text-embedding-ada-002 is OpenAI’s text-embedding model for representing written material as a numerical vector. Its output contains 1,536 components. The maker combines text similarity, document/query search and code-search roles in one representation. The result is data for comparison or another algorithm, rather than a generated answer to the text being embedded.
For semantic search, prepare meaningful document passages and retain their source identifiers. An illustrative workflow embeds each passage and the user’s question with the same model, compares the vectors and returns the relevant source passages. The application determines the retrieval rule, filters and presentation. A subsequent text-generation step can use the retrieved material to develop an answer, while the embedding model supplies the numerical representation.
Other documented uses include grouping similar records, recommending related content, classifying text and identifying outliers. For a recommendation, compare descriptions of the objects whose relationship matters. For classification, the guide describes comparison with category representations or using vectors as features in a classifier. For anomaly detection, the relevant result is a record that differs from the surrounding collection, interpreted according to the product’s task.
OpenAI lists an 8,192-token maximum input for this model. The producer’s embedding API accepts text strings or tokenized input, permits multiple inputs in one request and rejects empty strings. Its aggregate limit is 300,000 tokens across a single request, in addition to the per-input limit. Split longer documents into useful passages while preserving titles, definitions and the reference back to the original material.
The output is a vector of floating-point values; the producer also documents base64 as an alternative transport encoding. OpenAI’s dimension-shortening parameter is for third-generation embedding models and later, so the Ada model’s documented 1,536-dimensional result is kept distinct from that control. Store the model identity and vector with the source record so later comparisons use a consistent representation.
The embedding guide recommends cosine similarity and states that OpenAI embeddings are normalized to unit length. For those vectors, a dot product can compute cosine similarity and Euclidean distance gives the same ranking. A similarity score is part of the application’s retrieval or classification logic, not a categorical decision supplied automatically by the model.
Define which source fields become the input text and how passages should be divided. An illustrative result is a ranked set of document passages or related records, each connected to its original source and the rule used for selection. Keep the preparation consistent and evaluate whether the returned material addresses the actual question. This makes the numerical output useful to the next search, recommendation or analysis step.
", "aboutText": "text-embedding-ada-002 is OpenAI’s text-embedding model for representing written material as a numerical vector. Its output contains 1,536 components. The maker combines text similarity, document/query search and code-search roles in one representation. The result is data for comparison or another algorithm, rather than a generated answer to the text being embedded.\n\nFor semantic search, prepare meaningful document passages and retain their source identifiers. An illustrative workflow embeds each passage and the user’s question with the same model, compares the vectors and returns the relevant source passages. The application determines the retrieval rule, filters and presentation. A subsequent text-generation step can use the retrieved material to develop an answer, while the embedding model supplies the numerical representation.\n\nOther documented uses include grouping similar records, recommending related content, classifying text and identifying outliers. For a recommendation, compare descriptions of the objects whose relationship matters. For classification, the guide describes comparison with category representations or using vectors as features in a classifier. For anomaly detection, the relevant result is a record that differs from the surrounding collection, interpreted according to the product’s task.\n\nOpenAI lists an 8,192-token maximum input for this model. The producer’s embedding API accepts text strings or tokenized input, permits multiple inputs in one request and rejects empty strings. Its aggregate limit is 300,000 tokens across a single request, in addition to the per-input limit. Split longer documents into useful passages while preserving titles, definitions and the reference back to the original material.\n\nThe output is a vector of floating-point values; the producer also documents base64 as an alternative transport encoding. OpenAI’s dimension-shortening parameter is for third-generation embedding models and later, so the Ada model’s documented 1,536-dimensional result is kept distinct from that control. Store the model identity and vector with the source record so later comparisons use a consistent representation.\n\nThe embedding guide recommends cosine similarity and states that OpenAI embeddings are normalized to unit length. For those vectors, a dot product can compute cosine similarity and Euclidean distance gives the same ranking. A similarity score is part of the application’s retrieval or classification logic, not a categorical decision supplied automatically by the model.\n\nDefine which source fields become the input text and how passages should be divided. An illustrative result is a ranked set of document passages or related records, each connected to its original source and the rule used for selection. Keep the preparation consistent and evaluate whether the returned material addresses the actual question. This makes the numerical output useful to the next search, recommendation or analysis step.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "adcaf00067c0b5103e797e9c3541b74fdb964e6da086fd958cb316ec5faf347d", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/text-embedding-ada-002An OpenAI text-embedding model that returns a 1,536-dimensional numerical vector. Use those representations for semantic search, related-content recommendations, clustering, classification or detecting unusual text records.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
text-embedding-ada-002 is OpenAI’s text-embedding model for representing written material as a numerical vector. Its output contains 1,536 components. The maker combines text similarity, document/query search and code-search roles in one representation. The result is data for comparison or another algorithm, rather than a generated answer to the text being embedded.
For semantic search, prepare meaningful document passages and retain their source identifiers. An illustrative workflow embeds each passage and the user’s question with the same model, compares the vectors and returns the relevant source passages. The application determines the retrieval rule, filters and presentation. A subsequent text-generation step can use the retrieved material to develop an answer, while the embedding model supplies the numerical representation.
Other documented uses include grouping similar records, recommending related content, classifying text and identifying outliers. For a recommendation, compare descriptions of the objects whose relationship matters. For classification, the guide describes comparison with category representations or using vectors as features in a classifier. For anomaly detection, the relevant result is a record that differs from the surrounding collection, interpreted according to the product’s task.
OpenAI lists an 8,192-token maximum input for this model. The producer’s embedding API accepts text strings or tokenized input, permits multiple inputs in one request and rejects empty strings. Its aggregate limit is 300,000 tokens across a single request, in addition to the per-input limit. Split longer documents into useful passages while preserving titles, definitions and the reference back to the original material.
The output is a vector of floating-point values; the producer also documents base64 as an alternative transport encoding. OpenAI’s dimension-shortening parameter is for third-generation embedding models and later, so the Ada model’s documented 1,536-dimensional result is kept distinct from that control. Store the model identity and vector with the source record so later comparisons use a consistent representation.
The embedding guide recommends cosine similarity and states that OpenAI embeddings are normalized to unit length. For those vectors, a dot product can compute cosine similarity and Euclidean distance gives the same ranking. A similarity score is part of the application’s retrieval or classification logic, not a categorical decision supplied automatically by the model.
Define which source fields become the input text and how passages should be divided. An illustrative result is a ranked set of document passages or related records, each connected to its original source and the rule used for selection. Keep the preparation consistent and evaluate whether the returned material addresses the actual question. This makes the numerical output useful to the next search, recommendation or analysis step.
POST /v1/embeddingstext, token_idsembedding| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/text-embedding-ada-002 | Default— |
Fieldinput | Typestring|string[]|integer[]|integer[][] | RequirementRequired | Values & limits Minimum items: 1 Conditions: Nonempty homogeneous batch. Token IDs are nonnegative integers. Input budget: Maximum: 8,192 · Text unit: UTF8 bytes · Token unit: token-array elements | Default— |
Fieldencoding_format | Typestring | RequirementOptional | Values & limits float | Defaultfloat |
Fielddimensions | Typeinteger | RequirementNot supported | Values & limits Minimum: 1 | Default— |
Fielduser | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldsession_id | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldtrace | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options rejected | Default— |
text_to_embedding
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input |
Parameterinput_shapes | Contractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[] |
Parameterencoding_format | Contractfloat |
Parameterdimensions_override | Contractfalse |
Parametermax_input_budget_units | Contract8192 |
Parametermultimodal_objects | Contractfalse |
Parametermaterial_types | Contracttext, token_ids |
Lifecycle: synchronous_json
Keep every vector index and dimension.
Multimodal model name does not admit image objects on this exact path.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "openai/text-embedding-ada-002", "input": ["First document", "Second document"]}')\n\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\nfrom openai import OpenAI\nimport os\n\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.embeddings.create(model='openai/text-embedding-ada-002',input=["First document","Second document"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\njson
Keep every complete returned response, file and content part.
Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.
No embedding job endpoint is introduced.
| Field | Type |
|---|---|
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fielddata[].index | Typeinteger |
Fielddata[].embedding | Typefinite float[] |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra openai/text-embedding-ada-002, text-embedding-ada-002
Use the method paths shown above.
text-embedding-ada-002An OpenAI text-embedding model that returns a 1,536-dimensional numerical vector. Use those representations for semantic search, related-content recommendations, clustering, classification or detecting unusual text records.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
text-embedding-ada-002 is OpenAI’s text-embedding model for representing written material as a numerical vector. Its output contains 1,536 components. The maker combines text similarity, document/query search and code-search roles in one representation. The result is data for comparison or another algorithm, rather than a generated answer to the text being embedded.
For semantic search, prepare meaningful document passages and retain their source identifiers. An illustrative workflow embeds each passage and the user’s question with the same model, compares the vectors and returns the relevant source passages. The application determines the retrieval rule, filters and presentation. A subsequent text-generation step can use the retrieved material to develop an answer, while the embedding model supplies the numerical representation.
Other documented uses include grouping similar records, recommending related content, classifying text and identifying outliers. For a recommendation, compare descriptions of the objects whose relationship matters. For classification, the guide describes comparison with category representations or using vectors as features in a classifier. For anomaly detection, the relevant result is a record that differs from the surrounding collection, interpreted according to the product’s task.
OpenAI lists an 8,192-token maximum input for this model. The producer’s embedding API accepts text strings or tokenized input, permits multiple inputs in one request and rejects empty strings. Its aggregate limit is 300,000 tokens across a single request, in addition to the per-input limit. Split longer documents into useful passages while preserving titles, definitions and the reference back to the original material.
The output is a vector of floating-point values; the producer also documents base64 as an alternative transport encoding. OpenAI’s dimension-shortening parameter is for third-generation embedding models and later, so the Ada model’s documented 1,536-dimensional result is kept distinct from that control. Store the model identity and vector with the source record so later comparisons use a consistent representation.
The embedding guide recommends cosine similarity and states that OpenAI embeddings are normalized to unit length. For those vectors, a dot product can compute cosine similarity and Euclidean distance gives the same ranking. A similarity score is part of the application’s retrieval or classification logic, not a categorical decision supplied automatically by the model.
Define which source fields become the input text and how passages should be divided. An illustrative result is a ranked set of document passages or related records, each connected to its original source and the rule used for selection. Keep the preparation consistent and evaluate whether the returned material addresses the actual question. This makes the numerical output useful to the next search, recommendation or analysis step.
POST /v1/embeddingstextembedding| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits text-embedding-ada-002 | Default— |
Fieldinput | Typestring|string[]|integer[]|integer[][] | RequirementRequired | Values & limits Minimum items: 1 Conditions: Nonempty homogeneous batch. Token IDs are nonnegative integers. Input budget: Maximum: 8,192 · Text unit: UTF8 bytes · Token unit: token-array elements | Default— |
Fieldencoding_format | Typestring | RequirementOptional | Values & limits float | Defaultfloat |
Fielddimensions | Typeinteger | RequirementNot supported | Values & limits Minimum: 1 | Default— |
Fielduser | Typejson_value | RequirementOptional | Values & limits Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model. | Default— |
Fieldsession_id | Typejson_value | RequirementOptional | Values & limits Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model. | Default— |
Fieldtrace | Typejson_value | RequirementOptional | Values & limits Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model. | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options rejected | Default— |
text_to_embedding
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input |
Parameterinput_shapes | Contractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[] |
Parameterencoding_format | Contractfloat |
Parameterdimensions_override | Contractfalse |
Parametermax_input_budget_units | Contract8192 |
Parametermultimodal_objects | Contractfalse |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_json
Send the exact model ID and required fields.
Keep every returned item and its original identifiers.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "text-embedding-ada-002",\n "input": [\n "First document",\n "Second document"\n ],\n "encoding_format": "float"\n}set -eu\n: "${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\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'text-embedding-ada-002', 'input': ['First document', 'Second document'], 'encoding_format': 'float'}\npayload['input'] = [text]\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\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\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nfor vector in result.get('data', []):\n print('Vector', vector.get('index'), json.dumps(vector.get('embedding')))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'text-embedding-ada-002', 'input': ['First document', 'Second document'], 'encoding_format': 'float'}\npayload['input'] = [text]\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'Authorization': 'Bearer PLACEHOLDER_KEY', 'Content-Type': 'application/json'}\nheaders['Authorization'] = 'Bearer ' + api_key\nrequest = Request('https://api.ailoot.ai/v1/embeddings', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nfor vector in result.get('data', []):\n print('Vector', vector.get('index'), json.dumps(vector.get('embedding')))\njson
Keep every complete returned response, file and content part.
Keep every finite vector with its original index. Preserve all dimensions and the complete usage object.
No embedding job endpoint is introduced.
| Field | Type |
|---|---|
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fielddata[].index | Typeinteger |
Fielddata[].embedding | Typefinite float[] |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra openai/text-embedding-ada-002, text-embedding-ada-002
Use the method paths shown above.