Added a guide on setting page rank. (#6645)

### What problem does this PR solve?


### Type of change


- [x] Documentation Update

---------

Co-authored-by: balibabu <cike8899@users.noreply.github.com>
This commit is contained in:
writinwaters 2025-03-31 11:44:18 +08:00 committed by GitHub
parent 805a8f1f47
commit 2793c8e4fe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
12 changed files with 123 additions and 121 deletions

View File

@ -131,25 +131,17 @@ Yes, we support enhancing user queries based on existing context of an ongoing c
When debugging your chat assistant, you can use AI search as a reference to verify your model settings and retrieval strategy.
---
## Troubleshooting
---
### Issues with Docker images
---
#### How to build the RAGFlow image from scratch?
### How to build the RAGFlow image from scratch?
See [Build a RAGFlow Docker image](./develop/build_docker_image.mdx).
---
### Issues with huggingface models
---
#### Cannot access https://huggingface.co
### 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:
@ -180,7 +172,7 @@ To fix this issue, use https://hf-mirror.com instead:
---
#### `MaxRetryError: HTTPSConnectionPool(host='hf-mirror.com', port=443)`
### `MaxRetryError: HTTPSConnectionPool(host='hf-mirror.com', port=443)`
This error suggests that you do not have Internet access or are unable to connect to hf-mirror.com. Try the following:
@ -193,17 +185,13 @@ This error suggests that you do not have Internet access or are unable to connec
---
### Issues with RAGFlow servers
---
#### `WARNING: can't find /raglof/rag/res/borker.tm`
### `WARNING: can't find /raglof/rag/res/borker.tm`
Ignore this warning and continue. All system warnings can be ignored.
---
#### `network anomaly There is an abnormality in your network and you cannot connect to the server.`
### `network anomaly There is an abnormality in your network and you cannot connect to the server.`
![anomaly](https://github.com/infiniflow/ragflow/assets/93570324/beb7ad10-92e4-4a58-8886-bfb7cbd09e5d)
@ -226,11 +214,7 @@ You will not log in to RAGFlow unless the server is fully initialized. Run `dock
---
### Issues with RAGFlow backend services
---
#### `Realtime synonym is disabled, since no redis connection`
### `Realtime synonym is disabled, since no redis connection`
Ignore this warning and continue. All system warnings can be ignored.
@ -238,7 +222,7 @@ Ignore this warning and continue. All system warnings can be ignored.
---
#### Why does my document parsing stall at under one percent?
### Why does my document parsing stall at under one percent?
![stall](https://github.com/infiniflow/ragflow/assets/93570324/3589cc25-c733-47d5-bbfc-fedb74a3da50)
@ -255,7 +239,7 @@ Click the red cross beside the 'parsing status' bar, then restart the parsing pr
---
#### Why does my pdf parsing stall near completion, while the log does not show any error?
### Why does my pdf parsing stall near completion, while the log does not show any error?
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**.
@ -276,13 +260,13 @@ docker compose up -d
---
#### `Index failure`
### `Index failure`
An index failure usually indicates an unavailable Elasticsearch service.
---
#### How to check the log of RAGFlow?
### How to check the log of RAGFlow?
```bash
tail -f ragflow/docker/ragflow-logs/*.log
@ -290,7 +274,7 @@ tail -f ragflow/docker/ragflow-logs/*.log
---
#### How to check the status of each component in RAGFlow?
### How to check the status of each component in RAGFlow?
1. Check the status of the Elasticsearch Docker container:
@ -315,7 +299,7 @@ The status of a Docker container status does not necessarily reflect the status
---
#### `Exception: Can't connect to ES cluster`
### `Exception: Can't connect to ES cluster`
1. Check the status of the Elasticsearch Docker container:
@ -339,19 +323,19 @@ The status of a Docker container status does not necessarily reflect the status
---
#### Can't start ES container and get `Elasticsearch did not exit normally`
### Can't start ES container and get `Elasticsearch did not exit normally`
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.
---
#### `{"data":null,"code":100,"message":"<NotFound '404: Not Found'>"}`
### `{"data":null,"code":100,"message":"<NotFound '404: Not Found'>"}`
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.
---
#### `Ollama - Mistral instance running at 127.0.0.1:11434 but cannot add Ollama as model in RagFlow`
### `Ollama - Mistral instance running at 127.0.0.1:11434 but cannot add Ollama as model in RagFlow`
A correct Ollama IP address and port is crucial to adding models to Ollama:
@ -362,37 +346,13 @@ See [Deploy a local LLM](./guides/models/deploy_local_llm.mdx) for more informat
---
#### Do you offer examples of using DeepDoc to parse PDF or other files?
### Do you offer examples of using DeepDoc to parse PDF or other files?
Yes, we do. See the Python files under the **rag/app** folder.
---
#### Why did I fail to upload a 128MB+ file to my locally deployed RAGFlow?
Ensure that you update the **MAX_CONTENT_LENGTH** environment variable:
1. In **ragflow/docker/.env**, uncomment environment variable `MAX_CONTENT_LENGTH`:
```
MAX_CONTENT_LENGTH=176160768 # 168MB
```
2. Update **ragflow/docker/nginx/nginx.conf**:
```
client_max_body_size 168M
```
3. Restart the RAGFlow server:
```
docker compose up ragflow -d
```
---
#### `FileNotFoundError: [Errno 2] No such file or directory`
### `FileNotFoundError: [Errno 2] No such file or directory`
1. Check the status of the MinIO Docker container:
@ -418,14 +378,6 @@ The status of a Docker container status does not necessarily reflect the status
---
### How to increase the length of RAGFlow responses?
1. Right-click the desired dialog to display the **Chat Configuration** window.
2. Switch to the **Model Setting** tab and adjust the **Max Tokens** slider to get the desired length.
3. Click **OK** to confirm your change.
---
### How to run RAGFlow with a locally deployed LLM?
You can use Ollama or Xinference to deploy local LLM. See [here](./guides/models/deploy_local_llm.mdx) for more information.
@ -440,7 +392,7 @@ If your model is not currently supported but has APIs compatible with those of O
---
### How to interconnect RAGFlow with Ollama?
### How to integrate RAGFlow with Ollama?
- If RAGFlow is locally deployed, ensure that your RAGFlow and Ollama are in the same LAN.
- If you are using our online demo, ensure that the IP address of your Ollama server is public and accessible.
@ -486,3 +438,14 @@ See [Acquire a RAGFlow API key](./develop/acquire_ragflow_api_key.md).
See [Upgrade RAGFlow](./guides/upgrade_ragflow.mdx) for more information.
---
### How to switch the document engine to Infinity?
To switch your document engine from Elasticsearch to [Infinity](https://github.com/infiniflow/infinity):
1. In **docker/.env**, set `DOC_ENGINE=${DOC_ENGINE:-infinity}`
2. Restart your Docker image:
```bash
$ docker compose -f docker-compose.yml up -d
```

View File

@ -27,7 +27,7 @@ In contrast, chunks created from [knowledge graph construction](./construct_know
### Similarity threshold
This sets the bar for retrieving chunks: chunks with similarities below the threshold will be filtered out. By default, the threshold is set to 0.2. That means that only chunks with hybrid similarity score of 20 or higher will be retrieved.
This sets the bar for retrieving chunks: chunks with similarities below the threshold will be filtered out. By default, the threshold is set to 0.2. This means that only chunks with hybrid similarity score of 20 or higher will be retrieved.
### Keyword similarity weight

View File

@ -0,0 +1,39 @@
---
sidebar_position: 3
slug: /set_page_rank
---
# Set page rank
Create a step-retrieval strategy using page rank.
---
## Scenario
In an AI-powered chat, you can configure a chat assistant or an agent to respond using knowledge retrieved from multiple specified knowledge bases (datasets), provided that they employ the same embedding model. In situations where you prefer information from certain knowledge base(s) to take precedence or to be retrieved first, you can use RAGFlow's page rank feature to increase the ranking of chunks from these knowledge bases. For example, if you have configured a chat assistant to draw from two knowledge bases, knowledge base A for 2024 news and knowledge base B for 2023 news, but wish to prioritize news from year 2024, this feature is particularly useful.
:::info NOTE
It is important to note that this 'page rank' feature operates at the level of the entire knowledge base rather than on individual files or documents.
:::
## Configuration
On the **Configuration** page of your knowledge base, drag the slider under **Page rank** to set the page rank value for your knowledge base. You are also allowed to input the intended page rank value in the field next to the slider.
:::info NOTE
The page rank value must be an integer. Range: [0,100]
- 0: Disabled (Default)
- A specific value: enabled
:::
:::tip NOTE
If you set the page rank value to a non-integer, say 1.7, it will be rounded down to the nearest integer, which in this case is 1.
:::
## Mechanism
If you configure a chat assistant's **similarity threshold** to 0.2, only chunks with a hybrid score greater than 0.2 x 100 = 20 will be retrieved and sent to the chat model for content generation. This initial filtering step is crucial for narrowing down relevant information.
If you have assigned a page rank of 1 to knowledge base A (2024 news) and 0 to knowledge base B (2023 news), the final hybrid scores of the retrieved chunks will be adjusted accordingly. A chunk from knowledge base A with an initial score of 50 will receive a boost of 1 x 100 = 100 points, resulting in a final score of 50 + 1 x 100 = 150. In this way, chunks retrieved from knowledge base A will always precede chunks from knowledge base B.

View File

@ -624,19 +624,19 @@ export default {
'Das Standard-Chat-LLM, das alle neu erstellten Wissensdatenbanken verwenden werden.',
embeddingModel: 'Embedding-Modell',
embeddingModelTip:
'Das Standard-Embedding-Modell, das alle neu erstellten Wissensdatenbanken verwenden werden.',
'Das Standard-Einbettungsmodell für jede neu erstellte Wissensdatenbank. Wenn Sie kein Einbettungsmodell in der Dropdown-Liste finden, prüfen Sie, ob Sie die RAGFlow Slim Edition verwenden (die keine Einbettungsmodelle enthält), oder überprüfen Sie https://ragflow.io/docs/dev/supported_models, um zu sehen, ob Ihr Modellanbieter dieses Modell unterstützt.',
img2txtModel: 'Img2txt-Modell',
img2txtModelTip:
'Das Standard-Multimodul-Modell, das alle neu erstellten Wissensdatenbanken verwenden werden. Es kann ein Bild oder Video beschreiben.',
'Das Standardmodell img2txt für jede neu erstellte Wissensdatenbank. Es beschreibt ein Bild oder Video. Wenn Sie kein Modell im Dropdown-Menü finden können, überprüfen Sie https://ragflow.io/docs/dev/supported_models, um zu sehen, ob Ihr Modellanbieter dieses Modell unterstützt.',
sequence2txtModel: 'Sequence2txt-Modell',
sequence2txtModelTip:
'Das Standard-ASR-Modell, das alle neu erstellten Wissensdatenbanken verwenden werden. Verwenden Sie dieses Modell, um Stimmen in entsprechenden Text zu übersetzen.',
'Das Standard-ASR-Modell, das alle neu erstellten Wissensdatenbanken verwenden werden. Verwenden Sie dieses Modell, um Stimmen in entsprechenden Text zu übersetzen. Wenn Sie kein Modell im Dropdown-Menü finden können, überprüfen Sie https://ragflow.io/docs/dev/supported_models, um zu sehen, ob Ihr Modellanbieter dieses Modell unterstützt.',
rerankModel: 'Rerank-Modell',
rerankModelTip:
'Das Standard-Rerank-Modell wird verwendet, um Chunks neu zu ordnen, die durch Benutzerfragen abgerufen wurden.',
'Das Standard-Rerank-Modell zum Reranking von Textabschnitten. Wenn Sie kein Modell im Dropdown-Menü finden, überprüfen Sie https://ragflow.io/docs/dev/supported_models, um zu sehen, ob Ihr Modellanbieter dieses Modell unterstützt.',
ttsModel: 'TTS-Modell',
ttsModelTip:
'Das Standard-TTS-Modell wird verwendet, um auf Anfrage Sprache während Gesprächen zu generieren.',
'Das Standard-Text-to-Speech-Modell. Wenn Sie kein Modell im Dropdown-Menü finden, überprüfen Sie https://ragflow.io/docs/dev/supported_models, um zu sehen, ob Ihr Modellanbieter dieses Modell unterstützt.',
workspace: 'Arbeitsbereich',
upgrade: 'Upgrade',
addLlmTitle: 'LLM hinzufügen',

View File

@ -111,7 +111,7 @@ export default {
'Conduct a retrieval test to check if RAGFlow can recover the intended content for the LLM. If you have adjusted the default settings, such as keyword similarity weight or similarity threshold, to achieve the optimal results, be aware that these changes will not be automatically saved. You must apply them to your chat assistant settings or the Retrieval agent component settings.',
similarityThreshold: 'Similarity threshold',
similarityThresholdTip:
'RAGFlow employs either a combination of weighted keyword similarity and weighted vector cosine similarity, or a combination of weighted keyword similarity and weighted reranking score during retrieval. This parameter sets the threshold for similarities between the user query and chunks. Any chunk with a similarity score below this threshold will be excluded from the results. By default, the threshold is set to 0.2. That means that only chunks with hybrid similarity score of 20 or higher will be retrieved.',
'RAGFlow employs either a combination of weighted keyword similarity and weighted vector cosine similarity, or a combination of weighted keyword similarity and weighted reranking score during retrieval. This parameter sets the threshold for similarities between the user query and chunks. Any chunk with a similarity score below this threshold will be excluded from the results. By default, the threshold is set to 0.2. This means that only chunks with hybrid similarity score of 20 or higher will be retrieved.',
vectorSimilarityWeight: 'Keyword similarity weight',
vectorSimilarityWeightTip:
'This sets the weight of keyword similarity in the combined similarity score, either used with vector cosine similarity or with reranking score. The total of the two weights must equal 1.0.',
@ -595,21 +595,21 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
systemModelSettings: 'System Model Settings',
chatModel: 'Chat model',
chatModelTip:
'The default chat LLM all the newly created knowledgebase will use.',
'The default chat model for each newly created knowledge base.',
embeddingModel: 'Embedding model',
embeddingModelTip:
'The default embedding model all the newly created knowledgebase will use.',
'The default embedding model for each newly created knowledge base. If you cannot find an embedding model from the dropdown, check if you are using RAGFlow slim edition (which does not include embedding models) or check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.',
img2txtModel: 'Img2txt model',
img2txtModelTip:
'The default multi-module model all the newly created knowledgebase will use. It can describe a picture or video.',
'The default img2txt model for each newly created knowledge base. It describes a picture or video. If you cannot find a model from the dropdown, check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.',
sequence2txtModel: 'Speech2txt model',
sequence2txtModelTip:
'The default ASR model all the newly created knowledgebase will use. Use this model to translate voices to corresponding text.',
'The default ASR model for each newly created knowledgebase. Use this model to translate voices to corresponding text.',
rerankModel: 'Rerank model',
rerankModelTip: `The default rerank model is used to rerank chunks retrieved by users' questions.`,
rerankModelTip: `The default rerank model for reranking chunks. If you cannot find a model from the dropdown, check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.`,
ttsModel: 'TTS Model',
ttsModelTip:
'The default TTS model will be used to generate speech during conversations upon request.',
'The default text-to-speech model. If you cannot find a model from the dropdown, check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.',
workspace: 'Workspace',
upgrade: 'Upgrade',
addLlmTitle: 'Add LLM',

View File

@ -345,19 +345,19 @@ export default {
'El modelo LLM de chat predeterminado que todas las nuevas bases de conocimiento utilizarán.',
embeddingModel: 'Modelo de embeddings',
embeddingModelTip:
'El modelo de embeddings predeterminado que todas las nuevas bases de conocimiento utilizarán.',
'El modelo de incrustación predeterminado para cada nueva base de conocimiento creada. Si no puedes encontrar un modelo de incrustación en el menú desplegable, verifica si estás utilizando la edición slim de RAGFlow (que no incluye modelos de incrustación) o consulta https://ragflow.io/docs/dev/supported_models para comprobar si tu proveedor de modelos admite este modelo.',
img2txtModel: 'Modelo de img2txt',
img2txtModelTip:
'El modelo multimódulo predeterminado que todas las nuevas bases de conocimiento utilizarán. Puede describir una imagen o video.',
'El modelo predeterminado img2txt para cada base de conocimiento recién creada. Describe una imagen o video. Si no puedes encontrar un modelo en el menú desplegable, consulta https://ragflow.io/docs/dev/supported_models para ver si tu proveedor de modelos admite este modelo.',
sequence2txtModel: 'Modelo de secuencia a texto',
sequence2txtModelTip:
'El modelo ASR predeterminado que todas las nuevas bases de conocimiento utilizarán. Usa este modelo para transcribir voces a texto correspondiente.',
'El modelo ASR predeterminado que todas las nuevas bases de conocimiento utilizarán. Usa este modelo para transcribir voces a texto correspondiente. Si no puedes encontrar un modelo en el menú desplegable, consulta https://ragflow.io/docs/dev/supported_models para ver si tu proveedor de modelos admite este modelo.',
rerankModel: 'Modelo de reordenamiento',
rerankModelTip:
'El modelo de reordenamiento predeterminado que se usará para reordenar los fragmentos recuperados por las preguntas de los usuarios.',
'El modelo de rerank predeterminado para reranking de fragmentos. Si no encuentra un modelo en el menú desplegable, consulte https://ragflow.io/docs/dev/supported_models para comprobar si su proveedor de modelos es compatible con este modelo.',
ttsModel: 'Modelo TTS',
ttsModelTip:
'El modelo TTS predeterminado que se usará para generar discurso durante las conversaciones cuando se solicite.',
'El modelo de text-to-speech predeterminado. Si no encuentra un modelo en el menú desplegable, consulte https://ragflow.io/docs/dev/supported_models para comprobar si su proveedor de modelos es compatible con este modelo.',
workspace: 'Espacio de trabajo',
upgrade: 'Actualizar',
addLlmTitle: 'Agregar LLM',

View File

@ -515,18 +515,18 @@ export default {
'Model LLM obrolan default yang akan digunakan semua basis pengetahuan baru yang dibuat.',
embeddingModel: 'Model Embedding',
embeddingModelTip:
'Model embedding default yang akan digunakan semua basis pengetahuan baru yang dibuat.',
'Model embedding default untuk setiap basis pengetahuan baru yang dibuat. Jika Anda tidak dapat menemukan model embedding dari dropdown, periksa apakah Anda menggunakan RAGFlow slim edition (yang tidak menyertakan model embedding) atau periksa https://ragflow.io/docs/dev/supported_models untuk melihat apakah penyedia model Anda mendukung model ini.',
img2txtModel: 'Model Img2txt',
img2txtModelTip:
'Model multi-modul default yang akan digunakan semua basis pengetahuan baru yang dibuat. Ini dapat menggambarkan gambar atau video.',
'Model img2txt default untuk setiap basis pengetahuan yang baru dibuat. Model ini menggambarkan gambar atau video. Jika Anda tidak dapat menemukan model dari menu dropdown, periksa https://ragflow.io/docs/dev/supported_models untuk melihat apakah penyedia model Anda mendukung model ini.',
sequence2txtModel: 'Model Speech2txt',
sequence2txtModelTip:
'Model ASR default yang akan digunakan semua basis pengetahuan baru yang dibuat. Gunakan model ini untuk menerjemahkan suara ke teks yang sesuai.',
'Model ASR default yang akan digunakan semua basis pengetahuan baru yang dibuat. Gunakan model ini untuk menerjemahkan suara ke teks yang sesuai. Jika Anda tidak dapat menemukan model dari menu dropdown, periksa https://ragflow.io/docs/dev/supported_models untuk melihat apakah penyedia model Anda mendukung model ini.',
rerankModel: 'Model Rerank',
rerankModelTip: `Model rerank default digunakan untuk mererank potongan yang diambil oleh pertanyaan pengguna.`,
rerankModelTip: `Model rerank default untuk reranking potongan teks. Jika Anda tidak dapat menemukan model dari dropdown, periksa https://ragflow.io/docs/dev/supported_models untuk melihat apakah penyedia model Anda mendukung model ini.`,
ttsModel: 'Model TTS',
ttsModelTip:
'Model TTS default akan digunakan untuk menghasilkan ucapan selama percakapan atas permintaan.',
'Model text-to-speech default. Jika Anda tidak dapat menemukan model dari dropdown, periksa https://ragflow.io/docs/dev/supported_models untuk melihat apakah penyedia model Anda mendukung model ini.',
workspace: 'Ruang Kerja',
upgrade: 'Tingkatkan',
addLlmTitle: 'Tambahkan LLM',

View File

@ -510,18 +510,18 @@ export default {
'新しく作成されたナレッジベースが使用するデフォルトのチャットLLM。',
embeddingModel: '埋め込みモデル',
embeddingModelTip:
'新しく作成されたナレッジベースが使用するデフォルトの埋め込みモデル。',
'新しく作成された各ナレッジベースのデフォルト埋め込みモデルです。ドロップダウンから埋め込みモデルが見つからない場合は、RAGFlowスリムエディション埋め込みモデルを含まないを使用しているか、https://ragflow.io/docs/dev/supported_models を確認して、モデルプロバイダーがこのモデルをサポートしているかどうかを確認してください。',
img2txtModel: '画像からテキストへのモデル',
img2txtModelTip:
'新しく作成されたナレッジベースが使用するデフォルトのマルチモジュールモデル。画像やビデオを説明できます。',
'新しく作成された知識ベースごとのデフォルトのimg2txtモデル。それは画像や動画を説明します。ドロップダウンからモデルが見つからない場合は、https://ragflow.io/docs/dev/supported_models を確認して、モデルプロバイダーがこのモデルをサポートしているかどうかを確認してください。',
sequence2txtModel: 'シーケンスからテキストへのモデル',
sequence2txtModelTip:
'新しく作成されたナレッジベースが使用するデフォルトのASRモデル。音声を対応するテキストに変換するために使用します。',
'新しく作成されたナレッジベースが使用するデフォルトのASRモデル。音声を対応するテキストに変換するために使用します。ドロップダウンからモデルが見つからない場合は、https://ragflow.io/docs/dev/supported_models を確認して、モデルプロバイダーがこのモデルをサポートしているかどうかを確認してください。',
rerankModel: '再ランクモデル',
rerankModelTip: `ユーザーの質問によって取得されたチャンクを再ランク付けするために使用されるデフォルトの再ランクモデル`,
rerankModelTip: `チャンクをrerankingするためのデフォルトのrerankモデル。ドロップダウンからモデルが見つからない場合は、https://ragflow.io/docs/dev/supported_models を確認して、ご使用のモデルプロバイダーがこのモデルをサポートしているかをご確認ください`,
ttsModel: 'TTSモデル',
ttsModelTip:
'会話中にリクエストに応じて音声を生成するために使用されるデフォルトのTTSモデル。',
'デフォルトのtext-to-speechモデル。ドロップダウンからモデルが見つからない場合は、https://ragflow.io/docs/dev/supported_models を確認して、ご使用のモデルプロバイダーがこのモデルをサポートしているかをご確認ください。',
workspace: 'ワークスペース',
upgrade: 'アップグレード',
addLlmTitle: 'LLMを追加',

View File

@ -504,19 +504,19 @@ export default {
'O modelo LLM padrão que todos os novos bancos de conhecimento usarão.',
embeddingModel: 'Modelo de incorporação',
embeddingModelTip:
'O modelo de incorporação padrão que todos os novos bancos de conhecimento usarão.',
'O modelo de incorporação padrão para cada nova base de conhecimento criada. Se você não encontrar um modelo de incorporação na lista suspensa, verifique se está usando a edição slim do RAGFlow (que não inclui modelos de incorporação) ou consulte https://ragflow.io/docs/dev/supported_models para verificar se o provedor do modelo suporta este modelo.',
img2txtModel: 'Modelo Img2Txt',
img2txtModelTip:
'O modelo multimodal padrão que todos os novos bancos de conhecimento usarão. Ele pode descrever uma imagem ou vídeo.',
'O modelo padrão img2txt para cada base de conhecimento recém-criada. Ele descreve uma imagem ou vídeo. Se você não conseguir encontrar um modelo no menu suspenso, verifique https://ragflow.io/docs/dev/supported_models para ver se seu provedor de modelo suporta este modelo.',
sequence2txtModel: 'Modelo Speech2Txt',
sequence2txtModelTip:
'O modelo ASR padrão que todos os novos bancos de conhecimento usarão. Use este modelo para converter vozes em texto correspondente.',
'O modelo ASR padrão que todos os novos bancos de conhecimento usarão. Use este modelo para converter vozes em texto correspondente. Se você não conseguir encontrar um modelo no menu suspenso, verifique https://ragflow.io/docs/dev/supported_models para ver se seu provedor de modelo suporta este modelo.',
rerankModel: 'Modelo de Reordenação',
rerankModelTip:
'O modelo de reordenação padrão usado para reordenar os fragmentos recuperados pelas perguntas dos usuários.',
'O modelo de rerank padrão para reranking de trechos. Se você não encontrar um modelo no menu suspenso, verifique https://ragflow.io/docs/dev/supported_models para ver se o seu provedor de modelo oferece suporte a este modelo.',
ttsModel: 'Modelo TTS',
ttsModelTip:
'O modelo TTS padrão será usado para gerar fala durante as conversas sob demanda.',
'O modelo padrão de text-to-speech. Se você não encontrar um modelo no menu suspenso, verifique https://ragflow.io/docs/dev/supported_models para ver se o seu provedor de modelo oferece suporte a este modelo.',
workspace: 'Área de trabalho',
upgrade: 'Atualizar',
addLlmTitle: 'Adicionar LLM',

View File

@ -561,18 +561,18 @@ export default {
'LLM trò chuyện mặc định mà tất cả các cơ sở kiến thức mới tạo sẽ sử dụng.',
embeddingModel: 'Mô hình nhúng',
embeddingModelTip:
'Mô hình nhúng mặc định mà tất cả các cơ sở kiến thức mới tạo sẽ sử dụng.',
'Mô hình nhúng mặc định cho từng cơ sở tri thức mới được tạo. Nếu bạn không tìm thấy mô hình nhúng từ danh sách thả xuống, hãy kiểm tra xem bạn có đang sử dụng phiên bản RAGFlow slim (không bao gồm các mô hình nhúng) hay không, hoặc kiểm tra https://ragflow.io/docs/dev/supported_models để xem nhà cung cấp mô hình của bạn có hỗ trợ mô hình này không.',
img2txtModel: 'Mô hình img2txt',
img2txtModelTip:
'Mô hình đa mô-đun mặc định mà tất cả các cơ sở kiến thức mới tạo sẽ sử dụng. Nó có thể mô tả hình ảnh hoặc video.',
'Mô hình img2txt mặc định cho mỗi cơ sở tri thức mới được tạo. Nó mô tả một bức tranh hoặc video. Nếu bạn không thể tìm thấy mô hình từ danh sách thả xuống, hãy kiểm tra https://ragflow.io/docs/dev/supported_models để xem nhà cung cấp mô hình của bạn có hỗ trợ mô hình này không.',
sequence2txtModel: 'Mô hình speech2txt',
sequence2txtModelTip:
'Mô hình ASR mặc định mà tất cả các cơ sở kiến thức mới tạo sẽ sử dụng. Sử dụng mô hình này để chuyển đổi giọng nói thành văn bản tương ứng.',
'Mô hình ASR mặc định mà tất cả các cơ sở kiến thức mới tạo sẽ sử dụng. Sử dụng mô hình này để chuyển đổi giọng nói thành văn bản tương ứng. Nếu bạn không thể tìm thấy mô hình từ danh sách thả xuống, hãy kiểm tra https://ragflow.io/docs/dev/supported_models để xem nhà cung cấp mô hình của bạn có hỗ trợ mô hình này không.',
rerankModel: 'Mô hình xếp hạng lại',
rerankModelTip: `Mô hình xếp hạng lại mặc định được sử dụng để xếp hạng lại các khối được truy xuất bởi các câu hỏi của người dùng.`,
rerankModelTip: `Mô hình rerank mặc định để reranking các đoạn văn bản. Nếu bạn không tìm thấy mô hình nào từ danh sách thả xuống, hãy kiểm tra https://ragflow.io/docs/dev/supported_models để xem nhà cung cấp mô hình của bạn có hỗ trợ mô hình này không.`,
ttsModel: 'Mô hình TTS',
ttsModelTip:
'Mô hình TTS mặc định sẽ được sử dụng để tạo giọng nói trong quá trình trò chuyện theo yêu cầu.',
'Mô hình text-to-speech mặc định. Nếu bạn không tìm thấy mô hình nào từ danh sách thả xuống, hãy kiểm tra https://ragflow.io/docs/dev/supported_models để xem nhà cung cấp mô hình của bạn có hỗ trợ mô hình này không.',
workspace: 'Không gian làm việc',
upgrade: 'Nâng cấp',
addLlmTitle: 'Thêm LLM',

View File

@ -161,7 +161,7 @@ export default {
topKTip: `K塊將被送入Rerank型號。`,
delimiter: `文字分段標識符`,
delimiterTip:
'支持多字符作為分隔符,多字符分隔符用 包裹。如配置成:\\n`##`; 系統將首先使用換行符、兩個#號以及分號先對文本進行分割,隨後再對分得的小文本塊按照「建议文本块大小」設定的大小進行拼裝。在设置文本分段標識符之前,請確保您已理解上述文本分段切片機制。',
'支持多字符作為分隔符,多字符用 `` 分隔符包裹。若配置成:\\n`##`; 系統將首先使用換行符、兩個#號以及分號先對文本進行分割,隨後再對分得的小文本塊按照「建议文本块大小」設定的大小進行拼裝。在设置文本分段標識符之前,請確保您已理解上述文本分段切片機制。',
html4excel: '表格轉HTML',
html4excelTip: `啟用後,電子表格將解析為 HTML 表格,一張表格最多 256 行。否則,會按行解析成鍵值對。`,
autoKeywords: '自動關鍵字',
@ -575,19 +575,19 @@ export default {
modify: '修改',
systemModelSettings: '系統模型設置',
chatModel: '聊天模型',
chatModelTip: '所有新創建的知識庫都會使用默認的聊天LLM。',
chatModelTip: '所有新創建的知識庫都會使用默認的聊天模型。',
ttsModel: '語音合成模型',
ttsModelTip: '默認的tts模型會被用於在對話過程中請求語音生成時使用。',
ttsModelTip: '默認的tts模型會被用於在對話過程中請求語音生成時使用。如未显示可选模型,请根据 https://ragflow.io/docs/dev/supported_models 确认你的模型供应商是否提供该模型。',
embeddingModel: '嵌入模型',
embeddingModelTip: '所有新創建的知識庫都將使用的默認嵌入模型。',
embeddingModelTip: '如未顯示可選模型,請檢查你是否在使用 RAGFlow slim 版(不含嵌入模型);或根據 https://ragflow.io/docs/dev/supported_models 確認你的模型供應商是否提供該模型。',
img2txtModel: 'img2Txt模型',
img2txtModelTip:
'所有新創建的知識庫都將使用默認的多模塊模型。它可以描述圖片或視頻。',
'所有新創建的知識庫都將使用默認的 img2txt 模型。它可以描述圖片或視頻。如未顯示可選模型,請根據 https://ragflow.io/docs/dev/supported_models 確認你的模型供應商是否提供該模型。',
sequence2txtModel: 'speech2Txt模型',
sequence2txtModelTip:
'所有新創建的知識庫都將使用默認的 ASR 模型。使用此模型將語音翻譯為相應的文本。',
'所有新創建的知識庫都將使用默認的 ASR 模型。使用此模型將語音翻譯為相應的文本。如未顯示可選模型,請根據 https://ragflow.io/docs/dev/supported_models 確認你的模型供應商是否提供該模型。',
rerankModel: 'rerank模型',
rerankModelTip: `默認的重讀模型用於用戶問題檢索到重讀塊`,
rerankModelTip: `默認的 reranking 模型。如未顯示可選模型,請根據 https://ragflow.io/docs/dev/supported_models 確認你的模型供應商是否提供該模型`,
workspace: '工作空間',
upgrade: '升級',
addLlmTitle: '添加Llm',
@ -596,7 +596,7 @@ export default {
modelUid: '模型uid',
modelType: '模型類型',
addLlmBaseUrl: '基礎 Url',
vision: '是否支持Vision',
vision: '是否支持 Vision',
modelNameMessage: '請輸入模型名稱!',
modelTypeMessage: '請輸入模型類型!',
baseUrlNameMessage: '請輸入基礎 Url',

View File

@ -161,7 +161,7 @@ export default {
topKTip: `K块将被送入Rerank型号。`,
delimiter: `文本分段标识符`,
delimiterTip:
'支持多字符作为分隔符,多字符分隔符用 ` 包裹。如配置成:\\n`##`; 系统将首先使用换行符、两个#号以及分号先对文本进行分割,随后再对分得的小文本块按照「建议文本块大小」设定的大小进行拼装。在设置文本分段标识符前请确保理解上述文本分段切片机制。',
'支持多字符作为分隔符,多字符用 `` 分隔符包裹。若配置成:\\n`##`; 系统将首先使用换行符、两个#号以及分号先对文本进行分割,随后再对分得的小文本块按照「建议文本块大小」设定的大小进行拼装。在设置文本分段标识符前请确保理解上述文本分段切片机制。',
html4excel: '表格转HTML',
html4excelTip: `开启后电子表格会被解析为 HTML 表格,每张表格最多 256 行,否则会按行解析为键值对。`,
autoKeywords: '自动关键词提取',
@ -592,19 +592,19 @@ General实体和关系提取提示来自 GitHub - microsoft/graphrag基于
modify: '修改',
systemModelSettings: '系统模型设置',
chatModel: '聊天模型',
chatModelTip: '所有新创建的知识库都会使用默认的聊天LLM。',
chatModelTip: '所有新创建的知识库都会使用默认的聊天模型。',
ttsModel: 'TTS模型',
ttsModelTip: '默认的tts模型会被用于在对话过程中请求语音生成时使用',
ttsModelTip: '默认的tts模型会被用于在对话过程中请求语音生成时使用。如未显示可选模型,请根据 https://ragflow.io/docs/dev/supported_models 确认你的模型供应商是否提供该模型。',
embeddingModel: '嵌入模型',
embeddingModelTip: '所有新创建的知识库都将使用的默认嵌入模型。',
embeddingModelTip: '所有新创建的知识库使用的默认嵌入模型。如未显示可选模型,请检查你是否在使用 RAGFlow slim 版(不含嵌入模型);或根据 https://ragflow.io/docs/dev/supported_models 确认你的模型供应商是否提供该模型。',
img2txtModel: 'Img2txt模型',
img2txtModelTip:
'所有新创建的知识库都将使用默认的多模块模型。 它可以描述图片或视频。',
'所有新创建的知识库都将使用默认的 img2txt 模型。 它可以描述图片或视频。如未显示可选模型,请根据 https://ragflow.io/docs/dev/supported_models 确认你的模型供应商是否提供该模型。',
sequence2txtModel: 'Speech2txt模型',
sequence2txtModelTip:
'所有新创建的知识库都将使用默认的 ASR 模型。 使用此模型将语音翻译为相应的文本。',
'所有新创建的知识库都将使用默认的 ASR 模型。 使用此模型将语音翻译为相应的文本。如未显示可选模型,请根据 https://ragflow.io/docs/dev/supported_models 确认你的模型供应商是否提供该模型。',
rerankModel: 'Rerank模型',
rerankModelTip: `默认的重读模型用于用户问题检索到重读块`,
rerankModelTip: `默认的 reranking 模型。如未显示可选模型,请根据 https://ragflow.io/docs/dev/supported_models 确认你的模型供应商是否提供该模型`,
workspace: '工作空间',
upgrade: '升级',
addLlmTitle: '添加 LLM',