Skip to content

Commit 4ec185c

Browse files
tisniktisnik
committed
Updated configuration doc
1 parent bd62934 commit 4ec185c

4 files changed

Lines changed: 674 additions & 591 deletions

File tree

‎docs/config.html‎

Lines changed: 97 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -376,6 +376,11 @@ <h2 id="azureentraidconfiguration">AzureEntraIdConfiguration</h2>
376376
<h2 id="byokrag">ByokRag</h2>
377377
<p>BYOK (Bring Your Own Knowledge) RAG configuration.</p>
378378
<table>
379+
<colgroup>
380+
<col style="width: 26%"/>
381+
<col style="width: 23%"/>
382+
<col style="width: 50%"/>
383+
</colgroup>
379384
<thead>
380385
<tr class="header">
381386
<th>Field</th>
@@ -414,6 +419,13 @@ <h2 id="byokrag">ByokRag</h2>
414419
<td>string</td>
415420
<td>Path to RAG database.</td>
416421
</tr>
422+
<tr class="odd">
423+
<td>score_multiplier</td>
424+
<td>number</td>
425+
<td>Multiplier applied to relevance scores from this vector store. Used
426+
to weight results when querying multiple knowledge sources. Values &gt;
427+
1 boost this store&#x2019;s results; values &lt; 1 reduce them.</td>
428+
</tr>
417429
</tbody>
418430
</table>
419431
<h2 id="corsconfiguration">CORSConfiguration</h2>
@@ -603,9 +615,15 @@ <h2 id="configuration">Configuration</h2>
603615
&#x2018;production&#x2019;). Used in telemetry events.</td>
604616
</tr>
605617
<tr class="even">
606-
<td>solr</td>
618+
<td>rag</td>
607619
<td/>
608-
<td>Configuration for Solr vector search operations.</td>
620+
<td>Configuration for all RAG strategies (inline and tool-based).</td>
621+
</tr>
622+
<tr class="odd">
623+
<td>okp</td>
624+
<td/>
625+
<td>OKP provider settings. Only used when &#x2018;okp&#x2019; is listed in rag.inline
626+
or rag.tool.</td>
609627
</tr>
610628
</tbody>
611629
</table>
@@ -1089,6 +1107,41 @@ <h2 id="modelcontextprotocolserver">ModelContextProtocolServer</h2>
10891107
</tr>
10901108
</tbody>
10911109
</table>
1110+
<h2 id="okpconfiguration">OkpConfiguration</h2>
1111+
<p>OKP (Offline Knowledge Portal) provider configuration.</p>
1112+
<p>Controls provider-specific behaviour for the OKP vector store. Only
1113+
relevant when <code>"okp"</code> is listed in <code>rag.inline</code> or
1114+
<code>rag.tool</code>.</p>
1115+
<table>
1116+
<colgroup>
1117+
<col style="width: 26%"/>
1118+
<col style="width: 23%"/>
1119+
<col style="width: 50%"/>
1120+
</colgroup>
1121+
<thead>
1122+
<tr class="header">
1123+
<th>Field</th>
1124+
<th>Type</th>
1125+
<th>Description</th>
1126+
</tr>
1127+
</thead>
1128+
<tbody>
1129+
<tr class="odd">
1130+
<td>offline</td>
1131+
<td>boolean</td>
1132+
<td>When True, use parent_id for OKP chunk source URLs. When False, use
1133+
reference_url for chunk source URLs.</td>
1134+
</tr>
1135+
<tr class="even">
1136+
<td>chunk_filter_query</td>
1137+
<td>string</td>
1138+
<td>OKP filter query applied to every OKP search request. Defaults to
1139+
&#x2018;is_chunk:true&#x2019; to restrict results to chunk documents. To add extra
1140+
constraints, extend the expression using boolean syntax,
1141+
e.g.&#xA0;&#x2018;is_chunk:true AND product:<em>openshift</em>&#x2019;.</td>
1142+
</tr>
1143+
</tbody>
1144+
</table>
10921145
<h2 id="postgresqldatabaseconfiguration">PostgreSQLDatabaseConfiguration</h2>
10931146
<p>PostgreSQL database configuration.</p>
10941147
<p>PostgreSQL database is used by Lightspeed Core Stack service for
@@ -1337,6 +1390,48 @@ <h2 id="rhidentityconfiguration">RHIdentityConfiguration</h2>
13371390
</tr>
13381391
</tbody>
13391392
</table>
1393+
<h2 id="ragconfiguration">RagConfiguration</h2>
1394+
<p>RAG strategy configuration.</p>
1395+
<p>Controls which RAG sources are used for inline and tool-based
1396+
retrieval.</p>
1397+
<p>Each strategy lists RAG IDs to include. The special ID
1398+
<code>"okp"</code> defined in constants, activates the OKP provider; all
1399+
other IDs refer to entries in <code>byok_rag</code>.</p>
1400+
<p>Backward compatibility: - <code>inline</code> defaults to
1401+
<code>[]</code> (no inline RAG). - <code>tool</code> defaults to
1402+
<code>None</code> which means all registered vector stores are used
1403+
(identical to the previous <code>tool.byok.enabled = True</code>
1404+
default).</p>
1405+
<table>
1406+
<colgroup>
1407+
<col style="width: 26%"/>
1408+
<col style="width: 23%"/>
1409+
<col style="width: 50%"/>
1410+
</colgroup>
1411+
<thead>
1412+
<tr class="header">
1413+
<th>Field</th>
1414+
<th>Type</th>
1415+
<th>Description</th>
1416+
</tr>
1417+
</thead>
1418+
<tbody>
1419+
<tr class="odd">
1420+
<td>inline</td>
1421+
<td>array</td>
1422+
<td>RAG IDs whose sources are injected as context before the LLM call.
1423+
Use &#x2018;okp&#x2019; to enable OKP inline RAG. Empty by default (no inline
1424+
RAG).</td>
1425+
</tr>
1426+
<tr class="even">
1427+
<td>tool</td>
1428+
<td>array</td>
1429+
<td>RAG IDs made available to the LLM as a file_search tool. Use &#x2018;okp&#x2019;
1430+
to include the OKP vector store. When omitted, all registered BYOK
1431+
vector stores are used (backward compatibility).</td>
1432+
</tr>
1433+
</tbody>
1434+
</table>
13401435
<h2 id="sqlitedatabaseconfiguration">SQLiteDatabaseConfiguration</h2>
13411436
<p>SQLite database configuration.</p>
13421437
<table>
@@ -1429,39 +1524,6 @@ <h2 id="serviceconfiguration">ServiceConfiguration</h2>
14291524
</tr>
14301525
</tbody>
14311526
</table>
1432-
<h2 id="solrconfiguration">SolrConfiguration</h2>
1433-
<p>Solr configuration for vector search queries.</p>
1434-
<p>Controls whether to use offline or online mode when building document
1435-
URLs from vector search results, and enables/disables Solr vector IO
1436-
functionality.</p>
1437-
<table>
1438-
<colgroup>
1439-
<col style="width: 26%"/>
1440-
<col style="width: 23%"/>
1441-
<col style="width: 50%"/>
1442-
</colgroup>
1443-
<thead>
1444-
<tr class="header">
1445-
<th>Field</th>
1446-
<th>Type</th>
1447-
<th>Description</th>
1448-
</tr>
1449-
</thead>
1450-
<tbody>
1451-
<tr class="odd">
1452-
<td>enabled</td>
1453-
<td>boolean</td>
1454-
<td>When True, enables Solr vector IO functionality for vector search
1455-
queries. When False, disables Solr vector search processing.</td>
1456-
</tr>
1457-
<tr class="even">
1458-
<td>offline</td>
1459-
<td>boolean</td>
1460-
<td>When True, use parent_id for chunk source URLs. When False, use
1461-
reference_url for chunk source URLs.</td>
1462-
</tr>
1463-
</tbody>
1464-
</table>
14651527
<h2 id="splunkconfiguration">SplunkConfiguration</h2>
14661528
<p>Splunk HEC (HTTP Event Collector) configuration.</p>
14671529
<p>Splunk HEC allows sending events directly to Splunk over HTTP/HTTPS.

‎docs/config.md‎

Lines changed: 41 additions & 59 deletions
Original file line numberDiff line numberDiff line change
@@ -130,12 +130,12 @@ byok_rag:
130130
| Field | Type | Description |
131131
|-------|------|-------------|
132132
| rag_id | string | Unique RAG ID |
133-
| rag_type | string | Type of RAG database (e.g. `inline::faiss`). |
133+
| rag_type | string | Type of RAG database. |
134134
| embedding_model | string | Embedding model identification |
135135
| embedding_dimension | integer | Dimensionality of embedding vectors. |
136136
| vector_db_id | string | Vector database identification. |
137137
| db_path | string | Path to RAG database. |
138-
| score_multiplier | number | Multiplier applied to relevance scores from this vector store when querying multiple sources. Values > 1 boost results; values < 1 reduce them. Default: 1.0. |
138+
| score_multiplier | number | Multiplier applied to relevance scores from this vector store. Used to weight results when querying multiple knowledge sources. Values > 1 boost this store's results; values < 1 reduce them. |
139139
140140
141141
## CORSConfiguration
@@ -187,7 +187,8 @@ Global service configuration.
187187
| azure_entra_id | | |
188188
| splunk | | Splunk HEC configuration for sending telemetry events. |
189189
| deployment_environment | string | Deployment environment name (e.g., 'development', 'staging', 'production'). Used in telemetry events. |
190-
| rag | | RAG strategy configuration (OKP and BYOK). Controls pre-query (Inline RAG) and tool-based (Tool RAG) retrieval. |
190+
| rag | | Configuration for all RAG strategies (inline and tool-based). |
191+
| okp | | OKP provider settings. Only used when 'okp' is listed in rag.inline or rag.tool. |
191192
192193
193194
## ConversationHistoryConfiguration
@@ -395,6 +396,21 @@ Useful resources:
395396
| timeout | integer | Timeout in seconds for requests to the MCP server. If not specified, the default timeout from Llama Stack will be used. Note: This field is reserved for future use when Llama Stack adds timeout support. |
396397
397398
399+
## OkpConfiguration
400+
401+
402+
OKP (Offline Knowledge Portal) provider configuration.
403+
404+
Controls provider-specific behaviour for the OKP vector store.
405+
Only relevant when ``"okp"`` is listed in ``rag.inline`` or ``rag.tool``.
406+
407+
408+
| Field | Type | Description |
409+
|-------|------|-------------|
410+
| offline | boolean | When True, use parent_id for OKP chunk source URLs. When False, use reference_url for chunk source URLs. |
411+
| chunk_filter_query | string | OKP filter query applied to every OKP search request. Defaults to 'is_chunk:true' to restrict results to chunk documents. To add extra constraints, extend the expression using boolean syntax, e.g. 'is_chunk:true AND product:*openshift*'. |
412+
413+
398414
## PostgreSQLDatabaseConfiguration
399415
400416
@@ -501,6 +517,28 @@ Red Hat Identity authentication configuration.
501517
| required_entitlements | array | List of all required entitlements. |
502518

503519

520+
## RagConfiguration
521+
522+
523+
RAG strategy configuration.
524+
525+
Controls which RAG sources are used for inline and tool-based retrieval.
526+
527+
Each strategy lists RAG IDs to include. The special ID ``"okp"`` defined in constants,
528+
activates the OKP provider; all other IDs refer to entries in ``byok_rag``.
529+
530+
Backward compatibility:
531+
- ``inline`` defaults to ``[]`` (no inline RAG).
532+
- ``tool`` defaults to ``None`` which means all registered vector stores
533+
are used (identical to the previous ``tool.byok.enabled = True`` default).
534+
535+
536+
| Field | Type | Description |
537+
|-------|------|-------------|
538+
| inline | array | RAG IDs whose sources are injected as context before the LLM call. Use 'okp' to enable OKP inline RAG. Empty by default (no inline RAG). |
539+
| tool | array | RAG IDs made available to the LLM as a file_search tool. Use 'okp' to include the OKP vector store. When omitted, all registered BYOK vector stores are used (backward compatibility). |
540+
541+
504542
## SQLiteDatabaseConfiguration
505543

506544

@@ -537,62 +575,6 @@ the service can handle requests concurrently.
537575
| cors | | Cross-Origin Resource Sharing configuration for cross-domain requests |
538576

539577

540-
## RagConfiguration
541-
542-
543-
Top-level RAG strategy configuration. Controls two complementary retrieval modes:
544-
545-
- **Inline RAG**: context is fetched from the listed sources and injected before the
546-
LLM request.
547-
- **Tool RAG**: the LLM can call the `file_search` tool during generation to retrieve
548-
context on demand from the listed vector stores. Supports both BYOK and OKP.
549-
550-
Each strategy is configured as a list of RAG IDs referencing entries in `byok_rag`.
551-
The special ID `okp` activates the OKP provider (no `byok_rag` entry needed).
552-
553-
**Backward compatibility**: omitting `tool` uses all registered BYOK vector stores
554-
(equivalent to the old `tool.byok.enabled = True`). Omitting `inline` means no
555-
context is injected before the LLM request.
556-
557-
Example:
558-
559-
```yaml
560-
rag:
561-
inline:
562-
- my-docs # inject context from my-docs before the LLM request
563-
tool:
564-
- okp # LLM can search OKP as a tool
565-
- my-docs # LLM can also search my-docs as a tool
566-
567-
okp:
568-
offline: true # use parent_id for OKP URL construction
569-
```
570-
571-
572-
| Field | Type | Description |
573-
|-------|------|-------------|
574-
| inline | list[string] | RAG IDs whose content is injected before the LLM request. Use `okp` for OKP. Empty by default (no inline RAG). |
575-
| tool | list[string] or null | RAG IDs exposed as a `file_search` tool the LLM can invoke. Use `okp` to include OKP. When omitted, all registered BYOK vector stores are used (backward compatibility). |
576-
577-
578-
## OkpConfiguration
579-
580-
OKP (Offline Knowledge Portal) provider settings. Only used when `okp` is listed in `rag.inline` or `rag.tool`.
581-
582-
Example:
583-
584-
```yaml
585-
okp:
586-
offline: true # use parent_id for OKP URL construction
587-
chunk_filter_query: "is_chunk:true"
588-
```
589-
590-
| Field | Type | Description |
591-
|-------|------|-------------|
592-
| offline | boolean | When `true` (default), use `parent_id` for OKP chunk source URLs. When `false`, use `reference_url`. |
593-
| chunk_filter_query | string | OKP filter query (`fq`) applied to every OKP search request. Defaults to `"is_chunk:true"`. Extend with `AND` for extra constraints. |
594-
595-
596578
## SplunkConfiguration
597579

598580

0 commit comments

Comments
 (0)