-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
139 additions
and
20 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,78 @@ | ||
package analyzer_test | ||
|
||
import ( | ||
"database/sql" | ||
"github.com/initialcapacity/ai-starter/internal/analyzer" | ||
"github.com/initialcapacity/ai-starter/pkg/dbsupport" | ||
"github.com/initialcapacity/ai-starter/pkg/testsupport" | ||
"github.com/pgvector/pgvector-go" | ||
"github.com/stretchr/testify/assert" | ||
"testing" | ||
) | ||
|
||
func TestEmbeddingsGateway_UnprocessedIds(t *testing.T) { | ||
testDb := testsupport.NewTestDb(t) | ||
defer testDb.Close() | ||
testDb.ClearTables() | ||
|
||
gateway := analyzer.NewEmbeddingsGateway(testDb.DB) | ||
|
||
testDb.Execute("insert into data (id, source, content) values ('aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16', 'https://example.com', 'some content')") | ||
testDb.Execute("insert into chunks (id, data_id, content) values ('bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16', 'aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16','a chunk')") | ||
testDb.Execute("insert into chunks (id, data_id, content) values ('cccccccc-2f3f-4bc9-8dba-ba397156cc16', 'aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16','a chunk')") | ||
vector := createVector(0) | ||
testDb.Execute("insert into embeddings (chunk_id, embedding) values ('bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16', $1)", pgvector.NewVector(vector)) | ||
|
||
ids, err := gateway.UnprocessedIds() | ||
assert.NoError(t, err) | ||
|
||
assert.Equal(t, []string{"cccccccc-2f3f-4bc9-8dba-ba397156cc16"}, ids) | ||
} | ||
|
||
func TestEmbeddingsGateway_Save(t *testing.T) { | ||
testDb := testsupport.NewTestDb(t) | ||
defer testDb.Close() | ||
testDb.ClearTables() | ||
|
||
gateway := analyzer.NewEmbeddingsGateway(testDb.DB) | ||
|
||
testDb.Execute("insert into data (id, source, content) values ('aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16', 'https://example.com', 'some content')") | ||
testDb.Execute("insert into chunks (id, data_id, content) values ('bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16', 'aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16','a chunk')") | ||
|
||
err := gateway.Save("bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16", createVector(0)) | ||
assert.NoError(t, err) | ||
|
||
chunkId, err := dbsupport.QueryOne(testDb.DB, "select chunk_id from embeddings", func(row *sql.Row, chunkId *string) error { | ||
return row.Scan(chunkId) | ||
}) | ||
assert.NoError(t, err) | ||
assert.Equal(t, "bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16", chunkId) | ||
} | ||
|
||
func TestEmbeddingsGateway_FindSimilar(t *testing.T) { | ||
testDb := testsupport.NewTestDb(t) | ||
defer testDb.Close() | ||
testDb.ClearTables() | ||
|
||
gateway := analyzer.NewEmbeddingsGateway(testDb.DB) | ||
|
||
testDb.Execute("insert into data (id, source, content) values ('aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16', 'https://example.com', 'some content')") | ||
testDb.Execute("insert into chunks (id, data_id, content) values ('bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16', 'aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16','a chunk')") | ||
testDb.Execute("insert into chunks (id, data_id, content) values ('cccccccc-2f3f-4bc9-8dba-ba397156cc16', 'aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16','another chunk')") | ||
|
||
err := gateway.Save("bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16", createVector(0)) | ||
assert.NoError(t, err) | ||
err = gateway.Save("cccccccc-2f3f-4bc9-8dba-ba397156cc16", createVector(1)) | ||
assert.NoError(t, err) | ||
|
||
similar, err := gateway.FindSimilar(createVector(1)) | ||
assert.NoError(t, err) | ||
|
||
assert.Equal(t, analyzer.CitedChunkRecord{Content: "another chunk", Source: "https://example.com"}, similar) | ||
} | ||
|
||
func createVector(oneIndex int) []float32 { | ||
embedding := make([]float32, 3072) | ||
embedding[oneIndex] = 1 | ||
return embedding | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,46 @@ | ||
package collector_test | ||
|
||
import ( | ||
"database/sql" | ||
"github.com/initialcapacity/ai-starter/internal/collector" | ||
"github.com/initialcapacity/ai-starter/pkg/dbsupport" | ||
"github.com/initialcapacity/ai-starter/pkg/testsupport" | ||
"github.com/stretchr/testify/assert" | ||
"testing" | ||
) | ||
|
||
func TestChunksGateway_Save(t *testing.T) { | ||
testDb := testsupport.NewTestDb(t) | ||
defer testDb.Close() | ||
testDb.ClearTables() | ||
|
||
gateway := collector.NewChunksGateway(testDb.DB) | ||
|
||
testDb.Execute("insert into data (id, source, content) values ('41345dc1-2f3f-4bc9-8dba-ba397156cc16', 'https://example.com', 'some content')") | ||
err := gateway.Save("41345dc1-2f3f-4bc9-8dba-ba397156cc16", "a chunk") | ||
assert.NoError(t, err) | ||
|
||
content, err := dbsupport.QueryOne(testDb.DB, "select content from chunks", func(row *sql.Row, content *string) error { | ||
return row.Scan(content) | ||
}) | ||
assert.NoError(t, err) | ||
assert.Equal(t, "a chunk", content) | ||
} | ||
|
||
func TestChunksGateway_Get(t *testing.T) { | ||
testDb := testsupport.NewTestDb(t) | ||
defer testDb.Close() | ||
testDb.ClearTables() | ||
|
||
gateway := collector.NewChunksGateway(testDb.DB) | ||
|
||
testDb.Execute("insert into data (id, source, content) values ('aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16', 'https://example.com', 'some content')") | ||
testDb.Execute("insert into chunks (id, data_id, content) values ('bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16', 'aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16','a chunk')") | ||
|
||
record, err := gateway.Get("bbbbbbbb-2f3f-4bc9-8dba-ba397156cc16") | ||
assert.NoError(t, err) | ||
assert.Equal(t, collector.ChunkRecord{ | ||
DataId: "aaaaaaaa-2f3f-4bc9-8dba-ba397156cc16", | ||
Content: "a chunk", | ||
}, record) | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters