receive schedule events and default data loader and recursive character text splitter
Configured with Agent, Document Default Data Loader, Embeddings Open Ai, Information Extractor, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Trigger
- AI & models
- Files / media
- Transform
- Data store
- Integration
- Routing
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| Schedule Trigger | Trigger | Schedule Trigger | See node parameters |
| Embeddings OpenAI | AI & models | Embeddings Open Ai | See node parameters |
| Default Data Loader | Files / media | Document Default Data Loader | See node parameters |
| Recursive Character Text Splitter | Transform | Text Splitter Recursive Character Text Splitter | See node parameters |
| Issues Similarity Database | Data store | Vector Store Supabase | See node parameters |
| Supabase Vector Store | Data store | Vector Store Supabase | See node parameters |
| Embeddings OpenAI1 | AI & models | Embeddings Open Ai | See node parameters |
| OpenAI Chat Model | AI & models | OpenAI Chat Model | See node parameters |
| Find Similar Issues + Assignees | AI & models | Agent | See node parameters |
| Check User Workflow | Integration | Jira | getAll |
| For Each User | Routing | Loop Over Items | See node parameters |
| Assign User to Ticket | Integration | Jira | update |
| Schedule Trigger1 | Trigger | Schedule Trigger | See node parameters |
| Remove Duplicates | Transform | Remove Duplicates | removeItemsSeenInPreviousExecutions |
| Collect Fields | Transform | Edit Fields | See node parameters |
| Get Unassigned Tickets more than 5 days | Integration | Jira | getAll |
| For Each Issue | Routing | Loop Over Items | See node parameters |
| Issue Ref | Routing | No Op | See node parameters |
| Add Comment to Issue | Integration | Jira | issueComment |
| Last 50 Resolved | Integration | Jira | getAll |
| OpenAI Chat Model1 | AI & models | OpenAI Chat Model | See node parameters |
| Issues to Items | Transform | Split Out | See node parameters |
| To Structured Output | AI & models | Information Extractor | See node parameters |
| Count Assigned Open Issues per User | Transform | Summarize | See node parameters |
| Tally In-Progress Issues per User | Transform | Edit Fields | See node parameters |
| Sort By Most Capacity | Transform | Sort | See node parameters |
| If has Items? | Routing | If | See node parameters |
| Skip | Routing | No Op | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
jiraSoftwareCloudApiopenAiApisupabaseApi
Workflow notes
1. Get Resolved Issues
1. Get Resolved Issues
Learn more about the JIRA node
To build our database of successfully resolved issues, we can pull them directly from JIRA with a JQL query. The remove duplicates node ensures we only add an issues into the database once.
2. Create Search Index In Vector Database
2. Create Search Index In Vector Database
Learn more about the Supabase Vector Store
Supabase is a third party database provider which serves traditional PostgreSQL but also supports Vector databases via the Pg-Vector extension. You will require some initial setup but easily done through Supabase's Langchain quickstart method
3. Watch for Stale Unassigned Issues
3. Watch for Stale Unassigned Issues
Read more about the Scheduled Trigger
Here, we're using a scheduled trigger to watch for stale issues where stale means unassigned issues for more than 5 days. As to not let these fall through the cracks, let's see if we can auto-assign to a team member based on relevance.
4. Find Similar Issues which have been Resolved
4. Find Similar Issues which have been Resolved
Our first step is to find similar but resolved issues. The logic is that if we find these issues, the team member who resolved them will likely be the best person in terms of context and experience to address the current stale issue. Here, we tap back into our resolved issues vector store database for this purpose.
5. Work out which Knowledgeable Team Member has most Capacity
5. Work out which Knowledgeable Team Member has most Capacity
Learn more about the Summarize node
If we've found similar resolved issues, we can then identify the last assignee of the issue as a possible candidate to assign the stale issue to. But before we do, we can do a quick check to see how many open issues the team member is currently assigned. We'll pick the team member with the least amount or in another way, the most capacity.
6. Auto-assign Stale Issue to Team Member
6. Auto-assign Stale Issue to Team Member
Learn more about the JIRA node
Finally, we'll auto-assign the team member to the stale issue and leave a comment. This continues until all stale issues that can be assigned, are assigned.
What is no similar issues are found?
What is no similar issues are found?
This is beyond the scope of this template so we'll skip the issue but in this situation, you may want to escalate to the project manager instead.
Try it out
Try it out
This n8n template builds a simple automation to ensure no JIRA issues go unassigned for more than a week to prevent them falling through the cracks. It uses AI to perform searching tasks against a Supabase Vector Store.
This can be one way to help reduce the amount of manual work in managing the issue backlog for busy teams with little effort.
How it works
- This template contains 2 separate flows which run continuously via schedule triggers.
- The first populates our Supabase vector store with resolved issues within the last day. This helps keep our vector store up-to-date and relevant for the purpose of finding similar issues.
- It does this by pulling the latest resolved issues from JIRA and populating the Supabase vectorstore with carefully chosen metadata. This will come in handy later.
- The second flow watches for stale, unassigned issues for the purpose of aut-assigning to a relevant team member.
- It does this by comparing the stale issue against our vector store of resolved issues with the goal of identifying which team member would have best context regarding the issue.
- In a busy team, this may net a few team members as possible candidates to assign. Therefore, we can introduce additional logic to count each team member's assigned, in-progress issues. This is intended to not overload our busiest members.
- The team member with the least assigned issues is pressumed to have the most capacity and therefore is assigned. A comennt is left in the issue to notify the team member that they've been auto-assigned due to age of issue.
How to use
- Modify the project and interval parameters to match those of your use-case and team members.
- Add additional criteria before assigning to a team member eg. department, as required.
Need Help?
Join the Discord or ask in the Forum!
Happy Hacking!
receive schedule events and default data loader and recursive character text splitter
receive schedule events and default data loader and recursive character text splitter
Purpose and structure
This folder contains the receive schedule events and default data loader and recursive character text splitter workflow. Its executable nodes use agent, documentDefaultDataLoader, embeddingsOpenAi, if, informationExtractor, jira, lmChatOpenAi, noOp, removeDuplicates, scheduleTrigger, set, sort, splitInBatches, splitOut, summarize, textSplitterRecursiveCharacterTextSplitter, vectorStoreSupabase. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
Schedule Trigger, Schedule Trigger1
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Splitout/0819_Splitout_Schedule_Create_Scheduled.json MIT; preserve source notices.