> ## Documentation Index
> Fetch the complete documentation index at: https://docs.alquimia.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Knowledge Base
> Connect your agent to documents so it can answer questions using your content.
The Knowledge Base gives your agent access to a collection of documents. When a user asks a question, the agent retrieves the most relevant passages and uses them to construct an accurate, grounded answer. This technique is called **RAG** — Retrieval-Augmented Generation.
## Prerequisites
None — embeddings are handled automatically by the Alquimia runtime. Just open the Knowledge Base step and start uploading.
## Uploading documents
Drag and drop files into the upload area or click to browse. Uploaded documents are:
1. Processed and chunked into passages
2. Embedded by the runtime engine
3. Stored in the vector database (Qdrant)
## Retrieval parameters
These parameters control how the agent searches your documents when answering a question.
### Search type
| Type | Description | Best for |
| ------------ | -------------------------------------------------------------- | --------------------------------------------- |
| `similarity` | Pure semantic similarity — finds the most relevant chunks | Specific, focused questions |
| `mmr` | Maximal Marginal Relevance — balances relevance with diversity | Broad questions, avoiding repetitive passages |
### Parameters
| Parameter | Default | Description |
| ------------------- | ------- | ------------------------------------------------------------------- |
| **K** | 4 | Number of document chunks retrieved per query |
| **Score Threshold** | none | Minimum similarity score (0.0–1.0). Chunks below this are excluded. |
| **Fetch K** | — | MMR only: candidates to evaluate before selecting the final K |
| **Lambda Mult** | — | MMR only: diversity weight (0 = max diversity, 1 = max relevance) |
Start with `similarity`, K=4, and no threshold. Run a few test queries in the Test Drawer. If answers are repetitive, switch to `mmr`. If answers include irrelevant content, add a score threshold (try 0.7 first).
## How retrieval works at runtime
When the agent receives a message:
1. The query is embedded by the runtime using the same model that indexed the documents
2. The vector database finds the K most similar document chunks
3. Those chunks are injected into the agent's prompt as context
4. The LLM uses this context to generate a grounded answer
The agent cites information from your documents rather than relying solely on what the LLM learned during training.
## Next steps
Add conversation memory alongside document retrieval.
Choose the LLM that generates grounded answers from retrieved context.