The "garbage in garbage out" status quo remains unchanged despite the fact that LLMs have advanced Natural Language Processing (NLP) significantly. In its response, RAGFlow introduces two unique features compared to other Retrieval-Augmented Generation (RAG) products.
- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.19.0-slim`
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.19.0`
### Why not use other open-source vector databases as the document engine?
Currently, only Elasticsearch and [Infinity](https://github.com/infiniflow/infinity) meet the hybrid search requirements of RAGFlow. Most open-source vector databases have limited support for full-text search, and sparse embedding is not an alternative to full-text search. Additionally, these vector databases lack critical features essential to RAGFlow, such as phrase search and advanced ranking capabilities.
These limitations led us to develop [Infinity](https://github.com/infiniflow/infinity), the AI-native database, from the ground up.
### Differences between demo.ragflow.io and a locally deployed open-source RAGFlow service?
demo.ragflow.io demonstrates the capabilities of RAGFlow Enterprise. Its DeepDoc models are pre-trained using proprietary data and it offers much more sophisticated team permission controls. Essentially, demo.ragflow.io serves as a preview of RAGFlow's forthcoming SaaS (Software as a Service) offering.
You can deploy an open-source RAGFlow service and call it from a Python client or through RESTful APIs. However, this is not supported on demo.ragflow.io.
We put painstaking effort into document pre-processing tasks like layout analysis, table structure recognition, and OCR (Optical Character Recognition) using our vision models. This contributes to the additional time required.
We officially support x86 CPU and nvidia GPU. While we also test RAGFlow on ARM64 platforms, we do not maintain RAGFlow Docker images for ARM. If you are on an ARM platform, follow [this guide](./develop/build_docker_image.mdx) to build a RAGFlow Docker image.
The corresponding APIs are now available. See the [RAGFlow HTTP API Reference](./references/http_api_reference.md) or the [RAGFlow Python API Reference](./references/python_api_reference.md) for more information.
Yes, we do. Stream output is enabled by default in the chat assistant and agent. Note that you cannot disable stream output via RAGFlow's UI. To disable stream output in responses, use RAGFlow's Python or RESTful APIs:
- **AI search**: This is a single-turn AI conversation using a predefined retrieval strategy (a hybrid search of weighted keyword similarity and weighted vector similarity) and the system's default chat model. It does not involve advanced RAG strategies like knowledge graph, auto-keyword, or auto-question. Retrieved chunks will be listed below the chat model's response.
- **AI chat**: This is a multi-turn AI conversation where you can define your retrieval strategy (a weighted reranking score can be used to replace the weighted vector similarity in a hybrid search) and choose your chat model. In an AI chat, you can configure advanced RAG strategies, such as knowledge graphs, auto-keyword, and auto-question, for your specific case. Retrieved chunks are not displayed along with the answer.
When debugging your chat assistant, you can use AI search as a reference to verify your model settings and retrieval strategy.
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'
This error suggests that you do not have Internet access or are unable to connect to hf-mirror.com. Try the following:
1. Manually download the resource files from [huggingface.co/InfiniFlow/deepdoc](https://huggingface.co/InfiniFlow/deepdoc) to your local folder **~/deepdoc**.
Click the red cross beside the 'parsing status' bar, then restart the parsing process to see if the issue remains. If the issue persists and your RAGFlow is deployed locally, try the following:
Click the red cross beside the 'parsing status' bar, then restart the parsing process to see if the issue remains. If the issue persists and your RAGFlow is deployed locally, the parsing process is likely killed due to insufficient RAM. Try increasing your memory allocation by increasing the `MEM_LIMIT` value in **docker/.env**.
The status of a Docker container status does not necessarily reflect the status of the service. You may find that your services are unhealthy even when the corresponding Docker containers are up running. Possible reasons for this include network failures, incorrect port numbers, or DNS issues.
The status of a Docker container status does not necessarily reflect the status of the service. You may find that your services are unhealthy even when the corresponding Docker containers are up running. Possible reasons for this include network failures, incorrect port numbers, or DNS issues.
3. If your container keeps restarting, ensure `vm.max_map_count` >= 262144 as per [this README](https://github.com/infiniflow/ragflow?tab=readme-ov-file#-start-up-the-server). Updating the `vm.max_map_count` value in **/etc/sysctl.conf** is required, if you wish to keep your change permanent. Note that this configuration works only for Linux.
This is because you forgot to update the `vm.max_map_count` value in **/etc/sysctl.conf** and your change to this value was reset after a system reboot.
Your IP address or port number may be incorrect. If you are using the default configurations, enter `http://<IP_OF_YOUR_MACHINE>` (**NOT 9380, AND NO PORT NUMBER REQUIRED!**) in your browser. This should work.
- If you are on demo.ragflow.io, ensure that the server hosting Ollama has a publicly accessible IP address. Note that 127.0.0.1 is not a publicly accessible IP address.
The status of a Docker container status does not necessarily reflect the status of the service. You may find that your services are unhealthy even when the corresponding Docker containers are up running. Possible reasons for this include network failures, incorrect port numbers, or DNS issues.
If your model is not currently supported but has APIs compatible with those of OpenAI, click **OpenAI-API-Compatible** on the **Model providers** page to configure your model:
For a locally deployed RAGFlow: the total file size limit per upload is 1GB, with a batch upload limit of 32 files. There is no cap on the total number of files per account. To update this 1GB file size limit:
- In **docker/.env**, upcomment `# MAX_CONTENT_LENGTH=1073741824`, adjust the value as needed, and note that `1073741824` represents 1GB in bytes.
- If you update the value of `MAX_CONTENT_LENGTH` in **docker/.env**, ensure that you update `client_max_body_size` in **nginx/nginx.conf** accordingly.
:::tip NOTE
It is not recommended to manually change the 32-file batch upload limit. However, if you use RAGFlow's HTTP API or Python SDK to upload files, the 32-file batch upload limit is automatically removed.
This error occurs because there are too many chunks matching your search criteria. Try reducing the **TopN** and increasing **Similarity threshold** to fix this issue:
### Where are my uploaded files stored in RAGFlow's image?
All uploaded files are stored in Minio, RAGFlow's object storage solution. For instance, if you upload your file directly to a knowledge base, it is located at `<knowledgebase_id>/filename`.
### How to tune batch size for document parsing and embedding?
You can control the batch size for document parsing and embedding by setting the environment variables `DOC_BULK_SIZE` and `EMBEDDING_BATCH_SIZE`. Increasing these values may improve throughput for large-scale data processing, but will also increase memory usage. Adjust them according to your hardware resources.
