{ "aboutHtml": "

依問題找到需要的頁面

Llama Nemotron Embed VL 1B v2 由 NVIDIA 開發，用於搜尋可協助回答問題的資料。查詢以文字設定；Ailoot 目前目錄為模型提供文字輸入，問題與資料皆以文字編碼。廠商也描述了以頁面影像，或影像搭配擷取文字表示文件的方式。這些視覺形式需要獨立且支援影像的方法。在相應輸入下，模型可將表格、圖表與資訊圖表表示於共同向量空間。

這種搜尋適合大型文件集的問答助理、內部參考資料與研究文件。編碼結果為數值向量；找到的頁面或片段，可再交給生成答案的模型。Embed VL 本身完成的是上下文搜尋階段。

廠商提供的文件形式

查詢與文件分別編碼，因此可預先處理文件集，將向量與原始頁面一起儲存，新問題出現時只計算查詢向量。向量相似度協助依語意選擇資料。查詢與文件的文字角色不同，準備資料時必須保留這個區別。

表示大小與輸入長度

每項輸入轉換成一個最多包含 2048 個數值的向量。文字模式使用 8192 個 token 的預算。廠商結合影像與文字的視覺方法，描述了兩者共用的 10240 個 token 預算，這不是 Ailoot 方法的文字上限。影像會分成片段；所述設定最多提供六個片段及整頁的縮小副本，合計約 1792 個視覺 token。長文字必須分段或縮短。

語言部分以 Llama 3.2 1B 為基礎，視覺部分使用 SigLIP2，兩者結合為編碼器，將輸入 token 的表示取平均後輸出單一向量。對比訓練讓問題更接近合適頁面，並遠離不相關資料。搜尋仍具機率性，向量接近不保證所選片段包含正確答案。

", "aboutText": "### 依問題找到需要的頁面\n\nLlama Nemotron Embed VL 1B v2 由 NVIDIA 開發，用於搜尋可協助回答問題的資料。查詢以文字設定；Ailoot 目前目錄為模型提供文字輸入，問題與資料皆以文字編碼。廠商也描述了以頁面影像，或影像搭配擷取文字表示文件的方式。這些視覺形式需要獨立且支援影像的方法。在相應輸入下，模型可將表格、圖表與資訊圖表表示於共同向量空間。\n\n這種搜尋適合大型文件集的問答助理、內部參考資料與研究文件。編碼結果為數值向量；找到的頁面或片段，可再交給生成答案的模型。Embed VL 本身完成的是上下文搜尋階段。\n\n### 廠商提供的文件形式\n\n- 文字文件：獨立章節、片段，或已辨識的頁面文字。\n- 影像：包含文字、表格與圖像元素的完整頁面。\n- 影像搭配文字：頁面的視覺外觀與文字內容，結合成同一表示形式。\n\n查詢與文件分別編碼，因此可預先處理文件集，將向量與原始頁面一起儲存，新問題出現時只計算查詢向量。向量相似度協助依語意選擇資料。查詢與文件的文字角色不同，準備資料時必須保留這個區別。\n\n### 表示大小與輸入長度\n\n每項輸入轉換成一個最多包含 2048 個數值的向量。文字模式使用 8192 個 token 的預算。廠商結合影像與文字的視覺方法，描述了兩者共用的 10240 個 token 預算，這不是 Ailoot 方法的文字上限。影像會分成片段；所述設定最多提供六個片段及整頁的縮小副本，合計約 1792 個視覺 token。長文字必須分段或縮短。\n\n語言部分以 Llama 3.2 1B 為基礎，視覺部分使用 SigLIP2，兩者結合為編碼器，將輸入 token 的表示取平均後輸出單一向量。對比訓練讓問題更接近合適頁面，並遠離不相關資料。搜尋仍具機率性，向量接近不保證所選片段包含正確答案。", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "cb722c3635f9869a23508ff01f613747e1dbe072c023a91d89cf40fbdc75ee85", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "zh-hant-tw", "methods": [ { "html": "
NV

Llama Nemotron Embed VL 1B v2

NVIDIA /nvidia/llama-nemotron-embed-vl-1b-v2

入門

Llama Nemotron Embed VL v2 為文件語意搜尋建立向量。Ailoot 目前目錄提供查詢與資料的文字輸入。

接受的輸入
文字
結果
embedding
關於模型

此說明介紹模型的能力。Ailoot 可用的輸入、輸出與選項，依所選方法列於下方。

依問題找到需要的頁面

Llama Nemotron Embed VL 1B v2 由 NVIDIA 開發，用於搜尋可協助回答問題的資料。查詢以文字設定；Ailoot 目前目錄為模型提供文字輸入，問題與資料皆以文字編碼。廠商也描述了以頁面影像，或影像搭配擷取文字表示文件的方式。這些視覺形式需要獨立且支援影像的方法。在相應輸入下，模型可將表格、圖表與資訊圖表表示於共同向量空間。

這種搜尋適合大型文件集的問答助理、內部參考資料與研究文件。編碼結果為數值向量；找到的頁面或片段，可再交給生成答案的模型。Embed VL 本身完成的是上下文搜尋階段。

廠商提供的文件形式

  • 文字文件：獨立章節、片段，或已辨識的頁面文字。
  • 影像：包含文字、表格與圖像元素的完整頁面。
  • 影像搭配文字：頁面的視覺外觀與文字內容，結合成同一表示形式。

查詢與文件分別編碼，因此可預先處理文件集，將向量與原始頁面一起儲存，新問題出現時只計算查詢向量。向量相似度協助依語意選擇資料。查詢與文件的文字角色不同，準備資料時必須保留這個區別。

表示大小與輸入長度

每項輸入轉換成一個最多包含 2048 個數值的向量。文字模式使用 8192 個 token 的預算。廠商結合影像與文字的視覺方法，描述了兩者共用的 10240 個 token 預算，這不是 Ailoot 方法的文字上限。影像會分成片段；所述設定最多提供六個片段及整頁的縮小副本，合計約 1792 個視覺 token。長文字必須分段或縮短。

語言部分以 Llama 3.2 1B 為基礎，視覺部分使用 SigLIP2，兩者結合為編碼器，將輸入 token 的表示取平均後輸出單一向量。對比訓練讓問題更接近合適頁面，並遠離不相關資料。搜尋仍具機率性，向量接近不保證所選片段包含正確答案。

Ailoot 可用 · 輸入與方法

Ailoot · 嵌入向量 POST /v1/embeddings
輸入
text
輸出
embedding
上下文
4,096 tokens
輸出格式
json
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
nvidia/llama-nemotron-embed-vl-1b-v2
預設值—
欄位input類型string|string[]要求必填值與限制
項目數下限: 1
條件: 每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。
預設值—
欄位input_type類型string要求選填值與限制
query, passage
預設值query
欄位encoding_format類型string要求選填值與限制
float, base64
預設值float
欄位truncate類型string要求選填值與限制
NONE, START, END
預設值—
欄位dimensions類型integer要求選填值與限制
最小值: 1
預設值—
欄位user類型string要求選填值與限制預設值—
輸入素材組合

text_to_embedding

方法參數與生命週期
參數規格
參數material_types規格text
參數required規格model, input
參數optional_controls規格null
參數content_type規格application/json

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot 嵌入向量POST /v1/embeddings
輸入
US$0.0001 / 1K

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · 嵌入向量

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nvidia/llama-nemotron-embed-vl-1b-v2", "input": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]=[text]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))\nPY_RESULT\n

接收並儲存結果

Ailoot · 嵌入向量

json

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。

需要檢查原始回應時

此流程未引入嵌入向量任務端點。

回應欄位
欄位類型
欄位data[].index類型integer
欄位data[].embedding類型finite float[]|base64 float32 vector
欄位model類型string
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot nvidia/llama-nemotron-embed-vl-1b-v2, nemotron-embed-vl, nemotron-embed-vl-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

nvidia/llama-nemotron-embed-vl-1b-v2, nemotron-embed-vl, nemotron-embed-vl-latest

", "method_identity": { "effective_request_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "fmt": "embeddings", "http": "POST", "path": "/v1/embeddings", "request_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "route_label": "Core" }, "method_key": "Core|embeddings|/v1/embeddings|nvidia%2Fllama-nemotron-embed-vl-1b-v2", "ordinal": 0, "rawMethod": { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Decode base64 vectors only when that format was requested; retain every vector and its original index.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "此流程未引入嵌入向量任務端點。" }, "material_combinations": [ { "alternatives": [ "nonempty string", "nonempty string[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。", "family": "embedding", "fields": [ { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]|base64 float32 vector" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "nvidia/llama-nemotron-embed-vl-1b-v2" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "conditions": "每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]" }, { "availability": "source_interface", "default": "query", "default_known": true, "enum": [ "query", "passage" ], "enum_known": true, "name": "input_type", "required": false, "type": "string" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float", "base64" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "NONE", "START", "END" ], "enum_known": true, "name": "truncate", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "image objects", "data URI text inputs", "token integer arrays on this NVIDIA adapter" ] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": null, "required": [ "model", "input" ] }, "lifecycle": { "mode": "exact retained published method" }, "method": { "http": "POST", "path": "/v1/embeddings" }, "operation_modes": [ "embeddings" ], "output": { "family": [ "embedding" ], "format": "indexed vectors JSON", "multioutputs": "retain every actual response output" } }, "ctx": 4096, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/llama-nemotron-embed-vl-1b-v2\", \"input\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=[text]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "Embed your source material", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "embeddings", "http": "POST", "img_in": null, "img_out": null, "in": 0.1, "input": [ "text" ], "label": "嵌入向量", "max_out": 0, "max_tool_calls": null, "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.1, "amount_unit": "usd_per_million_tokens", "key": "in", "label": "Input", "side": "in" }, { "amount": 0, "amount_unit": "usd_per_million_tokens", "key": "out", "label": "Output", "side": "out" } ] } ], "request_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } }, { "html": "
NV

Llama Nemotron Embed VL 1B v2

NVIDIA /nemotron-embed-vl

入門

Llama Nemotron Embed VL v2 為文件語意搜尋建立向量。Ailoot 目前目錄提供查詢與資料的文字輸入。

接受的輸入
文字
結果
embedding
關於模型

此說明介紹模型的能力。Ailoot 可用的輸入、輸出與選項，依所選方法列於下方。

依問題找到需要的頁面

Llama Nemotron Embed VL 1B v2 由 NVIDIA 開發，用於搜尋可協助回答問題的資料。查詢以文字設定；Ailoot 目前目錄為模型提供文字輸入，問題與資料皆以文字編碼。廠商也描述了以頁面影像，或影像搭配擷取文字表示文件的方式。這些視覺形式需要獨立且支援影像的方法。在相應輸入下，模型可將表格、圖表與資訊圖表表示於共同向量空間。

這種搜尋適合大型文件集的問答助理、內部參考資料與研究文件。編碼結果為數值向量；找到的頁面或片段，可再交給生成答案的模型。Embed VL 本身完成的是上下文搜尋階段。

廠商提供的文件形式

  • 文字文件：獨立章節、片段，或已辨識的頁面文字。
  • 影像：包含文字、表格與圖像元素的完整頁面。
  • 影像搭配文字：頁面的視覺外觀與文字內容，結合成同一表示形式。

查詢與文件分別編碼，因此可預先處理文件集，將向量與原始頁面一起儲存，新問題出現時只計算查詢向量。向量相似度協助依語意選擇資料。查詢與文件的文字角色不同，準備資料時必須保留這個區別。

表示大小與輸入長度

每項輸入轉換成一個最多包含 2048 個數值的向量。文字模式使用 8192 個 token 的預算。廠商結合影像與文字的視覺方法，描述了兩者共用的 10240 個 token 預算，這不是 Ailoot 方法的文字上限。影像會分成片段；所述設定最多提供六個片段及整頁的縮小副本，合計約 1792 個視覺 token。長文字必須分段或縮短。

語言部分以 Llama 3.2 1B 為基礎，視覺部分使用 SigLIP2，兩者結合為編碼器，將輸入 token 的表示取平均後輸出單一向量。對比訓練讓問題更接近合適頁面，並遠離不相關資料。搜尋仍具機率性，向量接近不保證所選片段包含正確答案。

Ailoot 可用 · 輸入與方法

Ailoot · 嵌入向量 POST /v1/embeddings
輸入
text
輸出
embedding
上下文
4,096 tokens
輸出格式
json
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
nemotron-embed-vl
預設值—
欄位input類型string|string[]要求必填值與限制
項目數下限: 1
條件: 每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。
預設值—
欄位input_type類型string要求選填值與限制
query, passage
預設值query
欄位encoding_format類型string要求選填值與限制
float, base64
預設值float
欄位truncate類型string要求選填值與限制
NONE, START, END
預設值—
欄位dimensions類型integer要求選填值與限制
最小值: 1
預設值—
欄位user類型string要求選填值與限制預設值—
輸入素材組合

text_to_embedding

方法參數與生命週期
參數規格
參數material_types規格text
參數required規格model, input
參數optional_controls規格null
參數content_type規格application/json

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot 嵌入向量POST /v1/embeddings
輸入
US$0.0001 / 1K

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · 嵌入向量

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nemotron-embed-vl", "input": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]=[text]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))\nPY_RESULT\n

接收並儲存結果

Ailoot · 嵌入向量

json

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。

需要檢查原始回應時

此流程未引入嵌入向量任務端點。

回應欄位
欄位類型
欄位data[].index類型integer
欄位data[].embedding類型finite float[]|base64 float32 vector
欄位model類型string
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot nvidia/llama-nemotron-embed-vl-1b-v2, nemotron-embed-vl, nemotron-embed-vl-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

nvidia/llama-nemotron-embed-vl-1b-v2, nemotron-embed-vl, nemotron-embed-vl-latest

", "method_identity": { "effective_request_model_id": "nemotron-embed-vl", "fmt": "embeddings", "http": "POST", "path": "/v1/embeddings", "request_model_id": "nemotron-embed-vl", "route_label": "Core" }, "method_key": "Core|embeddings|/v1/embeddings|nemotron-embed-vl", "ordinal": 1, "rawMethod": { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Decode base64 vectors only when that format was requested; retain every vector and its original index.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "此流程未引入嵌入向量任務端點。" }, "material_combinations": [ { "alternatives": [ "nonempty string", "nonempty string[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。", "family": "embedding", "fields": [ { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]|base64 float32 vector" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "nemotron-embed-vl" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "conditions": "每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]" }, { "availability": "source_interface", "default": "query", "default_known": true, "enum": [ "query", "passage" ], "enum_known": true, "name": "input_type", "required": false, "type": "string" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float", "base64" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "NONE", "START", "END" ], "enum_known": true, "name": "truncate", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "image objects", "data URI text inputs", "token integer arrays on this NVIDIA adapter" ] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": null, "required": [ "model", "input" ] }, "lifecycle": { "mode": "exact retained published method" }, "method": { "http": "POST", "path": "/v1/embeddings" }, "operation_modes": [ "embeddings" ], "output": { "family": [ "embedding" ], "format": "indexed vectors JSON", "multioutputs": "retain every actual response output" } }, "ctx": 4096, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-embed-vl\", \"input\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=[text]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "Embed your source material", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "embeddings", "http": "POST", "img_in": null, "img_out": null, "in": 0.1, "input": [ "text" ], "label": "嵌入向量", "max_out": 0, "max_tool_calls": null, "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.1, "amount_unit": "usd_per_million_tokens", "key": "in", "label": "Input", "side": "in" }, { "amount": 0, "amount_unit": "usd_per_million_tokens", "key": "out", "label": "Output", "side": "out" } ] } ], "request_model_id": "nemotron-embed-vl", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } }, { "html": "
NV

Llama Nemotron Embed VL 1B v2

NVIDIA /nemotron-embed-vl-latest

入門

Llama Nemotron Embed VL v2 為文件語意搜尋建立向量。Ailoot 目前目錄提供查詢與資料的文字輸入。

接受的輸入
文字
結果
embedding
關於模型

此說明介紹模型的能力。Ailoot 可用的輸入、輸出與選項，依所選方法列於下方。

依問題找到需要的頁面

Llama Nemotron Embed VL 1B v2 由 NVIDIA 開發，用於搜尋可協助回答問題的資料。查詢以文字設定；Ailoot 目前目錄為模型提供文字輸入，問題與資料皆以文字編碼。廠商也描述了以頁面影像，或影像搭配擷取文字表示文件的方式。這些視覺形式需要獨立且支援影像的方法。在相應輸入下，模型可將表格、圖表與資訊圖表表示於共同向量空間。

這種搜尋適合大型文件集的問答助理、內部參考資料與研究文件。編碼結果為數值向量；找到的頁面或片段，可再交給生成答案的模型。Embed VL 本身完成的是上下文搜尋階段。

廠商提供的文件形式

  • 文字文件：獨立章節、片段，或已辨識的頁面文字。
  • 影像：包含文字、表格與圖像元素的完整頁面。
  • 影像搭配文字：頁面的視覺外觀與文字內容，結合成同一表示形式。

查詢與文件分別編碼，因此可預先處理文件集，將向量與原始頁面一起儲存，新問題出現時只計算查詢向量。向量相似度協助依語意選擇資料。查詢與文件的文字角色不同，準備資料時必須保留這個區別。

表示大小與輸入長度

每項輸入轉換成一個最多包含 2048 個數值的向量。文字模式使用 8192 個 token 的預算。廠商結合影像與文字的視覺方法，描述了兩者共用的 10240 個 token 預算，這不是 Ailoot 方法的文字上限。影像會分成片段；所述設定最多提供六個片段及整頁的縮小副本，合計約 1792 個視覺 token。長文字必須分段或縮短。

語言部分以 Llama 3.2 1B 為基礎，視覺部分使用 SigLIP2，兩者結合為編碼器，將輸入 token 的表示取平均後輸出單一向量。對比訓練讓問題更接近合適頁面，並遠離不相關資料。搜尋仍具機率性，向量接近不保證所選片段包含正確答案。

Ailoot 可用 · 輸入與方法

Ailoot · 嵌入向量 POST /v1/embeddings
輸入
text
輸出
embedding
上下文
4,096 tokens
輸出格式
json
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
nemotron-embed-vl-latest
預設值—
欄位input類型string|string[]要求必填值與限制
項目數下限: 1
條件: 每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。
預設值—
欄位input_type類型string要求選填值與限制
query, passage
預設值query
欄位encoding_format類型string要求選填值與限制
float, base64
預設值float
欄位truncate類型string要求選填值與限制
NONE, START, END
預設值—
欄位dimensions類型integer要求選填值與限制
最小值: 1
預設值—
欄位user類型string要求選填值與限制預設值—
輸入素材組合

text_to_embedding

方法參數與生命週期
參數規格
參數material_types規格text
參數required規格model, input
參數optional_controls規格null
參數content_type規格application/json

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot 嵌入向量POST /v1/embeddings
輸入
US$0.0001 / 1K

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · 嵌入向量

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nemotron-embed-vl-latest", "input": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]=[text]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))\nPY_RESULT\n

接收並儲存結果

Ailoot · 嵌入向量

json

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。

需要檢查原始回應時

此流程未引入嵌入向量任務端點。

回應欄位
欄位類型
欄位data[].index類型integer
欄位data[].embedding類型finite float[]|base64 float32 vector
欄位model類型string
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot nvidia/llama-nemotron-embed-vl-1b-v2, nemotron-embed-vl, nemotron-embed-vl-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

nvidia/llama-nemotron-embed-vl-1b-v2, nemotron-embed-vl, nemotron-embed-vl-latest

", "method_identity": { "effective_request_model_id": "nemotron-embed-vl-latest", "fmt": "embeddings", "http": "POST", "path": "/v1/embeddings", "request_model_id": "nemotron-embed-vl-latest", "route_label": "Core" }, "method_key": "Core|embeddings|/v1/embeddings|nemotron-embed-vl-latest", "ordinal": 2, "rawMethod": { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Decode base64 vectors only when that format was requested; retain every vector and its original index.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "此流程未引入嵌入向量任務端點。" }, "material_combinations": [ { "alternatives": [ "nonempty string", "nonempty string[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。", "family": "embedding", "fields": [ { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]|base64 float32 vector" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "nemotron-embed-vl-latest" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "conditions": "每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]" }, { "availability": "source_interface", "default": "query", "default_known": true, "enum": [ "query", "passage" ], "enum_known": true, "name": "input_type", "required": false, "type": "string" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float", "base64" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "NONE", "START", "END" ], "enum_known": true, "name": "truncate", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "image objects", "data URI text inputs", "token integer arrays on this NVIDIA adapter" ] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": null, "required": [ "model", "input" ] }, "lifecycle": { "mode": "exact retained published method" }, "method": { "http": "POST", "path": "/v1/embeddings" }, "operation_modes": [ "embeddings" ], "output": { "family": [ "embedding" ], "format": "indexed vectors JSON", "multioutputs": "retain every actual response output" } }, "ctx": 4096, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-embed-vl-latest\", \"input\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=[text]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "Embed your source material", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "embeddings", "http": "POST", "img_in": null, "img_out": null, "in": 0.1, "input": [ "text" ], "label": "嵌入向量", "max_out": 0, "max_tool_calls": null, "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.1, "amount_unit": "usd_per_million_tokens", "key": "in", "label": "Input", "side": "in" }, { "amount": 0, "amount_unit": "usd_per_million_tokens", "key": "out", "label": "Output", "side": "out" } ] } ], "request_model_id": "nemotron-embed-vl-latest", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } } ], "model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "nativeProvenance": { "input_facts_canonical_sha256": "ee5d580bd0d6ec1833c9ed32f551db5b6bb648fa146a4488f9effed164dd8094", "input_html_sha256": "7d404235a00c0c432397b13cc7b18cb5bea0a94a982289ba5da8b9e3c5bf046b", "private_audit_sha256": "88d1341fca50c48d9436617a2e3fe73d4f918783effc00c49500697bb254d029", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/zh-hant-tw/nvidia-llama-nemotron-embed-vl-1b-v2/", "description": "Llama Nemotron Embed VL v2 為文件語意搜尋建立向量。Ailoot 目前目錄提供查詢與資料的文字輸入。", "locale": "zh-hant-tw", "md_url": "https://ailoot.ai/models/zh-hant-tw/nvidia-llama-nemotron-embed-vl-1b-v2/index.md", "title": "Llama Nemotron Embed VL 1B v2 — Ailoot", "url": "https://ailoot.ai/models/zh-hant-tw/nvidia-llama-nemotron-embed-vl-1b-v2/" }, "rawModel": { "about": "### 依問題找到需要的頁面\n\nLlama Nemotron Embed VL 1B v2 由 NVIDIA 開發，用於搜尋可協助回答問題的資料。查詢以文字設定；Ailoot 目前目錄為模型提供文字輸入，問題與資料皆以文字編碼。廠商也描述了以頁面影像，或影像搭配擷取文字表示文件的方式。這些視覺形式需要獨立且支援影像的方法。在相應輸入下，模型可將表格、圖表與資訊圖表表示於共同向量空間。\n\n這種搜尋適合大型文件集的問答助理、內部參考資料與研究文件。編碼結果為數值向量；找到的頁面或片段，可再交給生成答案的模型。Embed VL 本身完成的是上下文搜尋階段。\n\n### 廠商提供的文件形式\n\n- 文字文件：獨立章節、片段，或已辨識的頁面文字。\n- 影像：包含文字、表格與圖像元素的完整頁面。\n- 影像搭配文字：頁面的視覺外觀與文字內容，結合成同一表示形式。\n\n查詢與文件分別編碼，因此可預先處理文件集，將向量與原始頁面一起儲存，新問題出現時只計算查詢向量。向量相似度協助依語意選擇資料。查詢與文件的文字角色不同，準備資料時必須保留這個區別。\n\n### 表示大小與輸入長度\n\n每項輸入轉換成一個最多包含 2048 個數值的向量。文字模式使用 8192 個 token 的預算。廠商結合影像與文字的視覺方法，描述了兩者共用的 10240 個 token 預算，這不是 Ailoot 方法的文字上限。影像會分成片段；所述設定最多提供六個片段及整頁的縮小副本，合計約 1792 個視覺 token。長文字必須分段或縮短。\n\n語言部分以 Llama 3.2 1B 為基礎，視覺部分使用 SigLIP2，兩者結合為編碼器，將輸入 token 的表示取平均後輸出單一向量。對比訓練讓問題更接近合適頁面，並遠離不相關資料。搜尋仍具機率性，向量接近不保證所選片段包含正確答案。", "alias_of": null, "aliases": [ "nemotron-embed-vl", "nemotron-embed-vl-latest" ], "author": "NVIDIA", "ctx": 4096, "display_name": "Llama Nemotron Embed VL 1B v2", "formats": [ "embeddings" ], "id": "nvidia/llama-nemotron-embed-vl-1b-v2", "input": [ "text" ], "kind": "embedding", "max_out": null, "methods": [ { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Decode base64 vectors only when that format was requested; retain every vector and its original index.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "此流程未引入嵌入向量任務端點。" }, "material_combinations": [ { "alternatives": [ "nonempty string", "nonempty string[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。", "family": "embedding", "fields": [ { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]|base64 float32 vector" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "nvidia/llama-nemotron-embed-vl-1b-v2" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "conditions": "每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]" }, { "availability": "source_interface", "default": "query", "default_known": true, "enum": [ "query", "passage" ], "enum_known": true, "name": "input_type", "required": false, "type": "string" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float", "base64" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "NONE", "START", "END" ], "enum_known": true, "name": "truncate", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "image objects", "data URI text inputs", "token integer arrays on this NVIDIA adapter" ] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": null, "required": [ "model", "input" ] }, "lifecycle": { "mode": "exact retained published method" }, "method": { "http": "POST", "path": "/v1/embeddings" }, "operation_modes": [ "embeddings" ], "output": { "family": [ "embedding" ], "format": "indexed vectors JSON", "multioutputs": "retain every actual response output" } }, "ctx": 4096, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/llama-nemotron-embed-vl-1b-v2\", \"input\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=[text]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "Embed your source material", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "embeddings", "http": "POST", "img_in": null, "img_out": null, "in": 0.1, "input": [ "text" ], "label": "嵌入向量", "max_out": 0, "max_tool_calls": null, "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.1, "amount_unit": "usd_per_million_tokens", "key": "in", "label": "Input", "side": "in" }, { "amount": 0, "amount_unit": "usd_per_million_tokens", "key": "out", "label": "Output", "side": "out" } ] } ], "request_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] }, { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Decode base64 vectors only when that format was requested; retain every vector and its original index.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "此流程未引入嵌入向量任務端點。" }, "material_combinations": [ { "alternatives": [ "nonempty string", "nonempty string[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。", "family": "embedding", "fields": [ { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]|base64 float32 vector" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "nemotron-embed-vl" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "conditions": "每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]" }, { "availability": "source_interface", "default": "query", "default_known": true, "enum": [ "query", "passage" ], "enum_known": true, "name": "input_type", "required": false, "type": "string" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float", "base64" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "NONE", "START", "END" ], "enum_known": true, "name": "truncate", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "image objects", "data URI text inputs", "token integer arrays on this NVIDIA adapter" ] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": null, "required": [ "model", "input" ] }, "lifecycle": { "mode": "exact retained published method" }, "method": { "http": "POST", "path": "/v1/embeddings" }, "operation_modes": [ "embeddings" ], "output": { "family": [ "embedding" ], "format": "indexed vectors JSON", "multioutputs": "retain every actual response output" } }, "ctx": 4096, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-embed-vl\", \"input\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=[text]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "Embed your source material", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "embeddings", "http": "POST", "img_in": null, "img_out": null, "in": 0.1, "input": [ "text" ], "label": "嵌入向量", "max_out": 0, "max_tool_calls": null, "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.1, "amount_unit": "usd_per_million_tokens", "key": "in", "label": "Input", "side": "in" }, { "amount": 0, "amount_unit": "usd_per_million_tokens", "key": "out", "label": "Output", "side": "out" } ] } ], "request_model_id": "nemotron-embed-vl", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] }, { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Decode base64 vectors only when that format was requested; retain every vector and its original index.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "此流程未引入嵌入向量任務端點。" }, "material_combinations": [ { "alternatives": [ "nonempty string", "nonempty string[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "僅在請求該格式時才解碼 base64 向量；請保留每個向量及其原始索引。", "family": "embedding", "fields": [ { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]|base64 float32 vector" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "nemotron-embed-vl-latest" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "conditions": "每個字串去除前後空白後都不得為空；不接受 data URI；已接受的額度會計量相關的 UTF8 位元組。", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]" }, { "availability": "source_interface", "default": "query", "default_known": true, "enum": [ "query", "passage" ], "enum_known": true, "name": "input_type", "required": false, "type": "string" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float", "base64" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "NONE", "START", "END" ], "enum_known": true, "name": "truncate", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "image objects", "data URI text inputs", "token integer arrays on this NVIDIA adapter" ] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": null, "required": [ "model", "input" ] }, "lifecycle": { "mode": "exact retained published method" }, "method": { "http": "POST", "path": "/v1/embeddings" }, "operation_modes": [ "embeddings" ], "output": { "family": [ "embedding" ], "format": "indexed vectors JSON", "multioutputs": "retain every actual response output" } }, "ctx": 4096, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-embed-vl-latest\", \"input\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=[text]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "Embed your source material", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "embeddings", "http": "POST", "img_in": null, "img_out": null, "in": 0.1, "input": [ "text" ], "label": "嵌入向量", "max_out": 0, "max_tool_calls": null, "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.1, "amount_unit": "usd_per_million_tokens", "key": "in", "label": "Input", "side": "in" }, { "amount": 0, "amount_unit": "usd_per_million_tokens", "key": "out", "label": "Output", "side": "out" } ] } ], "request_model_id": "nemotron-embed-vl-latest", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } ], "model_aliases": [ { "canonical_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "request_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "route_label": "Core" }, { "canonical_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "request_model_id": "nemotron-embed-vl", "route_label": "Core" }, { "canonical_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "request_model_id": "nemotron-embed-vl-latest", "route_label": "Core" } ], "name": "nvidia/llama-nemotron-embed-vl-1b-v2", "price": { "in": 0.1, "in_label": null, "out": null, "out_label": null, "sort_in": 0.1, "sort_out": null, "varies": false }, "short": "Llama Nemotron Embed VL v2 為文件語意搜尋建立向量。Ailoot 目前目錄提供查詢與資料的文字輸入。" }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 }, { "contract_json_pointer": "/methods/1/rawMethod/contract", "html_json_pointer": "/methods/1/html", "method_ordinal": 1 }, { "contract_json_pointer": "/methods/2/rawMethod/contract", "html_json_pointer": "/methods/2/html", "method_ordinal": 2 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod", "/methods/1/rawMethod", "/methods/2/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Llama Nemotron Embed VL v2 為文件語意搜尋建立向量。Ailoot 目前目錄提供查詢與資料的文字輸入。", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "d07ea3e9c8a0849ba60a21e8a908f58bc695b9e93d7f6a55ec21aa4e751aa977", "renderer_sha256": "13a3fc1b22d07359278e2249d630bfc9bb9e6416c71ba53def933fb5a903660b" }, "sourceRevision": "6fa4be5758080a4893e38e556305f51dcef0729bc978f2407a45adcd60204a0e" }