[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data.
- 2024-04-19 Supports conversation API ([detail](./docs/conversation_api.md)).
- 2024-04-16 Integrates an embedding model 'bce-embedding-base_v1' from [BCEmbedding](https://github.com/netease-youdao/BCEmbedding), and [FastEmbed](https://github.com/qdrant/fastembed), which is designed specifically for light and speedy embedding.
- 2024-04-11 Supports [Xinference](./docs/xinference.md) for local LLM deployment.
- 2024-04-10 Adds a new layout recognition model for analyzing legal documents.
- 2024-04-08 Supports [Ollama](./docs/ollama.md) for local LLM deployment.
> If you have not installed Docker on your local machine (Windows, Mac, or Linux), see [Install Docker Engine](https://docs.docker.com/engine/install/).
> This change will be reset after a system reboot. To ensure your change remains permanent, add or update the `vm.max_map_count` value in **/etc/sysctl.conf** accordingly:
> Running the following commands automatically downloads the *dev* version RAGFlow Docker image. To download and run a specified Docker version, update `RAGFLOW_VERSION` in **docker/.env** to the intended version, for example `RAGFLOW_VERSION=v0.5.0`, before running the following commands.
> If you skip this confirmation step and directly log in to RAGFlow, your browser may prompt a `network anomaly` error because, at that moment, your RAGFlow may not be fully initialized.
> With default settings, you only need to enter `http://IP_OF_YOUR_MACHINE` (**sans** port number) as the default HTTP serving port `80` can be omitted when using the default configurations.
6. In [service_conf.yaml](./docker/service_conf.yaml), select the desired LLM factory in `user_default_llm` and update the `API_KEY` field with the corresponding API key.
> The [./docker/README](./docker/README.md) file provides a detailed description of the environment settings and service configurations, and you are REQUIRED 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.
3. Copy the entry script and configure environment variables
```bash
$ cp docker/entrypoint.sh .
$ vi entrypoint.sh
```
Use the following commands to obtain the Python path and the ragflow project path:
```bash
$ which python
$ pwd
```
Set the output of `which python` as the value for `PY` and the output of `pwd` as the value for `PYTHONPATH`.
If `LD_LIBRARY_PATH` is already configured, it can be commented out.
```bash
# Adjust configurations according to your actual situation; the two export commands are newly added.
PY=${PY}
export PYTHONPATH=${PYTHONPATH}
# Optional: Add Hugging Face mirror
export HF_ENDPOINT=https://hf-mirror.com
```
4. Start the base services
```bash
$ cd docker
$ docker compose -f docker-compose-base.yml up -d
```
5. Check the configuration files
Ensure that the settings in **docker/.env** match those in **conf/service_conf.yaml**. The IP addresses and ports for related services in **service_conf.yaml** should be changed to the local machine IP and ports exposed by the container.
RAGFlow flourishes via open-source collaboration. In this spirit, we embrace diverse contributions from the community. If you would like to be a part, review our [Contribution Guidelines](https://github.com/infiniflow/ragflow/blob/main/docs/CONTRIBUTING.md) first.
