Skip to content

Conversation

@prinskumar-tigergraph
Copy link
Collaborator

@prinskumar-tigergraph prinskumar-tigergraph commented Dec 8, 2025

User description

Updated the new code with new branch


PR Type

Enhancement, Other


Description

  • Streamed JSONL ingestion with temp sessions

  • PDF parsing via pymupdf4llm, safe cleanup

  • Session-aware deletion endpoints for uploads

  • Fixed ingest config attribute handling


Diagram Walkthrough

flowchart LR
  upload["Upload/server local files"]
  extractor["TextExtractor async processing"]
  jsonl["Temp session JSONL (processed_documents.jsonl)"]
  ingest["Ingest step (supportai.py)"]
  tg["TigerGraph loading job"]
  cleanup["Cleanup temp session folder"]
  ui["UI delete endpoints (session-aware)"]

  upload -- "process_folder(graphname, temp_folder)" --> extractor
  extractor -- "append docs line-by-line" --> jsonl
  ingest -- "read JSONL content" --> jsonl
  ingest -- "runLoadingJobWithData(JSONL)" --> tg
  tg -- "on success" --> cleanup
  ui -- "delete file/docs from JSONL" --> jsonl
Loading

File Walkthrough

Relevant files
Enhancement
5 files
text_extractors.py
Streamed JSONL pipeline and PDF extraction overhaul           
+335/-138
supportai.py
Server ingest uses temp JSONL sessions                                     
+56/-40 
ui.py
Add session-aware deletion and temp cleanup endpoints       
+97/-3   
image_data_extractor.py
Simplify LLM image description to file-based                         
+31/-134
Setup.tsx
UI setup adjustments for local sessions                                   
+662/-629
Dependencies
1 files
requirements.txt
Add pymupdf4llm and bump PyMuPDF                                                 
+2/-1     
Documentation
1 files
pymupdf4llm-AGPL-3.0.txt
Include AGPL license for pymupdf4llm                                         
+661/-0 
Configuration changes
5 files
server_config.json
Remove legacy server configuration file                                   
+0/-1     
nginx.conf
Remove legacy Nginx configuration                                               
+0/-1     
configs
Remove deprecated app configuration directory                       
+0/-1     
configs
Remove ECC configs folder                                                               
+0/-1     
common
Remove ECC common module                                                                 
+0/-1     
Miscellaneous
1 files
common
Remove deprecated common app module                                           
+0/-1     

@prinskumar-tigergraph prinskumar-tigergraph deleted the 2011-Local-files-supports branch December 8, 2025 15:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants