{"id":34062948,"url":"https://github.com/amikos-tech/chromadb-data-pipes","last_synced_at":"2026-04-01T23:02:14.334Z","repository":{"id":212117695,"uuid":"730750850","full_name":"amikos-tech/chromadb-data-pipes","owner":"amikos-tech","description":"ChromaDB Data Pipes 🖇️ - The easiest way to get data into and out of ChromaDB","archived":false,"fork":false,"pushed_at":"2024-10-22T11:37:47.000Z","size":4488,"stargazers_count":20,"open_issues_count":32,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-11-27T17:30:12.110Z","etag":null,"topics":["ai","chromadb","machine-learning","ml","mlops","pipeline"],"latest_commit_sha":null,"homepage":"https://datapipes.chromadb.dev/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/amikos-tech.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-12-12T15:39:13.000Z","updated_at":"2025-10-14T08:03:55.000Z","dependencies_parsed_at":"2023-12-12T17:49:50.600Z","dependency_job_id":"167e9542-9d42-431a-91ef-6fcc2a8d5d50","html_url":"https://github.com/amikos-tech/chromadb-data-pipes","commit_stats":null,"previous_names":["amikos-tech/chromadb-hfds","amikos-tech/chromadb-data-pump"],"tags_count":12,"template":false,"template_full_name":null,"purl":"pkg:github/amikos-tech/chromadb-data-pipes","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amikos-tech%2Fchromadb-data-pipes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amikos-tech%2Fchromadb-data-pipes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amikos-tech%2Fchromadb-data-pipes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amikos-tech%2Fchromadb-data-pipes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/amikos-tech","download_url":"https://codeload.github.com/amikos-tech/chromadb-data-pipes/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amikos-tech%2Fchromadb-data-pipes/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27717892,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-12-14T02:00:11.348Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","chromadb","machine-learning","ml","mlops","pipeline"],"created_at":"2025-12-14T05:01:17.142Z","updated_at":"2025-12-14T05:01:21.001Z","avatar_url":"https://github.com/amikos-tech.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ChromaDB Data Pipes 🖇️ - The easiest way to get data into and out of ChromaDB\n\nChromaDB Data Pipes is a collection of tools to build data pipelines for Chroma DB, inspired by the Unix philosophy of\n\"do one thing and do it well\".\n\nRoadmap:\n\n- ✅ Integration with LangChain 🦜🔗\n- 🚫 Integration with LlamaIndex 🦙\n- ✅ Support more than `all-MiniLM-L6-v2` as embedding functions (head over\n  to [Embedding Processors](https://datapipes.chromadb.dev/processors/embedding/) for more info)\n- 🚫 Multimodal support\n- ♾️ Much more!\n\n## Installation\n\n```bash\npip install chromadb-data-pipes\n```\n\n## Usage\n\n**Get help:**\n\n```bash\ncdp --help\n```\n\n### Example Use Cases\n\nThis is a short list of use cases to evaluate whether this is the right tool for your needs:\n\n- Importing large datasets from local documents (PDF, TXT, etc.), from HuggingFace, from local persisted Chroma DB or\n  even another remote Chroma DB.\n- Exporting large dataset to HuggingFace or any other dataformat supported by the library (if your format is not\n  supported, either implement it in a small function or open an issue)\n- Create a dataset from your data that you can share with others (including the embeddings)\n- Clone Collection with different embedding function, distance function, and other HNSW fine-tuning parameters\n- Re-embed documents in a collection with a different embedding function\n- Backup your data to a `jsonl` file\n- Use other existing unix or other tools to transform your data after exporting from or before importing into Chroma DB\n\n### Importing\n\n**Import data from HuggingFace Datasets to `.jsonl` file:**\n\n```bash\ncdp ds-get \"hf://tazarov/chroma-qna?split=train\" \u003e chroma-qna.jsonl\n```\n\n**Import data from HuggingFace Datasets to Chroma DB:**\n\nThe below command will import the `train` split of the given dataset to Chroma chroma-qna `chroma-qna` collection. The\ncollection will be created if it does not exist and documents will be upserted.\n\n```bash\ncdp ds-get \"hf://tazarov/chroma-qna?split=train\" | cdp import \"http://localhost:8000/chroma-qna\" --upsert --create\n```\n\n**Importing from a directory with PDF files into Local Persisted Chroma DB:**\n\n```bash\ncdp imp pdf sample-data/papers/ | grep \"2401.02412.pdf\" | head -1 | cdp chunk -s 500 | cdp embed --ef default | cdp import \"file://chroma-data/my-pdfs\" --upsert --create\n```\n\n\u003e Note: The above command will import the first PDF file from the `sample-data/papers/` directory, chunk it into 500\n\u003e word chunks, embed each chunk and import the chunks to the `my-pdfs` collection in Chroma DB.\n\n### Exporting\n\n**Export data from Local Persisted Chroma DB to `.jsonl` file:**\n\nThe below command will export the first 10 documents from the `chroma-qna` collection to `chroma-qna.jsonl` file.\n\n```bash\ncdp export \"file://chroma-data/chroma-qna\" --limit 10 \u003e chroma-qna.jsonl\n```\n\n**Export data from Local Persisted Chroma DB to `.jsonl` file with filter:**\n\nThe below command will export data from local persisted Chroma DB to a `.jsonl` file using a `where` filter to select\nthe documents to export.\n\n```bash\ncdp export \"file://chroma-data/chroma-qna\" --where '{\"document_id\": \"123\"}' \u003e chroma-qna.jsonl\n```\n\n**Export data from Chroma DB to HuggingFace Datasets:**\n\nThe below command will export the first 10 documents with offset 10 from the `chroma-qna` collection to HuggingFace\nDatasets `tazarov/chroma-qna` dataset. The dataset will be uploaded to HF.\n\n\u003e HF Auth and Privacy: Make sure you have `HF_TOKEN=hf_....` environment variable set. If you want your dataset to\n\u003e be private, add `--private` flag to the `cdp ds-put` command.\n\n```bash\ncdp export \"http://localhost:8000/chroma-qna\" --limit 10 --offset 10 | cdp ds-put \"hf://tazarov/chroma-qna-modified\"\n```\n\nTo export a dataset to a file, use `--uri` with `file://` prefix:\n\n```bash\ncdp export \"http://localhost:8000/chroma-qna\" --limit 10 --offset 10 | cdp ds-put \"file://chroma-qna\"\n```\n\n\u003e File Location The file is relative to the current working directory.\n\n### Processing\n\n**Copy collection from one Chroma collection to another and re-embed the documents:**\n\n```bash\ncdp export \"http://localhost:8000/chroma-qna\" | cdp embed --ef default | cdp import \"http://localhost:8000/chroma-qna-def-emb\" --upsert --create\n```\n\n\u003e Note: See [Embedding Processors](./processors/embedding.md) for more info about supported embedding functions.\n\n**Import dataset from HF to Local Persisted Chroma and embed the documents:**\n\n```bash\ncdp ds-get \"hf://tazarov/ds2?split=train\" | cdp embed --ef default | cdp import \"file://chroma-data/chroma-qna-def-emb-hf\" --upsert --create\n```\n\n**Chunk Large Documents:**\n\n```bash\ncdp imp pdf sample-data/papers/ | grep \"2401.02412.pdf\" | head -1 | cdp chunk -s 500\n```\n\n### Misc\n\n**Count the number of documents in a collection:**\n\n```bash\ncdp export \"http://localhost:8000/chroma-qna\" | wc -l\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famikos-tech%2Fchromadb-data-pipes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famikos-tech%2Fchromadb-data-pipes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famikos-tech%2Fchromadb-data-pipes/lists"}