updated LinktaFlowSchema with additional fields added to nodes and edges for updating linktaflow doc purpose after user edit the initial tree on frontend
added JSON.parse to parse LLM returned response
added UserInput.create() and LinkraFlow.create()to store user input prompt into DB and use the returned userInputId for storing linktaflow doc
[x] 🐛 Bug fix (non-breaking change which fixes an issue)
[x] ✨ New feature (non-breaking change which adds functionality)
[ ] 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] 📝 Documentation update
[ ] Other 🗒️ __
How Has This Been Tested?
Manually tested with dummy userID;
Calling GeminiAPI and successfully generating the desired response and storing it into the DB. But still need Chen to test out if the updated schema is working properly
[ ] Step 1: __
[ ] Step 2: __
[ ] Step 3: __
Checklist:
[x] I have performed a self-review of my own code.
[x] I have commented on my code, particularly in hard-to-understand areas.
[x] My changes generate no new warnings.
[ ] Any dependent changes have been merged and published in downstream modules.
[x] I have ensured that my pull request title is descriptive.
Additional Information:
P.S.
1 out of 10 times, I encountered a minor format issue, which is worth further research on prompting or function calling feature to ensure the returned response format is always as expected
regardless, prompting still is a work in progress
Description
nodes
andedges
for updating linktaflow doc purpose after user edit the initial tree on frontendUserInput.create()
andLinkraFlow.create()
to store user input prompt into DB and use the returned userInputId for storinglinktaflow
docHow Has This Been Tested?
Manually tested with dummy userID; Calling GeminiAPI and successfully generating the desired response and storing it into the DB. But still need Chen to test out if the updated schema is working properly
Checklist:
Additional Information:
P.S.
1 out of 10 times, I encountered a minor format issue, which is worth further research on prompting or function calling feature to ensure the returned response format is always as expected regardless, prompting still is a work in progress