pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md (#179)

Browse Source
This commit is contained in:
writinwaters
2024-03-31 19:43:16 +08:00
committed by GitHub
parent 121c7a5681
commit b349efcd1e
1 changed files with 24 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
README.md
View File

@ -27,21 +27,22 @@
## 🌟 Key Features ## 🌟 Key Features
- 🍭**Custom-build document understanding engine.** Our deep learning engine is made according to the needs of analyzing and searching various type of documents in different domain. - 🍭 **"Quality in, quality out"**
- For documents from different domain for different purpose, the engine applies different analyzing and search strategy. - Deep document understanding-based knowledge extraction from unstructured data with complicated formats.
- Easily intervene and manipulate the data proccessing procedure when things goes beyond expectation. - Finds "needle in a data haystack" of literally unlimited tokens.
- Multi-media document understanding is supported using OCR and multi-modal LLM. - 🍱 **Template-based chunking**
- 🍭**State-of-the-art table structure and layout recognition.** Precisely extract and understand the document including table content. See [README.](./deepdoc/README.md) - Intelligent and explainable.
- For PDF files, layout and table structures including row, column and span of them are recognized. - Plenty of template options to choose from.
- Put the table accrossing the pages together. - 🌱 **Grounded citations with reduced hallucinations**
- Reconstruct the table structure components into html table. - Visualization of text chunking to allow human intervention.
- **Querying database dumped data are supported.** After uploading tables from any database, you can search any data records just by asking. - Quick view of the key references and traceable citations to support grounded answers.
- You can now query a database using natural language instead of using SQL. - 🍔 **Compatibility with heterogeneous data sources**
- The record number uploaded is not limited. - Supports Word, slides, excel, txt, images, scanned copies, structured data, web pages, and more.
- **Reasoned and well-founded answers.** The cited document part in LLM's answer is provided and pointed out in the original document. - 🛀 **Automated and effortless RAG workflow**
- The answers are based on retrieved result for which we apply vector-keyword hybrids search and re-rank. - Streamlined RAG orchestration catered to both personal and large businesses.
- The part of document cited in the answer is presented in the most expressive way. - Configurable LLMs as well as embedding models.
- For PDF file, the cited parts in document can be located in the original PDF. - Multiple recall paired with fused re-ranking.
- Intuitive APIs for seamless integration with business.
## 🔎 System Architecture ## 🔎 System Architecture
@ -97,7 +98,7 @@
> The core image is about 15 GB in size and may take a while to load. > The core image is about 15 GB in size and may take a while to load.
4. Check the server status after pulling all images and having Docker up and running: 4. Check the server status after having the server up and running:
```bash ```bash
$ docker logs -f ragflow-server $ docker logs -f ragflow-server
``` ```
@ -117,9 +118,9 @@
INFO:werkzeug:Press CTRL+C to quit INFO:werkzeug:Press CTRL+C to quit
``` ```
5. In your web browser, enter the IP address of your server as prompted. 5. In your web browser, enter the IP address of your server as prompted and log in to RAGFlow.
*The show is on!* *The show is now on!*
## 🔧 Configurations ## 🔧 Configurations
@ -128,14 +129,14 @@ When it comes to system configurations, you will need to manage the following fi
- [.env](./docker/.env): Keeps the fundamental setups for the system, such as `SVR_HTTP_PORT`, `MYSQL_PASSWORD`, and `MINIO_PASSWORD`. - [.env](./docker/.env): Keeps the fundamental setups for the system, such as `SVR_HTTP_PORT`, `MYSQL_PASSWORD`, and `MINIO_PASSWORD`.
- [service_conf.yaml](./docker/service_conf.yaml): Configures the back-end services. - [service_conf.yaml](./docker/service_conf.yaml): Configures the back-end services.
- [docker-compose.yml](./docker-compose.yaml): The system relies on [docker-compose.yml](./docker-compose.yaml) to start up. - [docker-compose.yml](./docker/docker-compose.yml): The system relies on [docker-compose.yml](./docker/docker-compose.yml) to start up.
You must ensure that changes in [.env](./docker/.env) are in line with what are in the [service_conf.yaml](./docker/service_conf.yaml) file. You must ensure that changes to the [.env](./docker/.env) file are in line with what are in the [service_conf.yaml](./docker/service_conf.yaml) file.
> The [./docker/README](./docker/README.md) file provides a detailed description of the environment settings and service configurations, and it is IMPORTANT to ensure that all environment settings listed in the [./docker/README](./docker/README.md) file should be aligned with the corresponding settings in the [service_conf.yaml](./docker/service_conf.yaml) file. > The [./docker/README](./docker/README.md) file provides a detailed description of the environment settings and service configurations, and it is IMPORTANT to ensure that all environment settings listed in the [./docker/README](./docker/README.md) file are aligned with the corresponding configurations in the [service_conf.yaml](./docker/service_conf.yaml) file.
To change the default serving port (80), go to [docker-compose.yml](./docker-compose.yaml) and change `80:80` to `<YOUR_SERVING_PORT>:80`. To change the default serving port (80), go to [docker-compose.yml](./docker/docker-compose.yml) and change `80:80` to `<YOUR_SERVING_PORT>:80`.
> Updates to all system configurations require a system reboot to take effect: > Updates to all system configurations require a system reboot to take effect:
> >