| Name | doccano-mini JSON |
| Version |
0.0.10
JSON |
| download |
| home_page | https://github.com/doccano/doccano-mini |
| Summary | Annotation meets Large Language Models. |
| upload_time | 2023-04-04 04:55:23 |
| maintainer | |
| docs_url | None |
| author | Hironsan |
| requires_python | >=3.8, !=2.7.*, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*, !=3.7.* |
| license | MIT |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# 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](https://github.com/hwchase17/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
```bash
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.
```bash
export OPENAI_API_KEY="..."
```
Then, we can run the server.
```bash
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.
<img src="https://raw.githubusercontent.com/doccano/doccano-mini/master/docs/images/test_new_example.jpg" alt= “Step2” width="700">
### Step3: Download the config
In this step, we will download the [LangChain](https://github.com/hwchase17/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.
```python
from langchain.chains import load_chain
chain = load_chain("chain.yaml")
chain.run("YOUR TEXT")
```
## Development
```bash
poetry install
streamlit run doccano_mini/home.py
```
Raw data
{
"_id": null,
"home_page": "https://github.com/doccano/doccano-mini",
"name": "doccano-mini",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8, !=2.7.*, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*, !=3.7.*",
"maintainer_email": "",
"keywords": "",
"author": "Hironsan",
"author_email": "hiroki.nakayama.py@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/37/d2/6a41f8761b5a961b269cd8aeffb43705f51a11e46cdd28ddcfdcfab8276a/doccano_mini-0.0.10.tar.gz",
"platform": null,
"description": "# doccano-mini\n\ndoccano-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](https://github.com/hwchase17/langchain).\n\nAt this time, the following tasks are supported:\n\n- Text classification\n- Question answering\n- Summarization\n- Paraphrasing\n- Named Entity Recognition\n- Task Free\n\nNote: This is an experimental project.\n\n## Installation\n\n```bash\npip install doccano-mini\n```\n\n## Usage\n\nFor this example, we will be using OpenAI\u2019s APIs, so we need to set the environment variable in the terminal.\n\n```bash\nexport OPENAI_API_KEY=\"...\"\n```\n\nThen, we can run the server.\n\n```bash\ndoccano-mini\n```\n\nNow, we can open the browser and go to `http://localhost:8501/` to see the interface.\n\n### Step1: Annotate a few text\n\nIn 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.\n\n\n\nThe editor also supports pasting in tabular data from Google Sheets, Excel, and many other similar tools.\n\n\n\n### Step2: Test your task\n\nIn 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.\n\n<img src=\"https://raw.githubusercontent.com/doccano/doccano-mini/master/docs/images/test_new_example.jpg\" alt= \u201cStep2\u201d width=\"700\">\n\n### Step3: Download the config\n\nIn this step, we will download the [LangChain](https://github.com/hwchase17/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.\n\n```python\nfrom langchain.chains import load_chain\n\nchain = load_chain(\"chain.yaml\")\nchain.run(\"YOUR TEXT\")\n```\n\n## Development\n\n```bash\npoetry install\nstreamlit run doccano_mini/home.py\n```\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Annotation meets Large Language Models.",
"version": "0.0.10",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "b3c74c20efc74a155b90cb99b8decfa8c58815486359ffc6e6c2e8892e07ca08",
"md5": "408df380cf18b2df31bfe6125f1cebd0",
"sha256": "bc39c2e3ff44b1b7b3227dd7ef824c680030727809d8691774d7bfa2de49b500"
},
"downloads": -1,
"filename": "doccano_mini-0.0.10-py3-none-any.whl",
"has_sig": false,
"md5_digest": "408df380cf18b2df31bfe6125f1cebd0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8, !=2.7.*, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*, !=3.7.*",
"size": 20688,
"upload_time": "2023-04-04T04:55:20",
"upload_time_iso_8601": "2023-04-04T04:55:20.992410Z",
"url": "https://files.pythonhosted.org/packages/b3/c7/4c20efc74a155b90cb99b8decfa8c58815486359ffc6e6c2e8892e07ca08/doccano_mini-0.0.10-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "37d26a41f8761b5a961b269cd8aeffb43705f51a11e46cdd28ddcfdcfab8276a",
"md5": "a3fbe218f1ff14f7de02a74838fde02f",
"sha256": "4f56240e56b7e76afdaf6188c13de0d3ca8980328a14cb57448511f603e8da5f"
},
"downloads": -1,
"filename": "doccano_mini-0.0.10.tar.gz",
"has_sig": false,
"md5_digest": "a3fbe218f1ff14f7de02a74838fde02f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8, !=2.7.*, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*, !=3.7.*",
"size": 12929,
"upload_time": "2023-04-04T04:55:23",
"upload_time_iso_8601": "2023-04-04T04:55:23.967240Z",
"url": "https://files.pythonhosted.org/packages/37/d2/6a41f8761b5a961b269cd8aeffb43705f51a11e46cdd28ddcfdcfab8276a/doccano_mini-0.0.10.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-04-04 04:55:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "doccano",
"github_project": "doccano-mini",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "doccano-mini"
}
