gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #244 from langflow-ai/add-notes-to-flows

Browse source 
docs: add notes to starter flows
This commit is contained in:
Sebastián Estévez 2025-10-24 14:24:38 -04:00 • committed by GitHub
commit a7a588c94e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 78 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
flows/ingestion_flow.json
View file

@ -4149,12 +4149,39 @@
},
"selected": false,
"type": "genericNode"
},
{
"data": {
"id": "note-DCu9M",
"node": {
"description": "## README\n\nThis flow transforms raw documents into searchable knowledge stored in an OpenSearch vector database.\nThis [knowledge](https://docs.openr.ag/knowledge) serves as context that your [agents](https://docs.openr.ag/agents) draw upon to answer questions and perform tasks.\n\n* Data sources: This flow ingests data from OAuth connectors or can load from your local machine. For more, see [Ingest Knowledge](https://docs.openr.ag/knowledge#ingest-knowledge).\n* Docling ingestion: The [**Docling Serve** component](https://docs.openr.ag/ingestion) processes input documents by connecting to your instance of Docling serve. For more, see [Docling Ingestion](https://docs.openr.ag/ingestion).\n* Processing: The flow adds metadata through three [**DataFrame Operations** components](https://docs.langflow.org/components-processing#dataframe-operations) that add `filename`, `file_size`, and `mimetype` columns.\nThe **Split Text** component then splits the processed text into uniform, easily searchable chunks.\n* Embedding generation:The [**Embedding Model** component](https://docs.langflow.org/components-embedding-models) generates vector embeddings with the model you selected at [Application onboarding](https://docs.openr.ag/install#application-onboarding), and the [**OpenSearch** component](https://docs.langflow.org/bundles-elastic#opensearch) stores the processed documents and their embeddings in the documents index.\n* Metadata and ownership: The **Secret Input** components provide user context that is stored as metadata in OpenSearch. These fields are populated from OAuth configuration values, and enable multi-tenant document isolation in OpenSearch, so each user's documents remain private and traceable.\n\nFor more information, see the [OpenRAG docs](https://docs.openr.ag/ingestion#knowledge-ingestion-flows).\n",
"display_name": "",
"documentation": "",
"template": {}
},
"type": "note"
},
"dragging": false,
"height": 439,
"id": "note-DCu9M",
"measured": {
"height": 439,
"width": 1000
},
"position": {
"x": -538.3997974029603,
"y": 1984.9915833571447
},
"resizing": true,
"selected": false,
"type": "noteNode",
"width": 1000
}
],
"viewport": {
"x": -418.8241631881149,
"y": -563.2891507884635,
"zoom": 0.6194861362488232
"x": 502.99612621025017,
"y": -497.01724621189965,
"zoom": 0.5248650535598084
}
},
"description": "Load your data for chat context with Retrieval Augmented Generation.",

66
flows/openrag_agent.json
View file

@ -191,6 +191,7 @@
}
},
"id": "xy-edge__MCP-7EY21{œdataTypeœ:œMCPœ,œidœ:œMCP-7EY21œ,œnameœ:œcomponent_as_toolœ,œoutput_typesœ:[œToolœ]}-Agent-crjWf{œfieldNameœ:œtoolsœ,œidœ:œAgent-crjWfœ,œinputTypesœ:[œToolœ],œtypeœ:œotherœ}",
"selected": false,
"source": "MCP-7EY21",
"sourceHandle": "{œdataTypeœ:œMCPœ,œidœ:œMCP-7EY21œ,œnameœ:œcomponent_as_toolœ,œoutput_typesœ:[œToolœ]}",
"target": "Agent-crjWf",
@ -448,8 +449,8 @@
"width": 192
},
"position": {
"x": 1264.0651279011304,
"y": 1192.017532447814
"x": 1338.2905337667046,
"y": 1206.5715335979264
},
"selected": false,
"type": "genericNode"
@ -755,7 +756,7 @@
],
"frozen": false,
"icon": "OpenSearch",
"last_updated": "2025-10-06T15:23:50.339Z",
"last_updated": "2025-10-09T17:03:19.845Z",
"legacy": false,
"lf_version": "1.6.0",
"metadata": {
@ -1375,8 +1376,8 @@
"width": 320
},
"position": {
"x": 1202.1762389080463,
"y": 395.8072555285192
"x": 1183.2560374129,
"y": 320.1264495479339
},
"selected": false,
"type": "genericNode"
@ -1409,7 +1410,7 @@
],
"frozen": false,
"icon": "binary",
"last_updated": "2025-10-06T15:23:50.341Z",
"last_updated": "2025-10-09T17:03:19.846Z",
"legacy": false,
"lf_version": "1.6.0",
"metadata": {
@ -1734,7 +1735,7 @@
],
"frozen": false,
"icon": "bot",
"last_updated": "2025-10-06T15:23:50.396Z",
"last_updated": "2025-10-09T17:03:19.888Z",
"legacy": false,
"lf_version": "1.6.0",
"metadata": {
@ -2241,8 +2242,8 @@
"width": 320
},
"position": {
"x": 745.3341059713564,
"y": 95.0152511387621
"x": 722.0477041311764,
"y": 119.75705309395346
},
"selected": false,
"type": "genericNode"
@ -2273,7 +2274,7 @@
],
"frozen": false,
"icon": "brain-circuit",
"last_updated": "2025-10-06T15:23:50.343Z",
"last_updated": "2025-10-09T17:03:19.855Z",
"legacy": false,
"lf_version": "1.6.0",
"metadata": {
@ -2571,8 +2572,8 @@
"width": 320
},
"position": {
"x": 1206.0291133693556,
"y": -185.39565741253472
"x": 1188.5643119892204,
"y": -237.60813653856357
},
"selected": false,
"type": "genericNode"
@ -2601,7 +2602,7 @@
"frozen": false,
"icon": "Mcp",
"key": "mcp_lf-starter_project",
"last_updated": "2025-10-06T15:23:56.578Z",
"last_updated": "2025-10-09T17:03:19.855Z",
"legacy": false,
"mcpServerName": "lf-starter_project",
"metadata": {
@ -2819,17 +2820,46 @@
"width": 320
},
"position": {
"x": 675.7137923419156,
"y": 878.6218422334763
"x": 733.9297969423658,
"y": 862.6124409683524
},
"selected": false,
"type": "genericNode"
},
{
"data": {
"id": "note-Wg9xF",
"node": {
"description": "## README\n\nThis flow generates answers for OpenRAG's chat, informed by the context stored in OpenSearch.\nIn this flow, the [**Langflow Agent** component](https://docs.langflow.org/agents) uses the connected [**Language Model** component](https://docs.langflow.org/components-models) to select the correct tool to complete requests.\n* If the Agent determines your request requires external knowledge, it will embed your query with the [**Embedding Model** component](https://docs.langflow.org/components-embedding-models) and query your [OpenSearch knowledge](https://docs.openr.ag/knowledge).\n\n* If the Agent determines your request requires a web search, it selects the [**MCP Tools** component](https://docs.langflow.org/mcp-client#mcp-tools-parameters) to fetch web content with the [OpenSearch URL ingestion flow](https://docs.openr.ag/ingestion#url-flow).\n\nUsing the retrieved data, the Agent generates a response with the connected [**Language Model** component](https://docs.langflow.org/components-models) and sends it to the [**Chat Output** component](https://docs.langflow.org/components-io).\n\nFor more information, see the [OpenRAG docs](https://docs.openr.ag/agents).",
"display_name": "",
"documentation": "",
"template": {
"backgroundColor": "amber"
}
},
"type": "note"
},
"dragging": false,
"height": 469,
"id": "note-Wg9xF",
"measured": {
"height": 469,
"width": 644
},
"position": {
"x": 19.942791510714386,
"y": 259.5061905471592
},
"resizing": false,
"selected": false,
"type": "noteNode",
"width": 644
}
],
"viewport": {
"x": -237.0727605845459,
"y": 154.6885920024542,
"zoom": 0.602433700773958
"x": 15.987785397208654,
"y": 201.25966590756093,
"zoom": 0.6870962766086257
}
},
"description": "OpenRAG OpenSearch Agent",