Files
ragflow/internal/entity/models/voyage_test.go

414 lines
13 KiB
Go
Raw Normal View History

Go: implement provider: Voyage AI (#14811) ### What problem does this PR solve? Add a Go driver for Voyage AI (https://voyageai.com), one of the unchecked providers on the umbrella tracking issue #14736. Voyage AI is **embed + rerank only** — no chat, no streaming, no `/v1/models` endpoint. It's the first provider in the Go layer of this shape. Until this PR, a tenant who configured `voyage` as a model provider in the Go layer fell through to the default branch of `internal/entity/models/factory.go` and got the dummy driver. ### What this PR includes - New `internal/entity/models/voyage.go` with a `VoyageModel` implementing the `ModelDriver` interface. - New `conf/models/voyage.json` with 6 embedding models (`voyage-3.5`, `voyage-3.5-lite`, `voyage-3-large`, `voyage-code-3`, `voyage-law-2`, `voyage-finance-2`) and 2 rerank models (`rerank-2`, `rerank-2-lite`). - `factory.go`: route `"voyage"` to `NewVoyageModel`. - `internal/entity/models/voyage_test.go`: 19 unit tests. ### How the driver works - **Embed**: `POST /v1/embeddings`. Response is OpenAI-shaped (`{data: [{embedding, index, object, text}], model, usage}`). Driver reorders by `index`, rejects duplicate / out-of-range / missing slots, and short-circuits empty input without an HTTP call. - **Rerank**: `POST /v1/rerank`. Voyage uses **`top_k`** as the request param name (not `top_n` like Aliyun/SiliconFlow); the driver translates `RerankConfig.TopN` → `top_k`. Response is Cohere-shaped (`{data: [{relevance_score, index}], model}`), so the existing `RerankResponse{Data: []RerankResult{Index, RelevanceScore}}` shape fits cleanly. - **`ListModels`**: returns a hardcoded list of `voyageKnownModels`. Voyage does **not** expose `/v1/models` (probed live, returns 404), so the driver synthesizes the list from the same set the config ships. New upstream models are added by extending one slice. - **`CheckConnection`**: pings a 1-input embed call against `voyage-3.5`. Without `/v1/models`, this is the cheapest way to verify the API key + network path before a tenant tries a real workload. - **`ChatWithMessages` / `ChatStreamlyWithSender` / `Balance` / `TranscribeAudio` / `AudioSpeech` / `OCRFile`**: all return `"no such method"`. Voyage does not host any of these surfaces. No interface change. No new dependencies. ### How was this tested? **19 unit tests** in `internal/entity/models/voyage_test.go` — all pass on go 1.25: ``` $ go test -vet=off -run TestVoyage -count=1 ./internal/entity/models/... ok ragflow/internal/entity/models 0.036s ``` Coverage: Name; Embed (happy path, reorder, empty-input, missing key/model, duplicate index, out-of-range index, missing slot); Rerank (happy path with `top_k` assertion, default-to-len-documents, empty documents, out-of-range index); ListModels (static list, missing key); CheckConnection (happy, 401); chat methods sentinels; Balance sentinel; audio/OCR sentinels. `go build ./internal/entity/models/...` exits 0. **Live integration test** against `api.voyageai.com`: ``` === RUN TestVoyageLiveSmoke [OK] Name() = "voyage" [OK] ListModels (static): 8 models -> [voyage-3.5 voyage-3.5-lite voyage-3-large voyage-code-3 voyage-law-2 voyage-finance-2 rerank-2 rerank-2-lite] [OK] CheckConnection [OK] Embed vectors=3 dim=1024 indices=[0 1 2] [OK] Embed(empty) -> 0 vectors [OK] Rerank results=3 scores=[0.8125 0.59765625 0.39453125] [OK] ChatWithMessages returns voyage, no such method [OK] Balance returns voyage, no such method VOYAGE LIVE SMOKE PASSED --- PASS: TestVoyageLiveSmoke (0.81s) ``` What the live run proves on the wire: - Auth (`Bearer <key>`) accepted by `api.voyageai.com`. - Embed `voyage-3.5` on 3 inputs returns 3 vectors at dim 1024 with `index` field preserved as `[0, 1, 2]` — the reorder-by-index code is exercised on real data. - Empty input short-circuits without an HTTP call (mock server would have been hit if it did). - Rerank `rerank-2` on 3 docs returns 3 real `relevance_score` floats `[0.8125, 0.598, 0.395]`. The `top_k` translation works on the live wire. - All sentinel methods return the documented `"no such method"` strings. ### Note on PR history This branch was previously named for LocalAI Embed work which is now consolidated into PR #14813. The branch was reset to `upstream/main` and rebuilt for Voyage. Diff against `main` is a clean +838 lines across 4 files. ### Type of change - [x] New Feature (non-breaking change which adds functionality) Tracking: #14736 --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-13 15:46:54 -10:00
package models
import (
"encoding/json"
"io"
"net/http"
"net/http/httptest"
"strings"
"testing"
)
func newVoyageServer(t *testing.T, expectedPath string, handler func(t *testing.T, body map[string]interface{}, w http.ResponseWriter)) *httptest.Server {
t.Helper()
return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != expectedPath {
t.Errorf("expected path=%s, got %s", expectedPath, r.URL.Path)
return
}
if got := r.Header.Get("Authorization"); got != "Bearer test-key" {
t.Errorf("expected Authorization=Bearer test-key, got %q", got)
return
}
if got := r.Header.Get("Content-Type"); got != "application/json" {
t.Errorf("expected Content-Type=application/json, got %q", got)
return
}
raw, err := io.ReadAll(r.Body)
if err != nil {
t.Errorf("read body: %v", err)
return
}
var body map[string]interface{}
if err := json.Unmarshal(raw, &body); err != nil {
t.Errorf("unmarshal: %v\nraw=%s", err, string(raw))
return
}
handler(t, body, w)
}))
}
func newVoyageForTest(baseURL string) *VoyageModel {
return NewVoyageModel(
map[string]string{"default": baseURL},
URLSuffix{Embedding: "v1/embeddings", Rerank: "v1/rerank"},
)
}
func TestVoyageName(t *testing.T) {
2026-07-09 10:19:10 +08:00
if got := newVoyageForTest("http://unused").Name(); got != "Voyage AI" {
t.Errorf("Name()=%q, want %q", got, "Voyage AI")
Go: implement provider: Voyage AI (#14811) ### What problem does this PR solve? Add a Go driver for Voyage AI (https://voyageai.com), one of the unchecked providers on the umbrella tracking issue #14736. Voyage AI is **embed + rerank only** — no chat, no streaming, no `/v1/models` endpoint. It's the first provider in the Go layer of this shape. Until this PR, a tenant who configured `voyage` as a model provider in the Go layer fell through to the default branch of `internal/entity/models/factory.go` and got the dummy driver. ### What this PR includes - New `internal/entity/models/voyage.go` with a `VoyageModel` implementing the `ModelDriver` interface. - New `conf/models/voyage.json` with 6 embedding models (`voyage-3.5`, `voyage-3.5-lite`, `voyage-3-large`, `voyage-code-3`, `voyage-law-2`, `voyage-finance-2`) and 2 rerank models (`rerank-2`, `rerank-2-lite`). - `factory.go`: route `"voyage"` to `NewVoyageModel`. - `internal/entity/models/voyage_test.go`: 19 unit tests. ### How the driver works - **Embed**: `POST /v1/embeddings`. Response is OpenAI-shaped (`{data: [{embedding, index, object, text}], model, usage}`). Driver reorders by `index`, rejects duplicate / out-of-range / missing slots, and short-circuits empty input without an HTTP call. - **Rerank**: `POST /v1/rerank`. Voyage uses **`top_k`** as the request param name (not `top_n` like Aliyun/SiliconFlow); the driver translates `RerankConfig.TopN` → `top_k`. Response is Cohere-shaped (`{data: [{relevance_score, index}], model}`), so the existing `RerankResponse{Data: []RerankResult{Index, RelevanceScore}}` shape fits cleanly. - **`ListModels`**: returns a hardcoded list of `voyageKnownModels`. Voyage does **not** expose `/v1/models` (probed live, returns 404), so the driver synthesizes the list from the same set the config ships. New upstream models are added by extending one slice. - **`CheckConnection`**: pings a 1-input embed call against `voyage-3.5`. Without `/v1/models`, this is the cheapest way to verify the API key + network path before a tenant tries a real workload. - **`ChatWithMessages` / `ChatStreamlyWithSender` / `Balance` / `TranscribeAudio` / `AudioSpeech` / `OCRFile`**: all return `"no such method"`. Voyage does not host any of these surfaces. No interface change. No new dependencies. ### How was this tested? **19 unit tests** in `internal/entity/models/voyage_test.go` — all pass on go 1.25: ``` $ go test -vet=off -run TestVoyage -count=1 ./internal/entity/models/... ok ragflow/internal/entity/models 0.036s ``` Coverage: Name; Embed (happy path, reorder, empty-input, missing key/model, duplicate index, out-of-range index, missing slot); Rerank (happy path with `top_k` assertion, default-to-len-documents, empty documents, out-of-range index); ListModels (static list, missing key); CheckConnection (happy, 401); chat methods sentinels; Balance sentinel; audio/OCR sentinels. `go build ./internal/entity/models/...` exits 0. **Live integration test** against `api.voyageai.com`: ``` === RUN TestVoyageLiveSmoke [OK] Name() = "voyage" [OK] ListModels (static): 8 models -> [voyage-3.5 voyage-3.5-lite voyage-3-large voyage-code-3 voyage-law-2 voyage-finance-2 rerank-2 rerank-2-lite] [OK] CheckConnection [OK] Embed vectors=3 dim=1024 indices=[0 1 2] [OK] Embed(empty) -> 0 vectors [OK] Rerank results=3 scores=[0.8125 0.59765625 0.39453125] [OK] ChatWithMessages returns voyage, no such method [OK] Balance returns voyage, no such method VOYAGE LIVE SMOKE PASSED --- PASS: TestVoyageLiveSmoke (0.81s) ``` What the live run proves on the wire: - Auth (`Bearer <key>`) accepted by `api.voyageai.com`. - Embed `voyage-3.5` on 3 inputs returns 3 vectors at dim 1024 with `index` field preserved as `[0, 1, 2]` — the reorder-by-index code is exercised on real data. - Empty input short-circuits without an HTTP call (mock server would have been hit if it did). - Rerank `rerank-2` on 3 docs returns 3 real `relevance_score` floats `[0.8125, 0.598, 0.395]`. The `top_k` translation works on the live wire. - All sentinel methods return the documented `"no such method"` strings. ### Note on PR history This branch was previously named for LocalAI Embed work which is now consolidated into PR #14813. The branch was reset to `upstream/main` and rebuilt for Voyage. Diff against `main` is a clean +838 lines across 4 files. ### Type of change - [x] New Feature (non-breaking change which adds functionality) Tracking: #14736 --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-13 15:46:54 -10:00
}
}
func TestVoyageNewModelWithCustomDefaultTransport(t *testing.T) {
original := http.DefaultTransport
http.DefaultTransport = roundTripperFunc(func(*http.Request) (*http.Response, error) {
return nil, nil
})
t.Cleanup(func() {
http.DefaultTransport = original
})
if model := NewVoyageModel(map[string]string{"default": "http://unused"}, URLSuffix{}); model == nil {
t.Fatal("NewVoyageModel returned nil")
}
}
Go: implement provider: Voyage AI (#14811) ### What problem does this PR solve? Add a Go driver for Voyage AI (https://voyageai.com), one of the unchecked providers on the umbrella tracking issue #14736. Voyage AI is **embed + rerank only** — no chat, no streaming, no `/v1/models` endpoint. It's the first provider in the Go layer of this shape. Until this PR, a tenant who configured `voyage` as a model provider in the Go layer fell through to the default branch of `internal/entity/models/factory.go` and got the dummy driver. ### What this PR includes - New `internal/entity/models/voyage.go` with a `VoyageModel` implementing the `ModelDriver` interface. - New `conf/models/voyage.json` with 6 embedding models (`voyage-3.5`, `voyage-3.5-lite`, `voyage-3-large`, `voyage-code-3`, `voyage-law-2`, `voyage-finance-2`) and 2 rerank models (`rerank-2`, `rerank-2-lite`). - `factory.go`: route `"voyage"` to `NewVoyageModel`. - `internal/entity/models/voyage_test.go`: 19 unit tests. ### How the driver works - **Embed**: `POST /v1/embeddings`. Response is OpenAI-shaped (`{data: [{embedding, index, object, text}], model, usage}`). Driver reorders by `index`, rejects duplicate / out-of-range / missing slots, and short-circuits empty input without an HTTP call. - **Rerank**: `POST /v1/rerank`. Voyage uses **`top_k`** as the request param name (not `top_n` like Aliyun/SiliconFlow); the driver translates `RerankConfig.TopN` → `top_k`. Response is Cohere-shaped (`{data: [{relevance_score, index}], model}`), so the existing `RerankResponse{Data: []RerankResult{Index, RelevanceScore}}` shape fits cleanly. - **`ListModels`**: returns a hardcoded list of `voyageKnownModels`. Voyage does **not** expose `/v1/models` (probed live, returns 404), so the driver synthesizes the list from the same set the config ships. New upstream models are added by extending one slice. - **`CheckConnection`**: pings a 1-input embed call against `voyage-3.5`. Without `/v1/models`, this is the cheapest way to verify the API key + network path before a tenant tries a real workload. - **`ChatWithMessages` / `ChatStreamlyWithSender` / `Balance` / `TranscribeAudio` / `AudioSpeech` / `OCRFile`**: all return `"no such method"`. Voyage does not host any of these surfaces. No interface change. No new dependencies. ### How was this tested? **19 unit tests** in `internal/entity/models/voyage_test.go` — all pass on go 1.25: ``` $ go test -vet=off -run TestVoyage -count=1 ./internal/entity/models/... ok ragflow/internal/entity/models 0.036s ``` Coverage: Name; Embed (happy path, reorder, empty-input, missing key/model, duplicate index, out-of-range index, missing slot); Rerank (happy path with `top_k` assertion, default-to-len-documents, empty documents, out-of-range index); ListModels (static list, missing key); CheckConnection (happy, 401); chat methods sentinels; Balance sentinel; audio/OCR sentinels. `go build ./internal/entity/models/...` exits 0. **Live integration test** against `api.voyageai.com`: ``` === RUN TestVoyageLiveSmoke [OK] Name() = "voyage" [OK] ListModels (static): 8 models -> [voyage-3.5 voyage-3.5-lite voyage-3-large voyage-code-3 voyage-law-2 voyage-finance-2 rerank-2 rerank-2-lite] [OK] CheckConnection [OK] Embed vectors=3 dim=1024 indices=[0 1 2] [OK] Embed(empty) -> 0 vectors [OK] Rerank results=3 scores=[0.8125 0.59765625 0.39453125] [OK] ChatWithMessages returns voyage, no such method [OK] Balance returns voyage, no such method VOYAGE LIVE SMOKE PASSED --- PASS: TestVoyageLiveSmoke (0.81s) ``` What the live run proves on the wire: - Auth (`Bearer <key>`) accepted by `api.voyageai.com`. - Embed `voyage-3.5` on 3 inputs returns 3 vectors at dim 1024 with `index` field preserved as `[0, 1, 2]` — the reorder-by-index code is exercised on real data. - Empty input short-circuits without an HTTP call (mock server would have been hit if it did). - Rerank `rerank-2` on 3 docs returns 3 real `relevance_score` floats `[0.8125, 0.598, 0.395]`. The `top_k` translation works on the live wire. - All sentinel methods return the documented `"no such method"` strings. ### Note on PR history This branch was previously named for LocalAI Embed work which is now consolidated into PR #14813. The branch was reset to `upstream/main` and rebuilt for Voyage. Diff against `main` is a clean +838 lines across 4 files. ### Type of change - [x] New Feature (non-breaking change which adds functionality) Tracking: #14736 --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-13 15:46:54 -10:00
func TestVoyageEmbedHappyPath(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, body map[string]interface{}, w http.ResponseWriter) {
if body["model"] != "voyage-3.5" {
t.Errorf("model=%v", body["model"])
}
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"object": "list",
"data": []map[string]interface{}{
{"object": "embedding", "embedding": []float64{0.1, 0.2}, "index": 0},
{"object": "embedding", "embedding": []float64{0.3, 0.4}, "index": 1},
{"object": "embedding", "embedding": []float64{0.5, 0.6}, "index": 2},
},
"model": "voyage-3.5",
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
vecs, err := v.Embed(&model, []string{"a", "b", "c"}, &APIConfig{ApiKey: &apiKey}, nil)
if err != nil {
t.Fatalf("Embed: %v", err)
}
if len(vecs) != 3 {
t.Fatalf("len=%d want 3", len(vecs))
}
if vecs[1].Embedding[0] != 0.3 || vecs[1].Index != 1 {
t.Errorf("vecs[1]=%+v", vecs[1])
}
}
// TestVoyageEmbedPropagatesOutputDimension pins the docs-spelled
// param name. Voyage 400s on any other key (live-verified — sending
// "dimensions" returns "Argument 'dimensions' is not supported by our
// API"), so this name matters and must not regress.
func TestVoyageEmbedPropagatesOutputDimension(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, body map[string]interface{}, w http.ResponseWriter) {
if got, ok := body["output_dimension"].(float64); !ok || got != 256 {
t.Errorf("output_dimension=%v want 256", body["output_dimension"])
}
for _, wrong := range []string{"dimensions", "output_dimensions", "dimension"} {
if _, present := body[wrong]; present {
t.Errorf("must not send %q (Voyage rejects unknown fields)", wrong)
}
}
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{{"embedding": []float64{0.1}, "index": 0}},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
_, err := v.Embed(&model, []string{"x"}, &APIConfig{ApiKey: &apiKey},
&EmbeddingConfig{Dimension: 256})
if err != nil {
t.Fatalf("Embed: %v", err)
}
}
// And when Dimension is zero/unset, the field MUST be absent — Voyage
// would default the vector length, but only if we don't send the key
// at all (sending output_dimension: 0 is a 400).
func TestVoyageEmbedOmitsOutputDimensionWhenUnset(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, body map[string]interface{}, w http.ResponseWriter) {
if _, present := body["output_dimension"]; present {
t.Errorf("output_dimension must be absent when Dimension is unset, got %v", body["output_dimension"])
}
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{{"embedding": []float64{0.1}, "index": 0}},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
_, err := v.Embed(&model, []string{"x"}, &APIConfig{ApiKey: &apiKey}, nil)
if err != nil {
t.Fatalf("Embed: %v", err)
}
}
func TestVoyageEmbedReordersByIndex(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, _ map[string]interface{}, w http.ResponseWriter) {
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{
{"embedding": []float64{2}, "index": 2},
{"embedding": []float64{0}, "index": 0},
{"embedding": []float64{1}, "index": 1},
},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
vecs, err := v.Embed(&model, []string{"a", "b", "c"}, &APIConfig{ApiKey: &apiKey}, nil)
if err != nil {
t.Fatalf("Embed: %v", err)
}
for i, vec := range vecs {
if vec.Index != i || vec.Embedding[0] != float64(i) {
t.Errorf("slot %d=%+v", i, vec)
}
}
}
func TestVoyageEmbedEmptyInputShortCircuits(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
t.Error("Embed([]) made an unexpected HTTP call")
}))
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
vecs, err := v.Embed(&model, []string{}, &APIConfig{ApiKey: &apiKey}, nil)
if err != nil || len(vecs) != 0 {
t.Errorf("Embed([])=(%v,%v)", vecs, err)
}
}
func TestVoyageEmbedRequiresAPIKey(t *testing.T) {
v := newVoyageForTest("http://unused")
model := "voyage-3.5"
_, err := v.Embed(&model, []string{"a"}, &APIConfig{}, nil)
if err == nil || !strings.Contains(err.Error(), "api key is required") {
t.Errorf("expected api-key error, got %v", err)
}
}
func TestVoyageEmbedRequiresModelName(t *testing.T) {
v := newVoyageForTest("http://unused")
apiKey := "test-key"
_, err := v.Embed(nil, []string{"a"}, &APIConfig{ApiKey: &apiKey}, nil)
if err == nil || !strings.Contains(err.Error(), "model name is required") {
t.Errorf("expected model-name error, got %v", err)
}
}
func TestVoyageEmbedRejectsDuplicateIndex(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, _ map[string]interface{}, w http.ResponseWriter) {
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{
{"embedding": []float64{1}, "index": 0},
{"embedding": []float64{2}, "index": 0},
},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
_, err := v.Embed(&model, []string{"a", "b"}, &APIConfig{ApiKey: &apiKey}, nil)
if err == nil || !strings.Contains(err.Error(), "duplicate embedding index 0") {
t.Errorf("expected duplicate error, got %v", err)
}
}
func TestVoyageEmbedRejectsOutOfRangeIndex(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, _ map[string]interface{}, w http.ResponseWriter) {
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{
{"embedding": []float64{1}, "index": 7},
},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
_, err := v.Embed(&model, []string{"a", "b"}, &APIConfig{ApiKey: &apiKey}, nil)
if err == nil || !strings.Contains(err.Error(), "out of range") {
t.Errorf("expected out-of-range error, got %v", err)
}
}
func TestVoyageEmbedRejectsMissingSlot(t *testing.T) {
srv := newVoyageServer(t, "/v1/embeddings", func(t *testing.T, _ map[string]interface{}, w http.ResponseWriter) {
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{
{"embedding": []float64{1}, "index": 0},
},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "voyage-3.5"
_, err := v.Embed(&model, []string{"a", "b"}, &APIConfig{ApiKey: &apiKey}, nil)
if err == nil || !strings.Contains(err.Error(), "missing embedding for input index 1") {
t.Errorf("expected missing-slot error, got %v", err)
}
}
func TestVoyageRerankHappyPath(t *testing.T) {
srv := newVoyageServer(t, "/v1/rerank", func(t *testing.T, body map[string]interface{}, w http.ResponseWriter) {
// Voyage's request key is top_k (not top_n).
if body["top_k"] != float64(3) {
t.Errorf("top_k=%v want 3", body["top_k"])
}
if body["query"] != "x" {
t.Errorf("query=%v", body["query"])
}
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"object": "list",
"data": []map[string]interface{}{
{"relevance_score": 0.8, "index": 2},
{"relevance_score": 0.5, "index": 0},
{"relevance_score": 0.3, "index": 1},
},
"model": "rerank-2",
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "rerank-2"
resp, err := v.Rerank(&model, "x", []string{"a", "b", "c"},
&APIConfig{ApiKey: &apiKey}, &RerankConfig{TopN: 3})
if err != nil {
t.Fatalf("Rerank: %v", err)
}
if len(resp.Data) != 3 {
t.Fatalf("len=%d want 3", len(resp.Data))
}
want := map[int]float64{0: 0.5, 1: 0.3, 2: 0.8}
for _, r := range resp.Data {
if got, ok := want[r.Index]; !ok || got != r.RelevanceScore {
t.Errorf("unexpected result index=%d score=%v", r.Index, r.RelevanceScore)
}
}
}
func TestVoyageRerankTopKDefaultsToLenDocuments(t *testing.T) {
srv := newVoyageServer(t, "/v1/rerank", func(t *testing.T, body map[string]interface{}, w http.ResponseWriter) {
if body["top_k"] != float64(4) {
t.Errorf("top_k=%v want 4 (len(documents))", body["top_k"])
}
_ = json.NewEncoder(w).Encode(map[string]interface{}{"data": []map[string]interface{}{}})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "rerank-2"
_, err := v.Rerank(&model, "x", []string{"a", "b", "c", "d"},
&APIConfig{ApiKey: &apiKey}, &RerankConfig{})
if err != nil {
t.Fatalf("Rerank: %v", err)
}
}
func TestVoyageRerankEmptyDocuments(t *testing.T) {
v := newVoyageForTest("http://unused")
apiKey := "test-key"
model := "rerank-2"
resp, err := v.Rerank(&model, "x", nil,
&APIConfig{ApiKey: &apiKey}, &RerankConfig{TopN: 0})
if err != nil {
t.Fatalf("Rerank: %v", err)
}
if len(resp.Data) != 0 {
t.Errorf("expected empty Data, got %d", len(resp.Data))
}
}
func TestVoyageRerankRejectsOutOfRangeIndex(t *testing.T) {
srv := newVoyageServer(t, "/v1/rerank", func(t *testing.T, _ map[string]interface{}, w http.ResponseWriter) {
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{
{"relevance_score": 0.9, "index": 7},
},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "rerank-2"
_, err := v.Rerank(&model, "x", []string{"a", "b"},
&APIConfig{ApiKey: &apiKey}, &RerankConfig{TopN: 2})
if err == nil || !strings.Contains(err.Error(), "out of range") {
t.Errorf("expected out-of-range error, got %v", err)
}
}
func TestVoyageRerankRejectsDuplicateIndex(t *testing.T) {
// A duplicate index would silently overwrite an earlier slot, which
// is the same failure mode Embed already guards against. Make sure
// Rerank fails loudly too.
srv := newVoyageServer(t, "/v1/rerank", func(t *testing.T, _ map[string]interface{}, w http.ResponseWriter) {
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{
{"relevance_score": 0.9, "index": 0},
{"relevance_score": 0.8, "index": 0},
},
})
})
defer srv.Close()
v := newVoyageForTest(srv.URL)
apiKey := "test-key"
model := "rerank-2"
_, err := v.Rerank(&model, "x", []string{"a", "b"},
&APIConfig{ApiKey: &apiKey}, &RerankConfig{TopN: 2})
if err == nil || !strings.Contains(err.Error(), "duplicate rerank index 0") {
t.Errorf("expected duplicate-index error, got %v", err)
}
}
// TestVoyageEmbedTrimsTrailingSlashInBaseURL guards against a
// misconfigured baseURL ending in "/" producing a double-slash path
// (e.g. `.../v1//embeddings`). Rerank already trims, so Embed must
// trim too; CodeRabbit flagged the inconsistency.
func TestVoyageEmbedTrimsTrailingSlashInBaseURL(t *testing.T) {
var sawPath string
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
sawPath = r.URL.Path
_ = json.NewEncoder(w).Encode(map[string]interface{}{
"data": []map[string]interface{}{{"embedding": []float64{1}, "index": 0}},
})
}))
defer srv.Close()
v := NewVoyageModel(
map[string]string{"default": srv.URL + "/"}, // trailing slash
URLSuffix{Embedding: "v1/embeddings", Rerank: "v1/rerank"},
)
apiKey := "test-key"
model := "voyage-3.5"
if _, err := v.Embed(&model, []string{"x"}, &APIConfig{ApiKey: &apiKey}, nil); err != nil {
t.Fatalf("Embed: %v", err)
}
if sawPath != "/v1/embeddings" {
t.Errorf("path=%q want %q (no double slash)", sawPath, "/v1/embeddings")
}
}