yujunjun/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2025-06-26 22:19:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Editorial updates to Docker README (#3223)

Browse Source 
### What problem does this PR solve?



### Type of change


- [x] Documentation Update
This commit is contained in:
writinwaters 2024-11-06 09:43:54 +08:00 committed by GitHub
parent a418a343d1
commit af74bf01c0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 51 additions and 73 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
docker/README.md
View File

@ -8,66 +8,75 @@ Look into [.env](./.env), there're some important variables.
- `STACK_VERSION`
The Elasticsearch version. Defaults to `8.11.3`
- `ES_PORT`
Port to expose Elasticsearch HTTP API to the host. Defaults to `1200`.
- `ELASTIC_PASSWORD`
The Elasticsearch password.
- `MYSQL_PASSWORD`
The MySQL password. When updated, you must also revise the `mysql.password` entry in [service_conf.yaml](./service_conf.yaml) accordingly.
- `MYSQL_PORT`
The exported port number of MySQL Docker container, needed when you access the database from outside the docker containers.
The exported port number of MySQL Docker container, needed when you access the database from outside the Docker container.
- `MINIO_USER`
The MinIO username. When updated, you must also revise the `minio.user` entry in [service_conf.yaml](./service_conf.yaml) accordingly.
- `MINIO_PASSWORD`
The MinIO password. When updated, you must also revise the `minio.password` entry in [service_conf.yaml](./service_conf.yaml) accordingly.
- `SVR_HTTP_PORT`
The port number on which RAGFlow's backend API server listens.
- `TIMEZONE`
The local time zone.
- `RAGFLOW-IMAGE`
The Docker image edition. Available options:
- `infiniflow/ragflow:dev-slim` (default): The RAGFlow Docker image without embedding models
- `infiniflow/ragflow:dev`: The RAGFlow Docker image with embedding models. See the
- `TIMEZONE`
The local time zone.
- `infiniflow/ragflow:dev`: The RAGFlow Docker image with embedding models including:
- Embedded embedding models:
- `BAAI/bge-large-zh-v1.5`
- `BAAI/bge-reranker-v2-m3`
- `maidalun1020/bce-embedding-base_v1`
- `maidalun1020/bce-reranker-base_v1`
- Embedding models that will be downloaded once you select them in the RAGFlow UI:
- `BAAI/bge-base-en-v1.5`
- `BAAI/bge-large-en-v1.5`
- `BAAI/bge-small-en-v1.5`
- `BAAI/bge-small-zh-v1.5`
- `jinaai/jina-embeddings-v2-base-en`
- `jinaai/jina-embeddings-v2-small-en`
- `nomic-ai/nomic-embed-text-v1.5`
- `sentence-transformers/all-MiniLM-L6-v2`
## Service Configuration
[service_conf.yaml](./service_conf.yaml) defines the system-level configuration for RAGFlow and is used by RAGFlow's *API server* and *task executor*.
[service_conf.yaml](./service_conf.yaml) defines the system-level configuration for RAGFlow and is used by its API server and task executor.
- `ragflow`
- `host`: The IP address of the API server.
- `port`: The serving port of API server.
- `mysql`
- `name`: The database name in MySQL used by RAGFlow.
- `user`: The database name in MySQL used by RAGFlow.
- `password`: The database password. When updated, you must also revise the `MYSQL_PASSWORD` variable in [.env](./.env) accordingly.
- `port`: The serving port of MySQL inside the container. When updated, you must also revise the `MYSQL_PORT` variable in [.env](./.env) accordingly.
- `name`: The database name in MySQL used by RAGFlow. Defaults to `rag_flow`.
- `user`: The MySQL user name.
- `password`: The MySQL password. When updated, you must also revise the `MYSQL_PASSWORD` variable in [.env](./.env) accordingly.
- `port`: The serving port of MySQL inside the Docker container. When updated, you must also revise the `MYSQL_PORT` variable in [.env](./.env) accordingly.
- `max_connections`: The maximum database connection.
- `stale_timeout`: The timeout duration in seconds.
- `stale_timeout`: Timeout in seconds.
- `minio`
- `user`: The MinIO username. When updated, you must also revise the `MINIO_USER` variable in [.env](./.env) accordingly.
- `password`: The MinIO password. When updated, you must also revise the `MINIO_PASSWORD` variable in [.env](./.env) accordingly.
- `host`: The serving IP and port inside the docker container. This is not updating until changing the minio part in [docker-compose.yml](./docker-compose.yml)
- `user_default_llm`
Newly signed-up users use LLM configured by this part; otherwise, you need to configure your own LLM on the *Settings* page.
- `host`: The serving IP and port inside the docker container. This is not updated until changing the minio part in [docker-compose.yml](./docker-compose.yml)
- `user_default_llm`
The default LLM to use for a new RAGFlow user. It is disabled by default. If you have not set it here, you can configure the default LLM on the **Settings** page in the RAGFlow UI. Newly signed-up users use LLM configured by this part; otherwise, you need to configure your own LLM on the *Settings* page.
- `factory`: The LLM suppliers. "OpenAI"， "Tongyi-Qianwen", "ZHIPU-AI", "Moonshot", "DeepSeek", "Baichuan", and "VolcEngine" are supported.
- `api_key`: The API key for the specified LLM.
- `oauth`
The OAuth configuration for signing up or signing in to RAGFlow using a third-party account.
- `github`: Go to [Github](https://github.com/settings/developers), register a new application, the *client_id* and *secret_key* will be given.
The OAuth configuration for signing up or signing in to RAGFlow using a third-party account. It is disabled by default. To enable this feature, uncomment the corresponding lines in **service_conf.yaml**.
- `github`: The GitHub authentication settings for your application. Visit the [Github Developer Settings page](https://github.com/settings/developers) to obtain your client_id and secret_key.

19
docs/guides/llm_api_key_setup.md
View File

@ -9,24 +9,7 @@ An API key is required for RAGFlow to interact with an online AI model. This gui
## Get model API key
For now, RAGFlow supports the following online LLMs. Click the corresponding link to apply for your model API key. Most LLM providers grant newly-created accounts trial credit, which will expire in a couple of months, or a promotional amount of free quota.
- [OpenAI](https://platform.openai.com/login?launch)
- [Azure-OpenAI](https://ai.azure.com/)
- [Gemini](https://aistudio.google.com/)
- [Groq](https://console.groq.com/)
- [Mistral](https://mistral.ai/)
- [Bedrock](https://aws.amazon.com/cn/bedrock/)
- [Tongyi-Qianwen](https://dashscope.console.aliyun.com/model)
- [ZHIPU-AI](https://open.bigmodel.cn/)
- [MiniMax](https://platform.minimaxi.com/)
- [Moonshot](https://platform.moonshot.cn/docs)
- [DeepSeek](https://platform.deepseek.com/api-docs/)
- [Baichuan](https://www.baichuan-ai.com/home)
- [VolcEngine](https://www.volcengine.com/docs/82379)
- [Jina](https://jina.ai/reader/)
- [OpenRouter](https://openrouter.ai/)
- [StepFun](https://platform.stepfun.com/)
RAGFlow supports most mainstream LLMs. Please refer to [Supported Models](./references/supported_models.mdx) for a complete list of supported models. You will need to apply for your model API key online. Note that most LLM providers grant newly-created accounts trial credit, which will expire in a couple of months, or a promotional amount of free quota.
:::note
If you find your online LLM is not on the list, don't feel disheartened. The list is expanding, and you can [file a feature request](https://github.com/infiniflow/ragflow/issues/new?assignees=&labels=feature+request&projects=&template=feature_request.yml&title=%5BFeature+Request%5D%3A+) with us! Alternatively, if you have customized or locally-deployed models, you can [bind them to RAGFlow using Ollama, Xinference, or LocalAI](./deploy_local_llm.mdx).

4
docs/guides/manage_files.md
View File

@ -49,7 +49,7 @@ You can link your file to one knowledge base or multiple knowledge bases at one
## Search files or folders
As of RAGFlow v0.13.0, the search feature is still in a rudimentary form, supporting only file and folder search in the current directory by name (files or folders in the child directory will not be retrieved).
**File Management** only supports file name and folder name filtering in the current directory (files or folders in the child directory will not be retrieved).
![search file](https://github.com/infiniflow/ragflow/assets/93570324/77ffc2e5-bd80-4ed1-841f-068e664efffe)
@ -73,7 +73,7 @@ To bulk delete files or folders:
![bulk delete](https://github.com/infiniflow/ragflow/assets/93570324/519b99ab-ec7f-4c8a-8cea-e0b6dcb3cb46)
> - You are not allowed to delete the **root/.knowledgebase** folder.
> - Deleting files that have been linked to knowledge bases will AUTOMATICALLY REMOVE all associated file references across the knowledge bases.
> - Deleting files that have been linked to knowledge bases will **AUTOMATICALLY REMOVE** all associated file references across the knowledge bases.
## Download uploaded file

19
docs/quickstart.mdx
View File

@ -223,24 +223,7 @@ With the default settings, you only need to enter `http://IP_OF_YOUR_MACHINE` (*
## Configure LLMs
RAGFlow is a RAG engine, and it needs to work with an LLM to offer grounded, hallucination-free question-answering capabilities. For now, RAGFlow supports the following LLMs, and the list is expanding:
- [OpenAI](https://platform.openai.com/login?launch)
- [Azure-OpenAI](https://ai.azure.com/)
- [Gemini](https://aistudio.google.com/)
- [Groq](https://console.groq.com/)
- [Mistral](https://mistral.ai/)
- [Bedrock](https://aws.amazon.com/cn/bedrock/)
- [Tongyi-Qianwen](https://dashscope.console.aliyun.com/model)
- [ZHIPU-AI](https://open.bigmodel.cn/)
- [MiniMax](https://platform.minimaxi.com/)
- [Moonshot](https://platform.moonshot.cn/docs)
- [DeepSeek](https://platform.deepseek.com/api-docs/)
- [Baichuan](https://www.baichuan-ai.com/home)
- [VolcEngine](https://www.volcengine.com/docs/82379)
- [Jina](https://jina.ai/reader/)
- [OpenRouter](https://openrouter.ai/)
- [StepFun](https://platform.stepfun.com/)
RAGFlow is a RAG engine and needs to work with an LLM to offer grounded, hallucination-free question-answering capabilities. RAGFlow supports most mainstream LLMs. For a complete list of supported models, please refer to [Supported Models](./references/supported_models.mdx).
:::note
RAGFlow also supports deploying LLMs locally using Ollama, Xinference, or LocalAI, but this part is not covered in this quick start guide.

4
docs/references/faq.md
View File

@ -5,6 +5,8 @@ slug: /faq
# Frequently asked questions
Queries regarding general usage, troubleshooting, features, performance, and more.
## General
### 1. What sets RAGFlow apart from other RAG products?
@ -98,7 +100,7 @@ docker build -t infiniflow/ragflow:vX.Y.Z. --network host
#### 2.1 Cannot access https://huggingface.co
A *locally* deployed RAGflow downloads OCR and embedding modules from [Huggingface website](https://huggingface.co) by default. If your machine is unable to access this site, the following error occurs and PDF parsing fails:
A *locally* deployed RAGflow downloads OCR and embedding modules from [Huggingface website](https://huggingface.co) by default. If your machine is unable to access this site, the following error occurs and PDF parsing fails:
```
FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res'

9
docs/references/supported_models.mdx
View File

@ -12,7 +12,7 @@ A complete list of models supported by RAGFlow, which will continue to expand.
<APITable>
```
| Provider | Chat | Embedding | Rerank | Multi-modal | ASR/STT | TTS |
| Provider | Chat | Embedding | Rerank | Multimodal | ASR | TTS |
| --------------------- | ------------------ | ------------------ | ------------------ | ------------------ | ------------------ | ------------------ |
| Anthropic | :heavy_check_mark: | | | | | |
| Azure-OpenAI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: | |
@ -20,7 +20,7 @@ A complete list of models supported by RAGFlow, which will continue to expand.
| BaiChuan | :heavy_check_mark: | :heavy_check_mark: | | | | |
| BaiduYiyan | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| Bedrock | :heavy_check_mark: | :heavy_check_mark: | | | | |
| cohere | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| Cohere | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| DeepSeek | :heavy_check_mark: | | | | | |
| FastEmbed | | :heavy_check_mark: | | | | |
| Fish Audio | | | | | | :heavy_check_mark: |
@ -62,5 +62,6 @@ A complete list of models supported by RAGFlow, which will continue to expand.
</APITable>
```
:::note
The list of supported models is extracted from [this source](https://github.com/infiniflow/ragflow/blob/main/rag/llm/__init__.py) and may not be the most current. For the latest supported model list, please refer to the Python file.
:::