Skip to content

Latest commit

 

History

History
45 lines (36 loc) · 1.62 KB

jira_config.md

File metadata and controls

45 lines (36 loc) · 1.62 KB
Raw

JIRA connector

Create a yaml file under the config folder with the following parameters, let's assume jira_sandbox.yaml; contact your provider for some of these values:

jira:
  email: !!str 'string'
  api_token: !!str 'some_token' # get it from JIRA
  server_url: !!str 'somedomain.atlassian.net' # check with your provider
  project: !!str 'some project'
  query: !!str 'filter=id' # Create a filter for the issues and check the associated ID
  namespace: !!str 'namespace name' # Must match the associated RAG assistant, check the index section
saia:
  base_url: !!str 'string' # GeneXus Enterprise AI Base URL
  api_token: !!str 'string'
  profile: !!str 'string' # Must match the RAG assistant ID
  max_parallel_executions: !!int 5
  upload_operation_log: !!bool False|True (default) # Check operations LOG for detail if enabled
# Deprecated
vectorstore:
  api_key: !!str 'check with the provider'
  index_name: !!str 'check with the provider'
embeddings:
  openapi_key: !!str 'check with the provider'
  chunk_size: !!int integer # DefaultVectorStore.CHUNK_SIZE by default
  chunk_overlap: !!int integer # DefaultVectorStore.CHUNK_OVERLAP by default

Execution

Example execution:

saia-cli ingest -c ./config/jira_sandbox.yaml --type jira

Expected output is similar to:

INFO:root:processed 10 from 10
INFO:root:Successfully jira ingestion 'no timestamp' config: ./config/jira_sandbox.yaml

Tip: under the debug folder, the {provider}_YYYYMMDDHHMMSS.json is the result of the issues ingestion and can be uploaded to any RAG assistant if you use the .custom extension when uploading the file.