Skip to content

[draft] Vector search #388

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

Open
yutin1987 wants to merge 6 commits into
base: master
Choose a base branch
from
Open

[draft] Vector search #388

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0c4ed16
chore: ignore CLAUDE.md and refresh lockfile
yutin1987 May 4, 2026
85f5d2a
feat: add embedding util with airesponses cache
yutin1987 May 5, 2026
de95b57
feat: embed articles and replies on create
yutin1987 May 5, 2026
70773e5
feat: add hybrid BM25+vector search to lists
yutin1987 May 5, 2026
0578b5b
feat: backfill vertex embeddings for old docs
yutin1987 May 5, 2026
d92bee0
fix: embedding update race and test mocks
yutin1987 May 5, 2026
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
5 changes: 4 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ jspm_packages
.node_repl_history

# docker-compose test data
esdata
esdata*

# local config
config/local-*
Expand All @@ -48,3 +48,6 @@ config/local-*

# Prevent google-github-actions/auth credentials being committed to git by accident
gha-creds-*.json

# Claude Code local guidance
CLAUDE.md
9 changes: 5 additions & 4 deletions docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
version: "2"
services:
db-v9:
image: elasticsearch:9.2.2
image: elasticsearch:9.3.2
ports:
- "62222:9200"
volumes:
Expand All @@ -13,11 +13,12 @@ services:
- "ES_JAVA_OPTS=-Xms512m -Xmx512m" # Prevent elasticsearch eating up too much memory
# - "reindex.remote.whitelist=host.docker.internal:62222,ip:62222" # Allow reindex from old ES
- "discovery.type=single-node" # Single node mode for development
- "xpack.security.enabled=false" # ES 8+ enables HTTPS by default; disable for plaintext local dev
extra_hosts:
- "host.docker.internal:host-gateway" # Allow container to access host machine

kibana:
image: kibana:9.2.2
image: kibana:9.3.2
depends_on:
- db-v9
environment:
Expand All @@ -43,12 +44,12 @@ services:
ELASTICSEARCH_URL: "http://db-v9:9200"
URL_RESOLVER_URL: "url-resolver:4000"
ports:
- "5000:5000"
- "5001:5001"
- "5500:5500"

site:
image: cofacts/rumors-site:latest-en
ports:
- "3000:3000"
environment:
PUBLIC_API_URL: http://localhost:5000
PUBLIC_API_URL: http://localhost:5001
98 changes: 66 additions & 32 deletions package-lock.json
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
"@elastic/elasticsearch": "^9.0.0",
"@google-cloud/bigquery": "^6.2.0",
"@google-cloud/vision": "^3.1.4",
"@google/genai": "^1.6.0",
"@google/genai": "^2.0.1",
"@grpc/grpc-js": "^1.6.7",
"@grpc/proto-loader": "^0.5.0",
"@sinclair/typebox": "^0.33.22",
Expand Down
14 changes: 14 additions & 0 deletions src/graphql/models/AIResponse.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,9 @@ const AIResponse = new GraphQLInterfaceType({

case 'TRANSCRIPT':
return AITranscript;

case 'EMBEDDING':
return AIEmbedding;
}
},
});
Expand Down Expand Up @@ -93,6 +96,17 @@ export const AITranscript = new GraphQLObjectType({
},
});

export const AIEmbedding = new GraphQLObjectType({
name: 'AIEmbedding',
description:
'AI generated embedding vectors for the specified docId, used as cache for hybrid search. ' +
'The vector data itself is not exposed via GraphQL — only the cache metadata is queryable.',
interfaces: [Node, AIResponse],
fields: {
...commonAiResponseFields,
},
Comment on lines +105 to +107

@gemini-code-assist gemini-code-assist Bot May 5, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

medium

The AIEmbedding type is missing the text field. Since createEmbedding stores error messages in the text field when the status is ERROR, this field should be added to the GraphQL model to allow clients to retrieve error details.

  fields: {
    ...commonAiResponseFields,
    text: { type: GraphQLString },
  },

});

export const AIResponseConnection = createConnectionType(
'AIResponseConnection',
AIResponse
Expand Down
Loading
Loading