARCHAR, size UINT64, last_modified VARCHAR, etag VARCHAR, content_type VARCHAR)\nLANGUAGE PYTHON HANDLER = 'ai_list_files' ADDRESS = '\u003cyour-ai-server-address\u003e';\n\nCREATE OR REPLACE FUNCTION ai_embed_1024(text VARCHAR)\nRETURNS VECTOR(1024)\nLANGUAGE PYTHON HANDLER = 'ai_embed_1024' ADDRESS = '\u003cyour-ai-server-address\u003e';\n\nCREATE OR REPLACE FUNCTION ai_parse_document(stage_location STAGE_LOCATION, file_path VARCHAR)\nRETURNS VARIANT\nLANGUAGE PYTHON HANDLER = 'ai_parse_document' ADDRESS = '\u003cyour-ai-server-address\u003e';\n```\n\n### 2. Run Queries\n\n```sql\n-- Setup Stage\nCREATE CONNECTION my_s3_conn STORAGE_TYPE = 's3' ACCESS_KEY_ID = '...' SECRET_ACCESS_KEY = '...';\nCREATE STAGE docs_stage URL='s3://load/files/' CONNECTION = (CONNECTION_NAME = 'my_s3_conn');\n\n-- Execute AI Functions\nSELECT * FROM ai_list_files(@docs_stage, 50);\nSELECT ai_embed_1024(doc_body) FROM docs_tbl;\nSELECT ai_parse_document(@docs_stage, 'reports/q1.pdf');\n```\n\n## Development\n\n```bash\n# Run full test suite\nuv run pytest\n```\n\n---\n\nBuilt by the [Databend](https://github.com/databendlabs/databend) team.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatabendlabs%2Fdatabend-aiserver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatabendlabs%2Fdatabend-aiserver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatabendlabs%2Fdatabend-aiserver/lists"}