doccano-mini
doccano-mini is a few-shot annotation tool to assist the development of applications with Large language models (LLMs). Once you annotate a few text, you can solve your task (e.g. text classification) with LLMs via LangChain.
At this time, the following tasks are supported:
- Text classification
- Question answering
- Summarization
- Paraphrasing
- Named Entity Recognition
- Task Free
Note: This is an experimental project.
Installation
pip install doccano-mini
Usage
For this example, we will be using OpenAI’s APIs, so we need to set the environment variable in the terminal.
export OPENAI_API_KEY="..."
Then, we can run the server.
doccano-mini
Now, we can open the browser and go to http://localhost:8501/ to see the interface.
Step1: Annotate a few text
In this step, we will annotate a few text. We can add a new text by clicking the + button. Try it out by double-clicking on any cell. You'll notice you can edit all cell values.
The editor also supports pasting in tabular data from Google Sheets, Excel, and many other similar tools.
Step2: Test your task
In this step, we will test your task. We can enter a new test to the text box and click the Predict button. Then, we can see the result of the test.
Step3: Download the config
In this step, we will download the LangChain's config. We can click the Download button to download it. After loading the config file, we can predict a label for the new text.
from langchain.chains import load_chain
chain = load_chain("chain.yaml")
chain.run("YOUR TEXT")
Development
poetry install
streamlit run doccano_mini/home.py
Metadata
Release files for doccano-mini 0.0.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| doccano_mini-0.0.10.tar.gz | 12.9 kB | Without provenance | Details for doccano_mini-0.0.10.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| doccano_mini-0.0.10-py3-none-any.whl | Python 3 | none | any | Details for doccano_mini-0.0.10-py3-none-any.whl |
Total release size: 33.6 kB
Release files / doccano_mini-0.0.10.tar.gz
| Download URL | doccano_mini-0.0.10.tar.gz |
|---|---|
| Size | 12.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4f56240e56b7e76afdaf6188c13de0d3ca8980328a14cb57448511f603e8da5f
|
|
BLAKE2b-256 checksum How to use checksums |
37d26a41f8761b5a961b269cd8aeffb43705f51a11e46cdd28ddcfdcfab8276a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.16
|
Release files / doccano_mini-0.0.10-py3-none-any.whl
| Download URL | doccano_mini-0.0.10-py3-none-any.whl |
|---|---|
| Size | 20.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
bc39c2e3ff44b1b7b3227dd7ef824c680030727809d8691774d7bfa2de49b500
|
|
BLAKE2b-256 checksum How to use checksums |
b3c74c20efc74a155b90cb99b8decfa8c58815486359ffc6e6c2e8892e07ca08
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.16
|
Security for doccano-mini 0.0.10
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.