Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Member enrichment llm lfx 1712 #2688

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Member enrichment llm lfx 1712 #2688

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
1a9d743
WIP
themarolt Nov 13, 2024
f4f3784
Improved prompt
themarolt Nov 13, 2024
e255498
wip
themarolt Nov 14, 2024
6304b88
wip
themarolt Nov 14, 2024
1aba439
fix
themarolt Nov 14, 2024
d47bed7
small changes
themarolt Nov 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Empty file added backend/src/database/migrations/U1731052735__llm-prompt-history.sql
View file
Open in desktop
Empty file.
Empty file added backend/src/database/migrations/U1731484783__drop-member-deprecated-columns.sql
View file
Open in desktop
Empty file.
17 changes: 17 additions & 0 deletions backend/src/database/migrations/V1731052735__llm-prompt-history.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
create table "llmPromptHistory" (
id bigserial primary key,
type varchar(255) not null,
model text not null,
"entityId" text null,
metadata jsonb null,
prompt text not null,
answer text not null,
"inputTokenCount" int not null,
"outputTokenCount" int not null,
"responseTimeSeconds" decimal not null,
"createdAt" timestamptz not null default now()
);
Comment on lines +1 to +13
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🛠️ Refactor suggestion

Consider additional constraints and optimizations

  1. The type column could be more efficient as an enum type
  2. The model column should have a CHECK constraint to validate allowed models
  3. The metadata column should have validation to ensure JSON structure
+create type llm_prompt_type as enum (
+    'organization_merge_suggestion',
+    'member_merge_suggestion'
+    -- add other types as needed
+);
+
 create table "llmPromptHistory" (
     id                    bigserial primary key,
-    type                  varchar(255) not null,
+    type                  llm_prompt_type not null,
     model                 text         not null,
+                         check (model in ('anthropic.claude-v2', 'anthropic.claude-v1')),
     "entityId"            text         null,
-    metadata              jsonb        null,
+    metadata              jsonb        null check (jsonb_typeof(metadata) = 'object'),
     prompt                text         not null,
     answer                text         not null,
     "inputTokenCount"     int          not null,
     "outputTokenCount"    int          not null,
     "responseTimeSeconds" decimal      not null,
     "createdAt"           timestamptz  not null default now()
 );

Committable suggestion skipped: line range outside the PR's diff.


create index "ix_llmPromptHistory_type_entityId" on "llmPromptHistory"("type", "entityId");
create index "ix_llmPromptHistory_entityId" on "llmPromptHistory"("entityId");
create index "ix_llmPromptHistory_type" on "llmPromptHistory"("type");
5 changes: 5 additions & 0 deletions backend/src/database/migrations/V1731484783__drop-member-deprecated-columns.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
alter table members
drop column "oldEmails";

alter table members
drop column "oldWeakIdentities";
Loading
Loading