feat: add full document mode in knowledge base

docs/voice-agent/knowledge-base.mdx

@@ -6,7 +6,7 @@ description: "Upload documents that your voice agent can reference during live c
 The Knowledge Base lets you upload documents that your voice agents can reference during conversations. Instead of encoding all information into prompts, you can provide source documents and let the agent retrieve relevant content on the fly.
 
 <Warning>
-You must configure an embedding provider and API key in **AI Models Configuration → Embedding** before using the Knowledge Base. Document processing and retrieval depend on embeddings, so this feature will not work without a valid embedding configuration.
+An embedding API key (configured in **AI Models Configuration → Embedding**) is required for **Chunked Search** mode. **Full Document** mode does not require embeddings.
 </Warning>
 
 ![Embedding Configuration](../images/embedding-configurations.png)
@@ -14,9 +14,10 @@ You must configure an embedding provider and API key in **AI Models Configuratio
 ## How It Works
 
 1. You **upload** a document (PDF, DOCX, TXT, or JSON) to the Knowledge Base
-2. Dograh **processes** and chunks the document for efficient retrieval
-3. You **attach** the document to one or more workflow nodes
-4. During a call, the agent **searches** the document for relevant information based on the caller's questions and uses it to generate accurate responses
+2. You **choose a retrieval mode** — Full Document or Chunked Search
+3. Dograh **processes** the document based on the selected mode
+4. You **attach** the document to one or more workflow nodes
+5. During a call, the agent **retrieves** information from the document and uses it to generate accurate responses
 
 ## Supported File Types
 
@@ -33,7 +34,27 @@ Maximum file size: **5 MB**
 
 1. Go to **Knowledge Base Files** in the dashboard
 2. Click **Upload New** or drag and drop a file
-3. Wait for processing to complete — the document will be chunked and indexed automatically
+3. Choose a **retrieval mode** (see below)
+4. Click **Upload & Process** — the document will be processed according to the selected mode
+
+### Retrieval Modes
+
+When uploading a document, you choose how the agent retrieves information from it:
+
+<CardGroup cols={2}>
+  <Card title="Full Document" icon="file-lines">
+    The entire document text is provided to the agent whenever it queries the knowledge base. No chunking or embedding is performed.
+
+    **Best for:** menus, price lists, FAQs, short reference sheets, and any document where the agent needs access to all the information at once.
+
+    <Tip>Full Document mode does not require an embedding API key.</Tip>
+  </Card>
+  <Card title="Chunked Search" icon="magnifying-glass">
+    The document is split into smaller chunks and indexed with vector embeddings. When the agent queries the knowledge base, only the most relevant chunks are returned.
+
+    **Best for:** large documents like policies, manuals, or contracts where only a portion is relevant to any given question.
+  </Card>
+</CardGroup>
 
 ## Attaching Documents to Nodes
 
@@ -47,6 +68,8 @@ The agent will only search documents attached to the current node, so attach onl
 
 ## Best Practices
 
+- **Use Full Document for small reference files** — menus, price lists, and FAQs work best when the agent sees the entire document
+- **Use Chunked Search for large documents** — policies, manuals, and contracts are too large to fit in context, so chunked retrieval finds the relevant sections
 - **Keep documents focused** — a single topic per document produces better retrieval results than a large multi-topic file
 - **Use clear, structured content** — headings, lists, and short paragraphs help the chunking process
 - **Attach selectively** — only attach documents relevant to a specific node rather than attaching everything everywhere