Skip to main content

Document Understanding Engine for AI

Project description

Vectorless

PyPI PyPI Downloads

Knowing by reasoning, not vectors.

Deep and reliable. Vectorless plays nicely with your documents. Ask questions in plain language; get answers by reasoning with Vectorless.

Installation

Install using pip install -U vectorless. For more details, see the Installation section in the documentation.

A Simple Example

import asyncio
from vectorless import Engine

async def main():
    engine = Engine(api_key="sk-...", model="gpt-4o", endpoint="https://api.openai.com/v1")

    # Compile a document
    result = await engine.compile(path="./report.pdf")
    doc_id = result.doc_id

    # Ask a question
    response = await engine.ask("What is the total revenue?", doc_ids=[doc_id])
    print(response.single().content)

asyncio.run(main())

Help

See documentation for more details.

Contributing

Contributions welcome! See Contributing for setup and guidelines.

License

Apache License 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vectorless-0.1.12.tar.gz (317.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vectorless-0.1.12-cp310-cp310-manylinux_2_34_x86_64.whl (5.0 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.34+ x86-64

File details

Details for the file vectorless-0.1.12.tar.gz.

File metadata

  • Download URL: vectorless-0.1.12.tar.gz
  • Upload date:
  • Size: 317.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: maturin/1.12.6

File hashes

Hashes for vectorless-0.1.12.tar.gz
Algorithm Hash digest
SHA256 eccd5d312bf28e968221580f882a92395ae4bc1da5ed64a3d52efe141aab77d9
MD5 a6187ac243856d106d40a1ab7dccdb0e
BLAKE2b-256 5e27e8547cea14e85b78ab88e6d5e85a7c7e52234e31fb65b5b58469d9a68661

See more details on using hashes here.

File details

Details for the file vectorless-0.1.12-cp310-cp310-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for vectorless-0.1.12-cp310-cp310-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 e12365ca7c31910ce95686eaae7b44fdae9dd627c44f130e9fcdef4610333662
MD5 fa8e5a0589e4d3d16536e073f7956b7a
BLAKE2b-256 f2ecf1bc6100131cdbb12767f6c58bd4396d16ab01dade9f9db5a575d9f1639a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page