Automatic FAQ Mining Framework
Project description
AutoFAQ
AutoFAQ is a sophisticated FAQ dataset mining framework designed as an interactive CLI tool for rapid and efficient data collection. With AutoFAQ, you can compile comprehensive FAQ datasets in just minutes!
Process Overview
AutoFAQ's streamlined process follows these steps to generate a complete dataset:
- Expand Keywords: Provide a few initial keywords, and AutoFAQ will automatically expand the list to generate a comprehensive query list.
- Web Search: AutoFAQ performs searches using your choice of designated search engines to create a list of relevant webpages.
- Information Extraction: Once all webpages are downloaded, AutoFAQ extracts QA pairs using the available extractor engines.
- Data Cleaning: AutoFAQ's cleaning modules allow you to refine the dataset using semantic entailment of QA pairs, titles, or pages.
- Rendering: Finally, you can render the dataset into your desired format with ease. Success!
Getting Started
- Install the
autofaq
CLI tool using:pip install auto-faq
-
Usage: autofaq [OPTIONS] COMMAND [ARGS]... Options: --help Show this message and exit. Commands: clean Refines the dataset embed Computes vector embeddings of the dataset extract Collects webpages and extracts QA pairs init Initiates a new mining project keywords Generates an expanded list of keywords render Transforms the dataset into human-readable formats search Compiles search results for keywords
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
auto-faq-0.4.1.tar.gz
(14.7 kB
view details)
Built Distribution
auto_faq-0.4.1-py3-none-any.whl
(25.3 kB
view details)
File details
Details for the file auto-faq-0.4.1.tar.gz
.
File metadata
- Download URL: auto-faq-0.4.1.tar.gz
- Upload date:
- Size: 14.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5e347fab16de5d04e503dda94d58955241a17d49d52277f47bf8fb2458172e3f |
|
MD5 | 98099d02bc8afef2e7b2c8cc8326d946 |
|
BLAKE2b-256 | 14a434876cabf5285ba784c8aa004aa95b539aac90704459401d2c4f71948fba |
File details
Details for the file auto_faq-0.4.1-py3-none-any.whl
.
File metadata
- Download URL: auto_faq-0.4.1-py3-none-any.whl
- Upload date:
- Size: 25.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b353a1c253aae04e09f80066245950b1e00216641552ba701ff01b1218a40ea2 |
|
MD5 | 21ec7f4c3bfde90dca8996c61a66fd4c |
|
BLAKE2b-256 | f83ebaa5fad825d38bd0a8cca7317534f7204deab707ed714ae0d526a56c6b2a |