QAnything

Table of Contents - [What is QAnything](#what-is-qanything) - [Key features](#key-features) - [Architecture](#architecture) - [Latest Updates](#-latest-updates) - [Before You Start](#before-you-start) - [Getting Started](#getting-started) - [Latest Features Table](#latest-features-table) - [Version 2.0.0 adds detailed optimizations:](#version-200-adds-detailed-optimizations) - [Display of data at each stage:](#display-of-data-at-each-stage) - [Problem fixed](#problem-fixed) - [Comparison of New and Old Parsing Effects](#comparison-of-new-and-old-parsing-effects) - [Installation](#installation) - [Prerequisites](#prerequisites) - [step1: pull qanything repository](#step1-pull-qanything-repository) - [step2: Enter the project root directory and execute the startup command.](#step2-enter-the-project-root-directory-and-execute-the-startup-command) - [step3: start to experience](#step3-start-to-experience) - [API](#api) - [DEBUG](#debug) - [Close service](#close-service) - [Offline Use](#offline-use) - [FAQ](#faq) - [Contributing](#contributing) - [Thanks to all contributors for their efforts](#thanks-to-all-contributors-for-their-efforts) - [Special thanks!](#special-thanks) - [Business contact information：](#business-contact-information) - [Roadmap & Feedback](#-roadmap--feedback) - [Community & Support](#community--support) - [License](#license) - [Acknowledgements](#acknowledgments) # 🚀 Important Updates

Important things should be said three times.

# [2024-08-23: QAnything updated to version 2.0.] # [2024-08-23: QAnything updated to version 2.0.] # [2024-08-23: QAnything updated to version 2.0.]

* This update brings improvements in various aspects such as usability, resource consumption, search results, question and answer results, parsing results, front-end effects, service architecture, and usage methods. * At the same time, the old Docker version and Python version have been merged into a new unified version, using a single-line command with Docker Compose for one-click startup, ready to use out of the box.

## Contributing We appreciate your interest in contributing to our project. Whether you're fixing a bug, improving an existing feature, or adding something completely new, your contributions are welcome! ### Thanks to all contributors for their efforts ### Special thanks!

Please note: Our list of contributors is automatically updated, so your contributions may not appear immediately on this list.

Special thanks!：@ikun-moxiaofei

Special thanks!：@Ianarua

## Business contact information： ### 010-82558901 For business cooperation, please contact us by phone or email: - Phone: 010-82558901 - Email: [email protected] # What is QAnything? `QAnything`(**Q**uestion and **A**nswer based on **Anything**) is a local knowledge base question-answering system designed to support a wide range of file formats and databases, allowing for offline installation and use. With `QAnything`, you can simply drop any locally stored file of any format and receive accurate, fast, and reliable answers. Currently supported formats include: **PDF(pdf)**,**Word(docx)**,**PPT(pptx)**,**XLS(xlsx)**,**Markdown(md)**,**Email(eml)**,**TXT(txt)**,**Image(jpg，jpeg，png)**,**CSV(csv)**,**Web links(html)** and more formats coming soon… ## Key features - Data security, supports installation and use by unplugging the network cable throughout the process. - Supports multiple file types, high parsing success rate, supports cross-language question and answer, freely switches between Chinese and English question and answer, regardless of the language of the file. - Supports massive data question and answer, two-stage vector sorting, solves the problem of degradation of large-scale data retrieval, the more data, the better the effect, no limit on the number of uploaded files, fast retrieval speed. - Hardware friendly, defaults to running in a pure CPU environment, and supports multiple platforms such as Windows, Mac, and Linux, with no dependencies other than Docker. - User-friendly, no need for cumbersome configuration, one-click installation and deployment, ready to use, each dependent component (PDF parsing, OCR, embed, rerank, etc.) is completely independent, supports free replacement. - Supports a quick start mode similar to Kimi, fileless chat mode, retrieval mode only, custom Bot mode. ## Architecture ### Why 2 stage retrieval? In scenarios with a large volume of knowledge base data, the advantages of a two-stage approach are very clear. If only a first-stage embedding retrieval is used, there will be a problem of retrieval degradation as the data volume increases, as indicated by the green line in the following graph. However, after the second-stage reranking, there can be a stable increase in accuracy, **the more data, the better the performance**. QAnything uses the retrieval component [BCEmbedding](https://github.com/netease-youdao/BCEmbedding), which is distinguished for its bilingual and crosslingual proficiency. BCEmbedding excels in bridging Chinese and English linguistic gaps, which achieves - **A high performance on Semantic Representation Evaluations in MTEB**; - **A new benchmark in the realm of RAG Evaluations in LlamaIndex**. ### 1st Retrieval（embedding） | Model | Retrieval | STS | PairClassification | Classification | Reranking | Clustering | Avg | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | bge-base-en-v1.5 | 37.14 | 55.06 | 75.45 | 59.73 | 43.05 | 37.74 | 47.20 | | bge-base-zh-v1.5 | 47.60 | 63.72 | 77.40 | 63.38 | 54.85 | 32.56 | 53.60 | | bge-large-en-v1.5 | 37.15 | 54.09 | 75.00 | 59.24 | 42.68 | 37.32 | 46.82 | | bge-large-zh-v1.5 | 47.54 | 64.73 | **79.14** | 64.19 | 55.88 | 33.26 | 54.21 | | jina-embeddings-v2-base-en | 31.58 | 54.28 | 74.84 | 58.42 | 41.16 | 34.67 | 44.29 | | m3e-base | 46.29 | 63.93 | 71.84 | 64.08 | 52.38 | 37.84 | 53.54 | | m3e-large | 34.85 | 59.74 | 67.69 | 60.07 | 48.99 | 31.62 | 46.78 | | ***bce-embedding-base_v1*** | **57.60** | **65.73** | 74.96 | **69.00** | **57.29** | **38.95** | ***59.43*** | - More evaluation details please check [Embedding Models Evaluation Summary](https://github.com/netease-youdao/BCEmbedding/blob/master/Docs/EvaluationSummary/embedding_eval_summary.md)。 ### 2nd Retrieval（rerank） | Model | Reranking | Avg | |:-------------------------------|:--------:|:--------:| | bge-reranker-base | 57.78 | 57.78 | | bge-reranker-large | 59.69 | 59.69 | | ***bce-reranker-base_v1*** | **60.06** | ***60.06*** | - More evaluation details please check [Reranker Models Evaluation Summary](https://github.com/netease-youdao/BCEmbedding/blob/master/Docs/EvaluationSummary/reranker_eval_summary.md) ### RAG Evaluations in LlamaIndex（embedding and rerank） ***NOTE:*** - In `WithoutReranker` setting, our `bce-embedding-base_v1` outperforms all the other embedding models. - With fixing the embedding model, our `bce-reranker-base_v1` achieves the best performance. - **The combination of `bce-embedding-base_v1` and `bce-reranker-base_v1` is SOTA**. - If you want to use embedding and rerank separately, please refer to [BCEmbedding](https://github.com/netease-youdao/BCEmbedding) ### LLM The open source version of QAnything is based on QwenLM and has been fine-tuned on a large number of professional question-answering datasets. It greatly enhances the ability of question-answering. If you need to use it for commercial purposes, please follow the license of QwenLM. For more details, please refer to: [QwenLM](https://github.com/QwenLM/Qwen) # 🚀 Latest Updates - ***2024-08-23***: **Support quick start, front-end configuration parameters, online preview and editing of chunk blocks, greatly optimize project architecture and startup mode, greatly optimize parsing and retrieval effects.** - See More👉 [v2.0.0](https://github.com/netease-youdao/QAnything/releases/tag/v2.0.0) - ***2024-05-20***: **Support other large model services compatible with OpenAI API, and provide an optimized powerful PDF parser.** - See More👉 [v1.4.1](https://github.com/netease-youdao/QAnything/releases/tag/v1.4.1) - ***2024-04-26***: **Support web search, FAQ, custom bot, file traceability preview etc.** - See More👉 [v1.4.0](https://github.com/netease-youdao/QAnything/releases/tag/v1.4.0-python) - ***2024-04-03***: **Support installation in a pure Python environment.Support hybrid search.** - See More👉 [v1.3.0](https://github.com/netease-youdao/QAnything/releases/tag/v1.3.0) - ***2024-01-29***: **Support for custom large models, including OpenAI API and other open-source large models, with a minimum GPU requirement of GTX 1050Ti, greatly improving deployment, debugging, and user experience.** - See More👉 [v1.2.0](https://github.com/netease-youdao/QAnything/releases/tag/v1.2.0) - ***2024-01-23***: **Enable rerank by default and fix various issues when starting on Windows.** - See More👉 [v1.1.1](https://github.com/netease-youdao/QAnything/releases/tag/v1.1.1) - ***2024-01-18***: **Support one-click startup, support Windows deployment, improve PDF, XLSX, HTML parsing efficiency.** - See More👉 [v1.1.0](https://github.com/netease-youdao/QAnything/releases/tag/v1.1.0) # Before You Start **Star us on GitHub, and be instantly notified for new release!** * [🏄 Try QAnything Online](https://qanything.ai) * [📚 Try read.youdao.com | 有道速读](https://read.youdao.com) * [🛠️ Only use our BCEmbedding(embedding & rerank)](https://github.com/netease-youdao/BCEmbedding) * [📖 FAQ](FAQ_zh.md) * [👂️Let me hear your voice](https://qanything.canny.io/feature-requests) # Getting Started ## Latest Features Table | features | python （v1.4.2） | docker （v1.2.2） | QAnything v2.0.0 | Explanation | |----------------------------------------------------------------------|-----------------|-----------------|------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Detailed installation document | ✅ | ✅ | ✅ | | | Support API | ✅ | ✅ | ✅ | | | Support production environment | ❌ | ✅ | ✅ |