> ## Documentation Index
> Fetch the complete documentation index at: https://docs.streamkap.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge Bases

> Stream a Kafka topic into a vector store as embeddings so Streamkap agents can retrieve from live data at run time

A knowledge base streams a Kafka topic through an embedding model into a vector store, keeping an always-current index your agents can retrieve from. Attach a knowledge base to an agent and it becomes a retrieval tool: the model decides when to look something up, and gets back the most relevant chunks from your data.

Knowledge bases live on the **Knowledge Bases** tab of the Agentic section. Creating and managing them requires the `write:agents` permission.

## Prerequisites

* An **LLM connection** with the **Embedding** capability — **OpenAI**, **Azure**, **Ollama**, **AWS Bedrock**, **Qwen**, or any **OpenAI-compatible** endpoint. See [Connections](/streaming-agents-connections#llm-connections).
* A **vector store** connection — Pinecone, pgvector, Milvus, Amazon OpenSearch, Elasticsearch, or Amazon S3 Vectors. See [Connections](/streaming-agents-connections#vector-stores).
* The **input Kafka topic** to embed.

<Note>
  No credentials yet? Where available, the [Streamkap Default Connections](/streaming-agents-connections#streamkap-default-connections) can serve as both the embedding model and the vector store for a quick test — each knowledge base gets its own isolated namespace on the managed index automatically.
</Note>

## Create a Knowledge Base

Creation is a single form (not a multi-step wizard). Open **Knowledge Bases** and click **Create Knowledge Base**.

<Steps>
  <Step title="Name and source">
    Enter a **Name** (auto-derived from the topic) and select the **input topic** and its **serialization** (auto-detected, JSON, or Avro). Optionally set a **text template** with `${field}` placeholders to control what text gets embedded.
  </Step>

  <Step title="Embedding and destination">
    Pick the **embedding model** connection and the **vector store** connection, then set the **index name** (auto-derived) — the index or collection the embeddings are written to — and an optional **namespace**.
  </Step>

  <Step title="Chunking and runtime (advanced)">
    Optionally adjust chunk size and overlap, parallelism, checkpoint interval, and the distance metric (Cosine, Dot product, or Euclidean).
  </Step>

  <Step title="Create">
    Click **Create Knowledge Base** to deploy, or **Save as draft** to finish later.
  </Step>
</Steps>

<Warning>
  **Knowledge base settings are immutable after deploy.** There is no edit. To change a setting, use **Clone/Recreate** to start a new knowledge base from the existing configuration, then delete the old one.
</Warning>

## Attach to an Agent

On the agent wizard's **Input** step, use the **Knowledge Bases** picker to attach up to 10 **running** knowledge bases. The agent gets one retrieval tool per attached knowledge base, and the model retrieves from it when the prompt calls for it. See [Build an Agent](/streaming-agents-build#step-2--input).

## Preview Retrieval

From a knowledge base detail page, use **Preview retrieval** to test what the agent would get back. Enter a query and a result count (**n**), and Streamkap returns that many ranked chunks with their similarity scores and metadata.

Preview retrieval requires the knowledge base to be **Running** and the `write:agents` permission (retrieved chunks are your data). It's currently supported for **Pinecone** vector stores (including the Streamkap default); knowledge bases on other vector stores still serve retrieval to agents at run time — only the in-app preview is unavailable.

## Lifecycle

Knowledge bases reuse the same streaming infrastructure as agents but have a reduced lifecycle: **Cancel**, **Stop**, and **Delete** only. Because settings are immutable, there is no edit or redeploy. Recreate to change configuration.

## Related

* [Connections](/streaming-agents-connections) — embedding and vector store credentials
* [Build an Agent](/streaming-agents-build) — attach a knowledge base to an agent
* [Pinecone](/pinecone) — Pinecone as a Streamkap destination