Sieves
PulseGate's liveness check found it on 14 Oct 2026; it is registered on GitHub and has been in the index since 26 Jun 2026. How this is checked
Sieves is a library designed for zero-shot document AI, enabling users to build document AI pipelines that produce structured generation without the need for training data. It is intended for rapid prototyping scenarios where validated, structured output is required but annotated datasets are limited or unavailable. The tool brings together common natural language processing utilities, document parsing, and text chunking, making it suitable for developers and researchers…
Inferred · not functionally tested
Overview
5 featuresPurpose: Rapid prototyping of document AI pipelines without training data.
Inferred · not functionally tested
Audience: AI researchers and developers
Inferred · not functionally tested
Functions: data_extraction, rag, workflow_automation
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: unknown · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: API · deployment: api_only, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: sieves.ai · github.com. These links do not verify the individual claims.
Sieves is a RAG, search & retrieval project. Inferred · not functionally tested: Rapid prototyping of document AI pipelines without training data. Inferred · not functionally tested: It is built as an open-source project for AI researchers and developers. Basis unknown · not verified: Sieves is open source under the MIT license. Basis unknown · not verified: Sieves is available on API, and it can be self-hosted.
Sieves first shipped in 2024. Development happens publicly on GitHub with 126 stars and 6 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include zero-shot document AI, structured output, and NLP utilities. Inferred · not functionally tested: Catalogued interfaces include a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Zero-shot document AI
- Structured output
- NLP utilities
- Document parsing
- Pipeline architecture
Topics: Inferred · not functionally tested
Built with & integrations
- multiple
- bLangChain in the HTML
Trust & compliance
Indexing history
What PulseGate has recorded for this listing
Frequently asked questions about Sieves
- What is Sieves?
- Inferred · not functionally tested: Rapid prototyping of document AI pipelines without training data. It is catalogued under RAG, search & retrieval on PulseGate.
- Who should use Sieves?
- Inferred · not functionally tested: Sieves is an open-source project built for AI researchers and developers.
- Is Sieves free?
- Basis unknown · not verified: Yes — Sieves is open source under the MIT license and free to use.
- What platforms does Sieves run on?
- Basis unknown · not verified: Sieves runs on API. It can also be self-hosted.
- Is Sieves still active?
- PulseGate's liveness check found it on 14 Oct 2026. Its GitHub repository shows 6 commits in the last 90 days.
- When did Sieves launch?
- Sieves first shipped in 2024.
- Is Sieves open source?
- Basis unknown · not verified: Yes — Sieves is open source under the MIT license, developed on GitHub.
- Does Sieves have an API or integrations?
- Inferred · not functionally tested: Yes — Sieves exposes a public API.
Similar projects
Closest matches by what these projects do