> For the complete documentation index, see [llms.txt](https://api.docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://api.docs.blockbrain.ai/de/erste-schritte/wissensmanagement/eine-datenbank-erstellen.md).
# Eine Datenbank erstellen
[Dokumentendatenbanken](/de/konzepte/knowledge-base.md) speichern und bereitstellen die Quellmaterialien, auf die Wissens-Workflows angewiesen sind: Dateien, E-Mail-Inhalte und strukturierte Dokumente. In diesem Stack werden Dokumente über kurzlebige Verweise mit Gesprächen (Data Rooms) und Insights verknüpft, was Abruf, Verarbeitung und Indexierung ermöglicht und gleichzeitig Herkunft und Zugriffssteuerungen bewahrt.
**Jede Datenbank kann Folgendes haben:**
* **Ordner**: Kann zur Organisation nach Projekt, Thema oder Wissensdomäne verwendet werden. Ein fein granularer Zugriff kann bestimmten Benutzern gewährt werden.
* **Dokumente**: Hauptentitäten unterschiedlicher Typen wie PDFs, Word-/Office-Dokumente, E-Mails, Tabellenkalkulationen, strukturierte JSON/XML-Dateien und Bilder, die für RAG indiziert, in Chunks zerlegt und vektorisiert werden.
* Dokumente können manuell, über die API oder durch den bereitgestellten Web-Crawler importiert werden.
## Neue Knowledgebase / Datenbank erstellen
## POST /knowledge\_base
> Create Knowledgebase
```json
{"openapi":"3.1.0","info":{"title":"Blockbrain Knowledge Bots","version":"0.2.6"},"security":[{"HTTPBearer":[]}],"components":{"securitySchemes":{"HTTPBearer":{"type":"http","scheme":"bearer"}},"schemas":{"KnowledgeBaseCreate":{"properties":{"name":{"type":"string","title":"Name"},"description":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Description"},"is_public":{"type":"boolean","title":"Is Public","default":false},"embeddingModel":{"$ref":"#/components/schemas/EmbeddingModel","default":"azure-ada-002"},"chunkSize":{"anyOf":[{"type":"integer","maximum":30000,"minimum":0},{"type":"null"}],"title":"Chunksize","default":1200},"chunkOverlap":{"anyOf":[{"type":"integer","maximum":12000,"minimum":0},{"type":"null"}],"title":"Chunkoverlap","default":200},"markedLanguages":{"items":{"type":"string"},"type":"array","maxItems":3,"title":"Markedlanguages","default":[]},"enableExtractTable":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Enableextracttable","default":false},"enableExtractImage":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Enableextractimage","default":true},"enableConvertImage":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Enableconvertimage","default":false},"useContextualChunking":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Usecontextualchunking","default":false},"enableMultiplePdfPagesPerChunk":{"type":"boolean","title":"Enablemultiplepdfpagesperchunk","default":false}},"type":"object","required":["name","description"],"title":"KnowledgeBaseCreate"},"EmbeddingModel":{"type":"string","enum":["azure-ada-002","azure-emb-3-large","openai-ada-002","openai-emb-3-small","openai-emb-3-large","sagemaker-bge","vertex-ai-embedding-english-text-4","vertex-ai-embedding-multilingual-text-2","gemini-embedding-001"],"title":"EmbeddingModel"},"CommonResponseDTO":{"properties":{"code":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Code"},"key":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Key"},"body":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Body"}},"type":"object","title":"CommonResponseDTO"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}},"paths":{"/knowledge_base":{"post":{"tags":["knowledge_base"],"summary":"Create Knowledgebase","operationId":"create_knowledgebase_knowledge_base_post","requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/KnowledgeBaseCreate"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/CommonResponseDTO"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}}}}
```
Die Antwort enthält eine `Textkörper` Eigenschaft, die die `_id` der erstellten Knowledgebase enthält. Diese ID kann zum Ändern der DB, zum Erstellen von Ordnern und zum Hochladen von Dokumenten verwendet werden.
## Nächster Schritt
Jetzt, da Sie eine Knowledgebase erstellt haben, können Sie [Ordner erstellen](/de/erste-schritte/wissensmanagement/eine-datenbank-erstellen/ordner-erstellen.md) und [Dokumente in Datenbanken hochladen](/de/erste-schritte/wissensmanagement/dokumente-in-datenbanken-hochladen.md).
## Unterstützte Dateitypen
Jeder Standard-Dateityp wird bereits von unseren Indexierungs- und Vektorisierungspipelines unterstützt. Dennoch erweitern wir ständig die Kompatibilität.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://api.docs.blockbrain.ai/de/erste-schritte/wissensmanagement/eine-datenbank-erstellen.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.