mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-19 12:39:59 +08:00
Miscellaneous doc updates and refactored team management doc. (#6730)
### What problem does this PR solve? #5576, #6672 ### Type of change - [x] Documentation and UI Update
This commit is contained in:
writinwaters
GitHub
parent
132eae9d5b
commit
31296ad70f
@ -65,14 +65,6 @@ An embedding model converts chunks into embeddings. It cannot be changed once th
|
||||
The following embedding models can be deployed locally:
|
||||
|
||||
- BAAI/bge-large-zh-v1.5
|
||||
- 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
|
||||
- maidalun1020/bce-embedding-base_v1
|
||||
|
||||
### Upload file
|
||||
|
||||
@ -36,4 +36,4 @@ If you set the page rank value to a non-integer, say 1.7, it will be rounded dow
|
||||
|
||||
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.
|
||||
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 retrieved 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.
|
||||
@ -1,5 +1,5 @@
|
||||
---
|
||||
sidebar_position: 5
|
||||
sidebar_position: 6
|
||||
slug: /manage_files
|
||||
---
|
||||
|
||||
|
||||
@ -1,51 +0,0 @@
|
||||
---
|
||||
sidebar_position: 4
|
||||
slug: /manage_team_members
|
||||
---
|
||||
|
||||
# Team
|
||||
|
||||
Invite or remove team members, join or leave a team.
|
||||
|
||||
---
|
||||
|
||||
By default, each RAGFlow user is assigned a single team named after their name. RAGFlow allows you to invite RAGFlow users to your team. Your team members can help you:
|
||||
|
||||
- Upload documents to your datasets (knowledge bases).
|
||||
- Update document configurations in your datasets.
|
||||
- Update the default configurations for your datasets.
|
||||
- Parse documents in your datasets.
|
||||
|
||||
:::danger IMPORTANT
|
||||
To allow your team members to view and update your knowledge base, ensure that you set **Permissions** on its **Configuration** page from **Only me** to **Team**.
|
||||
:::
|
||||
|
||||
:::tip NOTE
|
||||
Team members are currently *not* allowed to invite users to your team, and only you, the team owner, is permitted to do so.
|
||||
:::
|
||||
|
||||
To enter the **Team** page, click on your avatar in the top right corner of the page **>** Team:
|
||||
|
||||
|
||||
|
||||
_On the **Team** page, you can view the information about members of your team and the teams you have joined._
|
||||
|
||||
## Invite team members
|
||||
|
||||
You are, by default, the owner of your own team and the only person permitted to invite users to join your team or remove team members.
|
||||
|
||||
:::danger IMPORTANT
|
||||
When using email address to invite a team member, ensure it is associated with an existing RAGFlow account to avoid errors.
|
||||
:::
|
||||
|
||||
|
||||
|
||||
## Remove team members
|
||||
|
||||
|
||||
|
||||
## Accept or decline team invite
|
||||
|
||||
|
||||
|
||||
_After accepting the team invite, you should be able to view and update the team owner's knowledge bases whose **Permissions** is set to **Team**._
|
||||
@ -1,5 +1,5 @@
|
||||
---
|
||||
sidebar_position: 7
|
||||
sidebar_position: 8
|
||||
slug: /run_health_check
|
||||
---
|
||||
|
||||
|
||||
8
docs/guides/team/_category_.json
Normal file
8
docs/guides/team/_category_.json
Normal file
@ -0,0 +1,8 @@
|
||||
{
|
||||
"label": "Team",
|
||||
"position": 4,
|
||||
"link": {
|
||||
"type": "generated-index",
|
||||
"description": "Team-specific guides."
|
||||
}
|
||||
}
|
||||
42
docs/guides/team/join_or_leave_team.md
Normal file
42
docs/guides/team/join_or_leave_team.md
Normal file
@ -0,0 +1,42 @@
|
||||
---
|
||||
sidebar_position: 2
|
||||
slug: /join_or_leave_team
|
||||
---
|
||||
|
||||
# Join or leave a team
|
||||
|
||||
Accept a team invite to join a team, decline a team invite, or leave a team.
|
||||
|
||||
---
|
||||
|
||||
Once you join a team, you can do the following:
|
||||
|
||||
- Upload documents to the team owner's shared datasets (knowledge bases).
|
||||
- Update document configurations in the team owner's shared datasets.
|
||||
- Update the default configurations for the team owner's shared datasets.
|
||||
- Parse documents in the team owner's shared datasets.
|
||||
|
||||
:::tip NOTE
|
||||
You cannot invite users to a team unless you are its owner.
|
||||
:::
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Ensure that your Email address that received the team invitation is associated with a RAGFlow user account.
|
||||
2. To view and update the team owner's shared knowledge base, The team owner must set a knowledge base's **Permissions** to **Team**.
|
||||
|
||||
## Accept or decline team invite
|
||||
|
||||
Click on your avatar in the top right corner of the page, then select **Team** in the left-hand panel to access the **Team** page.
|
||||
|
||||
|
||||
|
||||
_On the **Team** page, you can view the information about members of your team and the teams you have joined._
|
||||
|
||||
|
||||
|
||||
_After accepting the team invite, you should be able to view and update the team owner's knowledge bases whose **Permissions** is set to **Team**._
|
||||
|
||||
## Leave a joined team
|
||||
|
||||
|
||||
43
docs/guides/team/manage_team_members.md
Normal file
43
docs/guides/team/manage_team_members.md
Normal file
@ -0,0 +1,43 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
slug: /manage_team_members
|
||||
---
|
||||
|
||||
# Team
|
||||
|
||||
Invite or remove team members.
|
||||
|
||||
---
|
||||
|
||||
By default, each RAGFlow user is assigned a single team named after their name. RAGFlow allows you to invite RAGFlow users to your team. Your team members can help you:
|
||||
|
||||
- Upload documents to your shared datasets (knowledge bases).
|
||||
- Update document configurations in your shared datasets.
|
||||
- Update the default configurations for your shared datasets.
|
||||
- Parse documents in your shared datasets.
|
||||
|
||||
:::tip NOTE
|
||||
- Your team members are currently *not* allowed to invite users to your team, and only you, the team owner, is permitted to do so.
|
||||
- Sharing added models with team members is only available in RAGFlow's Enterprise edition.
|
||||
:::
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Ensure that the invited team member is a RAGFlow user and that the Email address used is associated with a RAGFlow user account.
|
||||
2. To allow your team members to view and update your knowledge base, ensure that you set **Permissions** on its **Configuration** page from **Only me** to **Team**.
|
||||
|
||||
## Invite team members
|
||||
|
||||
Click on your avatar in the top right corner of the page, then select **Team** in the left-hand panel to access the **Team** page.
|
||||
|
||||
|
||||
|
||||
_On the **Team** page, you can view the information about members of your team and the teams you have joined._
|
||||
|
||||
You are, by default, the owner of your own team and the only person permitted to invite users to join your team or remove team members.
|
||||
|
||||
|
||||
|
||||
## Remove team members
|
||||
|
||||
|
||||
@ -3,12 +3,16 @@ sidebar_position: 11
|
||||
slug: /upgrade_ragflow
|
||||
---
|
||||
|
||||
# Upgrade
|
||||
# Upgrading
|
||||
import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
|
||||
Upgrade RAGFlow to `nightly-slim`/`nightly` or the latest, published release.
|
||||
|
||||
:::info NOTE
|
||||
Upgrading RAGFlow in itself will *not* remove your uploaded/historical data. However, be aware that `docker compose -f docker/docker-compose.yml down -v` will remove Docker container volumes, resulting in data loss.
|
||||
:::
|
||||
|
||||
## Upgrade RAGFlow to `nightly-slim`/`nightly`, the most recent, tested Docker image
|
||||
|
||||
`nightly-slim` refers to the RAGFlow Docker image *without* embedding models, while `nightly` refers to the RAGFlow Docker image with embedding models. For details on their differences, see [ragflow/docker/.env](https://github.com/infiniflow/ragflow/blob/main/docker/.env).
|
||||
@ -79,4 +83,19 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
|
||||
```bash
|
||||
docker compose -f docker/docker-compose.yml pull
|
||||
docker compose -f docker/docker-compose.yml up -d
|
||||
```
|
||||
```
|
||||
|
||||
## Frequently asked questions
|
||||
|
||||
### Upgrade RAGFlow in an offline environment (without Internet access)
|
||||
|
||||
1. From an environment with Internet access, pull the required Docker image.
|
||||
2. Save the Docker image to a **.tar** file.
|
||||
```bash
|
||||
docker save -o ragflow.v0.17.2.tar infiniflow/ragflow:v0.17.2
|
||||
```
|
||||
3. Copy the **.tar** file to the target server.
|
||||
4. Load the **.tar** file into Docker:
|
||||
```bash
|
||||
docker load -i ragflow.v0.17.2.tar
|
||||
```
|
||||
|
||||
@ -270,7 +270,7 @@ Ensure that you [upgrade **both** your code **and** Docker image to this release
|
||||
#### Added documents
|
||||
|
||||
- [Configurations](https://ragflow.io/docs/dev/configurations)
|
||||
- [Manage team members](https://ragflow.io/docs/dev/manage_team_members)
|
||||
- [Manage team members](./guides/team/manage_team_members.md)
|
||||
- [Run health check on RAGFlow's dependencies](https://ragflow.io/docs/dev/run_health_check)
|
||||
|
||||
## v0.13.0
|
||||
|
||||
@ -170,7 +170,7 @@ export default {
|
||||
'Ein Trennzeichen oder Separator kann aus einem oder mehreren Sonderzeichen bestehen. Bei mehreren Zeichen stellen Sie sicher, dass sie in Backticks (` `) eingeschlossen sind. Wenn Sie beispielsweise Ihre Trennzeichen so konfigurieren: \\n`##`;, dann werden Ihre Texte an Zeilenumbrüchen, doppelten Rautenzeichen (##) oder Semikolons getrennt. Setzen Sie Trennzeichen nur nachdem Sie das Mechanismus der Textsegmentierung und -chunking verstanden haben.',
|
||||
html4excel: 'Excel zu HTML',
|
||||
html4excelTip:
|
||||
'Wenn aktiviert, wird die Tabelle in HTML-Tabellen umgewandelt, mit maximal 256 Zeilen pro Tabelle. Andernfalls wird sie in Schlüssel-Wert-Paare nach Zeilen umgewandelt.',
|
||||
'Verwenden Sie dies zusammen mit der General-Schnittmethode. Wenn deaktiviert, werden Tabellenkalkulationsdateien (XLSX, XLS (Excel97~2003)) zeilenweise in Schlüssel-Wert-Paare analysiert. Wenn aktiviert, werden Tabellenkalkulationsdateien in HTML-Tabellen umgewandelt. Wenn die ursprüngliche Tabelle mehr als 12 Zeilen enthält, teilt das System sie automatisch alle 12 Zeilen in mehrere HTML-Tabellen auf.',
|
||||
autoKeywords: 'Auto-Schlüsselwort',
|
||||
autoKeywordsTip:
|
||||
'Extrahieren Sie automatisch N Schlüsselwörter für jeden Abschnitt, um deren Ranking in Abfragen mit diesen Schlüsselwörtern zu verbessern. Beachten Sie, dass zusätzliche Tokens vom in den "Systemmodelleinstellungen" angegebenen Chat-Modell verbraucht werden. Sie können die hinzugefügten Schlüsselwörter eines Abschnitts in der Abschnittsliste überprüfen oder aktualisieren.',
|
||||
@ -355,7 +355,7 @@ export default {
|
||||
vietnamese: 'Vietnamesisch',
|
||||
pageRank: 'PageRank',
|
||||
pageRankTip:
|
||||
'Dies erhöht den Relevanzwert der Wissensdatenbank. Sein Wert wird dem Relevanzwert aller abgerufenen Chunks aus dieser Wissensdatenbank hinzugefügt. Nützlich, wenn Sie innerhalb mehrerer Wissensdatenbanken suchen und einer bestimmten einen höheren PageRank-Wert zuweisen möchten.',
|
||||
'Sie können während des Abrufs bestimmten Wissensdatenbanken eine höhere PageRank-Bewertung zuweisen. Die entsprechende Bewertung wird zu den hybriden Ähnlichkeitswerten der abgerufenen Chunks aus diesen Wissensdatenbanken addiert, wodurch deren Ranking erhöht wird. Weitere Informationen finden Sie unter https://ragflow.io/docs/dev/set_page_rank.',
|
||||
tagName: 'Tag',
|
||||
frequency: 'Häufigkeit',
|
||||
searchTags: 'Tags durchsuchen',
|
||||
|
||||
@ -165,7 +165,7 @@ export default {
|
||||
delimiterTip:
|
||||
'A delimiter or separator can consist of one or multiple special characters. If it is multiple characters, ensure they are enclosed in backticks( ``). For example, if you configure your delimiters like this: \\n`##`;, then your texts will be separated at line breaks, double hash symbols (##), and semicolons.',
|
||||
html4excel: 'Excel to HTML',
|
||||
html4excelTip: `When enabled, the spreadsheet will be parsed into HTML tables, and at most 256 rows for one table. Otherwise, it will be parsed into key-value pairs by row.`,
|
||||
html4excelTip: `Use with the General chunk method. When disabled, spreadsheets (XLSX or XLS(Excel97~2003)) in the knowledge base will be parsed into key-value pairs. When enabled, they will be parsed into HTML tables, splitting every 12 rows if the original table has more than 12 rows.`,
|
||||
autoKeywords: 'Auto-keyword',
|
||||
autoKeywordsTip: `Automatically extract N keywords for each chunk to increase their ranking for queries containing those keywords. Be aware that extra tokens will be consumed by the chat model specified in 'System model settings'. You can check or update the added keywords for a chunk from the chunk list. `,
|
||||
autoQuestions: 'Auto-question',
|
||||
@ -345,7 +345,7 @@ The above is the content you need to summarize.`,
|
||||
entityTypes: 'Entity types',
|
||||
vietnamese: 'Vietnamese',
|
||||
pageRank: 'Page rank',
|
||||
pageRankTip: `This increases the relevance score of the knowledge base. Its value will be added to the relevance score of all retrieved chunks from this knowledge base. Useful when you are searching within multiple knowledge bases and wanting to assign a higher pagerank score to a specific one.`,
|
||||
pageRankTip: `You can assign a higher PageRank score to specific knowledge bases during retrieval. The corresponding score is added to the hybrid similarity scores of retrieved chunks from these knowledge bases, increasing their ranking. See https://ragflow.io/docs/dev/set_page_rank for details.`,
|
||||
tagName: 'Tag',
|
||||
frequency: 'Frequency',
|
||||
searchTags: 'Search tags',
|
||||
|
||||
@ -154,7 +154,7 @@ export default {
|
||||
topKTip: `K fragmentos serán alimentados a los modelos de reordenamiento.`,
|
||||
delimiter: `Delimitadores para segmentación de texto`,
|
||||
html4excel: 'Excel a HTML',
|
||||
html4excelTip: `Excel se analizará en una tabla HTML o no. Si es FALSO, cada fila en Excel se formará como un fragmento.`,
|
||||
html4excelTip: `Usar junto con el método de fragmentación General. Cuando está desactivado, los archivos de hoja de cálculo (XLSX, XLS (Excel97~2003)) se analizan línea por línea como pares clave-valor. Cuando está activado, los archivos de hoja de cálculo se convierten en tablas HTML. Si la tabla original tiene más de 12 filas, el sistema la dividirá automáticamente en varias tablas HTML cada 12 filas.`,
|
||||
},
|
||||
|
||||
// Otros bloques de traducción
|
||||
|
||||
@ -158,7 +158,7 @@ export default {
|
||||
topKTip: `K potongan akan dimasukkan ke dalam model rerank.`,
|
||||
delimiter: `Pemisah untuk segmentasi teks`,
|
||||
html4excel: 'Excel ke HTML',
|
||||
html4excelTip: `Excel akan diparsing menjadi tabel HTML atau tidak. Jika FALSE, setiap baris di Excel akan dibentuk sebagai potongan.`,
|
||||
html4excelTip: `Gunakan bersama dengan metode pemotongan General. Ketika dinonaktifkan, file spreadsheet (XLSX, XLS (Excel97~2003)) akan dianalisis baris demi baris menjadi pasangan kunci-nilai. Ketika diaktifkan, file spreadsheet akan dianalisis menjadi tabel HTML. Jika tabel asli memiliki lebih dari 12 baris, sistem akan secara otomatis membagi menjadi beberapa tabel HTML setiap 12 baris.`,
|
||||
},
|
||||
knowledgeConfiguration: {
|
||||
titleDescription:
|
||||
|
||||
@ -160,7 +160,7 @@ export default {
|
||||
delimiter: `テキストセグメンテーションの区切り文字`,
|
||||
delimiterTip: 'デリミタやセパレータは、一つまたは複数の特殊文字で構成できます。複数の文字の場合、バッククォート(``)で囲むようにしてください。たとえば、デリミタを次のように設定した場合: \\n ## ;、テキストは行末、ダブルハッシュ記号(##)、およびセミコロンで分割されます。デリミタを設定する前に、テキストのセグメンテーションとチャンキングのメカニズムを理解していることを確認してください。',
|
||||
html4excel: 'ExcelをHTMLに変換',
|
||||
html4excelTip: `有効にすると、スプレッドシートはHTMLテーブルとして解析されます。それ以外の場合、キーと値のペアとして解析されます。`,
|
||||
html4excelTip: `General切片方法と併用してください。無効の場合、表計算ファイル（XLSX、XLS（Excel97~2003））は行ごとにキーと値のペアとして解析されます。有効の場合、表計算ファイルはHTML表として解析されます。元の表が12行を超える場合、システムは自動的に12行ごとに複数のHTML表に分割します。`,
|
||||
autoKeywords: '自動キーワード',
|
||||
autoKeywordsTip: `各チャンクに含まれるキーワードのランキングを向上させるために、自動的にN個のキーワードを抽出します。「システムモデル設定」で指定されたチャットモデルによって追加のトークンが消費されることに注意してください。チャンクリストから追加されたキーワードを確認または更新することができます。`,
|
||||
autoQuestions: '自動質問',
|
||||
@ -303,8 +303,7 @@ export default {
|
||||
randomSeedMessage: 'ランダムシードは必須です',
|
||||
entityTypes: 'エンティティタイプ',
|
||||
pageRank: 'ページランク',
|
||||
pageRankTip: `これは関連性スコアを高めるために使用されます。すべての取得されたチャンクの関連性スコアにこの数値が加算されます。
|
||||
特定のナレッジベースを最初に検索したい場合は、他のものよりも高いページランクスコアを設定してください。`,
|
||||
pageRankTip: `検索時に特定の知識ベースにより高いPageRankスコアを割り当てることができます。対応するスコアは、これらの知識ベースから取得されたチャンクのハイブリッド類似度スコアに加算され、ランキングが向上します。詳細については、https://ragflow.io/docs/dev/set_page_rank を参照してください。`,
|
||||
},
|
||||
chunk: {
|
||||
chunk: 'チャンク',
|
||||
|
||||
@ -167,7 +167,7 @@ export default {
|
||||
'Um delimitador ou separador pode consistir em um ou vários caracteres especiais. Se for múltiplos caracteres, certifique-se de que estejam entre crases (``). Por exemplo, se você configurar seus delimitadores assim: \\n`##`;, seus textos serão separados em quebras de linha, símbolos de hash duplo (##) ou ponto e vírgula. Defina os delimitadores apenas após entender o mecanismo de segmentação e particionamento de texto.',
|
||||
html4excel: 'Excel para HTML',
|
||||
html4excelTip:
|
||||
'Quando ativado, a planilha será analisada em tabelas HTML, com no máximo 256 linhas por tabela. Caso contrário, será analisada em pares chave-valor por linha.',
|
||||
'Use em conjunto com o método de fragmentação General. Quando desativado, arquivos de planilhas (XLSX, XLS (Excel97~2003)) serão analisados linha por linha como pares chave-valor. Quando ativado, os arquivos de planilhas serão convertidos em tabelas HTML. Se a tabela original tiver mais de 12 linhas, o sistema dividirá automaticamente em várias tabelas HTML a cada 12 linhas.',
|
||||
autoKeywords: 'Palavras-chave automáticas',
|
||||
autoKeywordsTip:
|
||||
'Extraia automaticamente N palavras-chave de cada bloco para aumentar sua classificação em consultas que contenham essas palavras-chave. Esteja ciente de que o modelo de chat especificado nas "Configurações do modelo do sistema" consumirá tokens adicionais. Você pode verificar ou atualizar as palavras-chave adicionadas a um bloco na lista de blocos.',
|
||||
@ -281,7 +281,7 @@ export default {
|
||||
entityTypes: 'Tipos de entidades',
|
||||
vietnamese: 'Vietnamita',
|
||||
pageRank: 'Ranking de páginas',
|
||||
pageRankTip: `Isso aumenta a pontuação de relevância da base de conhecimento. Seu valor será adicionado à pontuação de relevância de todos os fragmentos recuperados dessa base de conhecimento. Útil ao pesquisar em múltiplas bases e querer priorizar uma específica.`,
|
||||
pageRankTip: `Você pode atribuir uma pontuação PageRank mais alta a bases de conhecimento específicas durante a recuperação. A pontuação correspondente é adicionada às pontuações de similaridade híbrida dos fragmentos recuperados dessas bases de conhecimento, aumentando sua classificação. Veja https://ragflow.io/docs/dev/set_page_rank para mais detalhes.`,
|
||||
tagName: 'Etiqueta',
|
||||
frequency: 'Frequência',
|
||||
searchTags: 'Pesquisar etiquetas',
|
||||
|
||||
@ -164,7 +164,7 @@ export default {
|
||||
topKTip: `K khối sẽ được đưa vào các mô hình xếp hạng lại.`,
|
||||
delimiter: 'Dấu phân cách cho phân đoạn văn bản',
|
||||
html4excel: 'Excel sang HTML',
|
||||
html4excelTip: `Excel sẽ được phân tích cú pháp thành bảng HTML hay không. Nếu là FALSE, mỗi hàng trong Excel sẽ được tạo thành một khối.`,
|
||||
html4excelTip: `Sử dụng cùng với phương pháp cắt khúc General. Khi chưa được bật, tệp bảng tính (XLSX, XLS (Excel97~2003)) sẽ được phân tích theo dòng thành các cặp khóa-giá trị. Khi bật, tệp bảng tính sẽ được phân tích thành bảng HTML. Nếu bảng gốc vượt quá 12 dòng, hệ thống sẽ tự động chia thành nhiều bảng HTML mỗi 12 dòng.`,
|
||||
autoKeywords: 'Từ khóa tự động',
|
||||
autoKeywordsTip: `Tự động trích xuất N từ khóa cho mỗi khối để tăng thứ hạng của chúng trong các truy vấn chứa các từ khóa đó. Lưu ý rằng các token bổ sung sẽ được tiêu thụ bởi mô hình trò chuyện được chỉ định trong "Cài đặt mô hình hệ thống". Bạn có thể kiểm tra hoặc cập nhật các từ khóa đã thêm cho một khối từ danh sách khối.`,
|
||||
autoQuestions: 'Câu hỏi tự động',
|
||||
@ -315,7 +315,7 @@ export default {
|
||||
entityTypes: 'Loại thực thể',
|
||||
vietnamese: 'Tiếng Việt',
|
||||
pageRank: 'Xếp hạng trang',
|
||||
pageRankTip: `Điều này được sử dụng để tăng điểm liên quan. Điểm liên quan với tất cả các khối được truy xuất sẽ cộng với số này, Khi bạn muốn tìm kiếm cơ sở kiến thức đã cho ở vị trí đầu tiên, hãy đặt điểm "Page Rank" cao hơn những điểm khác.`,
|
||||
pageRankTip: `Bạn có thể gán điểm PageRank cao hơn cho các cơ sở kiến thức cụ thể trong quá trình truy xuất. Điểm tương ứng được cộng vào điểm tương đồng lai của các đoạn được truy xuất từ các cơ sở kiến thức này, làm tăng thứ hạng của chúng. Xem https://ragflow.io/docs/dev/set_page_rank để biết thêm chi tiết.`,
|
||||
tag: `<p>Cơ sở kiến thức sử dụng phương pháp phân đoạn 'Tag' hoạt động như một tập hợp thẻ. Các cơ sở kiến thức khác có thể sử dụng nó để gắn thẻ cho các đoạn của riêng chúng và các truy vấn tới các cơ sở kiến thức này cũng sẽ được gắn thẻ bằng tập hợp thẻ này.</p>
|
||||
<p>Cơ sở kiến thức sử dụng 'Tag' làm phương pháp phân đoạn sẽ <b>NOT</b> tham gia vào quy trình Tạo tăng cường truy xuất (RAG).</p>
|
||||
<p>Mỗi đoạn trong cơ sở kiến thức này là một cặp mô tả-thẻ độc lập.</p>
|
||||
|
||||
@ -163,7 +163,7 @@ export default {
|
||||
delimiterTip:
|
||||
'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。`,
|
||||
html4excelTip: `與 General 切片方法配合使用。未開啟狀態下，表格檔案（XLSX、XLS（Excel97~2003）會按行解析為鍵值對。開啟後，表格檔案會被解析為 HTML 表格。若原始表格超過 12 行，系統會自動按每 12 行拆分為多個 HTML 表格。`,
|
||||
autoKeywords: '自動關鍵字',
|
||||
autoKeywordsTip: `自動為每個文字區塊中提取 N 個關鍵詞，以提升查詢精度。請注意：此功能採用「系統模型設定」中設定的預設聊天模型提取關鍵詞，因此也會產生更多 Token 消耗。此外，你也可以手動更新生成的關鍵詞。`,
|
||||
autoQuestions: '自動問題',
|
||||
@ -333,8 +333,7 @@ export default {
|
||||
maxClusterTip: '最大聚類數。',
|
||||
entityTypes: '實體類型',
|
||||
pageRank: '頁面排名',
|
||||
pageRankTip: `這用來提高相關性分數。所有檢索到的區塊的相關性得分將加上該數字。
|
||||
當您想要先搜尋給定的知識庫時，請設定比其他人更高的 pagerank 分數。`,
|
||||
pageRankTip: `知識庫檢索時，你可以為特定知識庫設置較高的 PageRank 分數，該知識庫中匹配文本塊的混合相似度得分會自動疊加 PageRank 分數，從而提升排序權重。詳見 https://ragflow.io/docs/dev/set_page_rank。`,
|
||||
tagName: '標籤',
|
||||
frequency: '頻次',
|
||||
searchTags: '搜尋標籤',
|
||||
|
||||
@ -163,7 +163,7 @@ export default {
|
||||
delimiterTip:
|
||||
'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。`,
|
||||
html4excelTip: `与 General 切片方法配合使用。未开启状态下，表格文件（XLSX、XLS（Excel97~2003））会按行解析为键值对。开启后，表格文件会被解析为 HTML 表格。若原始表格超过 12 行，系统会自动按每 12 行拆分为多个 HTML 表格。`,
|
||||
autoKeywords: '自动关键词提取',
|
||||
autoKeywordsTip: `自动为每个文本块中提取 N 个关键词，用以提升查询精度。请注意：该功能采用“系统模型设置”中设置的默认聊天模型提取关键词，因此也会产生更多 Token 消耗。另外，你也可以手动更新生成的关键词。`,
|
||||
autoQuestions: '自动问题提取',
|
||||
@ -350,8 +350,7 @@ export default {
|
||||
maxClusterTip: '最大聚类数。',
|
||||
entityTypes: '实体类型',
|
||||
pageRank: '页面排名',
|
||||
pageRankTip: `这用于提高相关性得分。所有检索到的块的相关性得分将加上此数字。
|
||||
当您想首先搜索给定的知识库时，请设置比其他知识库更高的 pagerank 得分。`,
|
||||
pageRankTip: `知识库检索时，你可以为特定知识库设置较高的 PageRank 分数，该知识库中匹配文本块的混合相似度得分会自动叠加 PageRank 分数，从而提升排序权重。详见 https://ragflow.io/docs/dev/set_page_rank。`,
|
||||
tagName: '标签',
|
||||
frequency: '频次',
|
||||
searchTags: '搜索标签',
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user