tccli-intl-en 3.0.1282.1__py2.py3-none-any.whl → 3.1.33.1__py2.py3-none-any.whl

tccli/services/lkeap/lkeap_client.py

@@ -42,7 +42,7 @@ def doCreateReconstructDocumentFlow(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -97,7 +97,7 @@ def doGetSplitDocumentResult(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -152,7 +152,7 @@ def doCreateSplitDocumentFlow(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -207,7 +207,7 @@ def doReconstructDocumentSSE(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -262,7 +262,7 @@ def doRunRerank(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -317,7 +317,7 @@ def doGetReconstructDocumentResult(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -372,7 +372,7 @@ def doQueryRewrite(args, parsed_globals):
         endpoint=g_param[OptionsDefine.Endpoint],
         proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
     )
-    profile = ClientProfile(httpProfile=http_profile, signMethod="HmacSHA256")
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
     if g_param[OptionsDefine.Language]:
         profile.language = g_param[OptionsDefine.Language]
     mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
@@ -402,6 +402,61 @@ def doQueryRewrite(args, parsed_globals):
     FormatOutput.output("action", json_obj, g_param[OptionsDefine.Output], g_param[OptionsDefine.Filter])
 
 
+def doGetEmbedding(args, parsed_globals):
+    g_param = parse_global_arg(parsed_globals)
+
+    if g_param[OptionsDefine.UseCVMRole.replace('-', '_')]:
+        cred = credential.CVMRoleCredential()
+    elif g_param[OptionsDefine.RoleArn.replace('-', '_')] and g_param[OptionsDefine.RoleSessionName.replace('-', '_')]:
+        cred = credential.STSAssumeRoleCredential(
+            g_param[OptionsDefine.SecretId], g_param[OptionsDefine.SecretKey], g_param[OptionsDefine.RoleArn.replace('-', '_')],
+            g_param[OptionsDefine.RoleSessionName.replace('-', '_')], endpoint=g_param["sts_cred_endpoint"]
+        )
+    elif os.getenv(OptionsDefine.ENV_TKE_REGION) \
+            and os.getenv(OptionsDefine.ENV_TKE_PROVIDER_ID) \
+            and os.getenv(OptionsDefine.ENV_TKE_WEB_IDENTITY_TOKEN_FILE) \
+            and os.getenv(OptionsDefine.ENV_TKE_ROLE_ARN):
+        cred = credential.DefaultTkeOIDCRoleArnProvider().get_credentials()
+    else:
+        cred = credential.Credential(
+            g_param[OptionsDefine.SecretId], g_param[OptionsDefine.SecretKey], g_param[OptionsDefine.Token]
+        )
+    http_profile = HttpProfile(
+        reqTimeout=60 if g_param[OptionsDefine.Timeout] is None else int(g_param[OptionsDefine.Timeout]),
+        reqMethod="POST",
+        endpoint=g_param[OptionsDefine.Endpoint],
+        proxy=g_param[OptionsDefine.HttpsProxy.replace('-', '_')]
+    )
+    profile = ClientProfile(httpProfile=http_profile, signMethod="TC3-HMAC-SHA256")
+    if g_param[OptionsDefine.Language]:
+        profile.language = g_param[OptionsDefine.Language]
+    mod = CLIENT_MAP[g_param[OptionsDefine.Version]]
+    client = mod.LkeapClient(cred, g_param[OptionsDefine.Region], profile)
+    client._sdkVersion += ("_CLI_" + __version__)
+    models = MODELS_MAP[g_param[OptionsDefine.Version]]
+    model = models.GetEmbeddingRequest()
+    model.from_json_string(json.dumps(args))
+    start_time = time.time()
+    while True:
+        rsp = client.GetEmbedding(model)
+        result = rsp.to_json_string()
+        try:
+            json_obj = json.loads(result)
+        except TypeError as e:
+            json_obj = json.loads(result.decode('utf-8'))  # python3.3
+        if not g_param[OptionsDefine.Waiter] or search(g_param['OptionsDefine.WaiterInfo']['expr'], json_obj) == g_param['OptionsDefine.WaiterInfo']['to']:
+            break
+        cur_time = time.time()
+        if cur_time - start_time >= g_param['OptionsDefine.WaiterInfo']['timeout']:
+            raise ClientError('Request timeout, wait `%s` to `%s` timeout, last request is %s' %
+            (g_param['OptionsDefine.WaiterInfo']['expr'], g_param['OptionsDefine.WaiterInfo']['to'],
+            search(g_param['OptionsDefine.WaiterInfo']['expr'], json_obj)))
+        else:
+            print('Inquiry result is %s.' % search(g_param['OptionsDefine.WaiterInfo']['expr'], json_obj))
+        time.sleep(g_param['OptionsDefine.WaiterInfo']['interval'])
+    FormatOutput.output("action", json_obj, g_param[OptionsDefine.Output], g_param[OptionsDefine.Filter])
+
+
 CLIENT_MAP = {
     "v20240522": lkeap_client_v20240522,
 
@@ -420,6 +475,7 @@ ACTION_MAP = {
     "RunRerank": doRunRerank,
     "GetReconstructDocumentResult": doGetReconstructDocumentResult,
     "QueryRewrite": doQueryRewrite,
+    "GetEmbedding": doGetEmbedding,
 
 }
 

tccli/services/lkeap/v20240522/api.json

@@ -14,6 +14,13 @@
       "output": "CreateSplitDocumentFlowResponse",
       "status": "online"
     },
+    "GetEmbedding": {
+      "document": "This API is used to call the text representation model to convert text into a vector represented by numbers, which can be used in scenarios such as text retrieval, information recommendation, and knowledge mining. There is a single-account call limit control for this API. If you need to increase the concurrency limit, please contact us (https://cloud.tencent.com/act/event/Online_service).",
+      "input": "GetEmbeddingRequest",
+      "name": "Retrieve feature vector",
+      "output": "GetEmbeddingResponse",
+      "status": "online"
+    },
     "GetReconstructDocumentResult": {
       "document": "This is an asynchronous API for querying results, which is used to obtain the result of document parsing.",
       "input": "GetReconstructDocumentResultRequest",
@@ -331,6 +338,97 @@
       ],
       "usage": "out"
     },
+    "EmbeddingObject": {
+      "document": "Vector.",
+      "members": [
+        {
+          "disabled": false,
+          "document": "Vector.",
+          "example": "无",
+          "member": "float",
+          "name": "Embedding",
+          "output_required": false,
+          "required": false,
+          "type": "list",
+          "value_allowed_null": false
+        }
+      ],
+      "usage": "both"
+    },
+    "GetEmbeddingRequest": {
+      "document": "GetEmbedding request structure.",
+      "members": [
+        {
+          "disabled": false,
+          "document": "Select the model for generating vectors\nNote: Optional [adp-text-embedding-0.5b]\n\n",
+          "example": "lke-text-embedding-v1",
+          "member": "string",
+          "name": "Model",
+          "required": true,
+          "type": "string"
+        },
+        {
+          "disabled": false,
+          "document": "Text that requires embedding. The maximum length of a single text is 500 characters. The maximum total number of entries is 7.",
+          "example": "[\"hello\", \"world\"]",
+          "member": "string",
+          "name": "Inputs",
+          "required": true,
+          "type": "list"
+        },
+        {
+          "disabled": false,
+          "document": "The type of text vectorization. To achieve better retrieval performance, it is recommended to distinguish between query text and document text types. For symmetric tasks such as clustering and classification, there is no need for special specification simply use the system default value \"document\".",
+          "example": "document",
+          "member": "string",
+          "name": "TextType",
+          "required": false,
+          "type": "string"
+        },
+        {
+          "disabled": false,
+          "document": "This field is not currently supported.",
+          "example": "问题：",
+          "member": "string",
+          "name": "Instruction",
+          "required": false,
+          "type": "string"
+        }
+      ],
+      "type": "object"
+    },
+    "GetEmbeddingResponse": {
+      "document": "GetEmbedding response structure.",
+      "members": [
+        {
+          "disabled": false,
+          "document": "Feature.",
+          "example": "无",
+          "member": "EmbeddingObject",
+          "name": "Data",
+          "output_required": true,
+          "type": "list",
+          "value_allowed_null": false
+        },
+        {
+          "disabled": false,
+          "document": "Consumption. Returns TotalToken.",
+          "example": "无",
+          "member": "Usage",
+          "name": "Usage",
+          "output_required": false,
+          "type": "object",
+          "value_allowed_null": false
+        },
+        {
+          "document": "The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem.",
+          "member": "string",
+          "name": "RequestId",
+          "type": "string"
+        }
+      ],
+      "type": "object"
+    },
     "GetReconstructDocumentResultRequest": {
       "document": "GetReconstructDocumentResult request structure.",
       "members": [
@@ -611,6 +709,24 @@
     "ReconstructDocumentSSERequest": {
       "document": "ReconstructDocumentSSE request structure.",
       "members": [
+        {
+          "disabled": false,
+          "document": "File type.\n**Supported file types**: PDF, DOC, DOCX, PPT, PPTX, MD, TXT, XLS, XLSX, CSV, PNG, JPG, JPEG, BMP, GIF, WEBP, HEIC, EPS, ICNS, IM, PCX, PPM, TIFF, XBM, HEIF, JP2.\n**Supported file sizes**: \n- Max 100 MB for PDF, DOC, DOCX, PPT, and PPTX .\n- Max 10 MB for MD, TXT, XLS, XLSX, and CSV.\n- Max20 MB for others.",
+          "example": "PDF",
+          "member": "string",
+          "name": "FileType",
+          "required": true,
+          "type": "string"
+        },
+        {
+          "disabled": false,
+          "document": "File URL. It is recommended to store the file in Tencent Cloud as the URL where the file is stored in Tencent Cloud can ensure higher download speed and stability. External URL may affect the speed and stability. Refer to: [Tencent Cloud COS Documentation](https://www.tencentcloud.com/document/product/436/7749)",
+          "example": "url",
+          "member": "string",
+          "name": "FileUrl",
+          "required": false,
+          "type": "string"
+        },
         {
           "disabled": false,
           "document": "The base64 value of the file. File size limit: the downloaded file shall not exceed 8MB after base64 encoding. File download time does not exceed 3 seconds. Supported image pixels: the length of a single side is between 20-10000px. Either FileUrl or FileBase64 of the file must be provided. If both are provided, only the FileUrl is used.",
@@ -620,6 +736,24 @@
           "required": false,
           "type": "string"
         },
+        {
+          "disabled": false,
+          "document": "The starting page number of the file. When type of the uploaded file is pdf, doc, docx, ppt, or pptx, it specifies the starting page number for recognition, including the current value.",
+          "example": "1",
+          "member": "int64",
+          "name": "FileStartPageNumber",
+          "required": false,
+          "type": "int"
+        },
+        {
+          "disabled": false,
+          "document": "The end page number of the file. When type of the uploaded file is pdf, doc, docx, ppt, or pptx, it specifies the end page number for recognition, including the current value.",
+          "example": "100",
+          "member": "int64",
+          "name": "FileEndPageNumber",
+          "required": false,
+          "type": "int"
+        },
         {
           "disabled": false,
           "document": "Document parsing configuration information.\t",

tccli/services/lkeap/v20240522/examples.json

@@ -16,6 +16,26 @@
         "title": "PDF Splitting Task Creation"
       }
     ],
+    "GetEmbedding": [
+      {
+        "document": "",
+        "input": "POST / HTTP/1.1\nHost: lkeap.tencentcloudapi.com\nContent-Type: application/json\nX-TC-Action: GetEmbedding\n<Common request parameters>\n\n{\n    \"Model\": \"adp-text-embedding-0.5b\",\n    \"Inputs\": [\n        \"Hello.\"\n    ]\n}",
+        "output": "{\n    \"Response\": {\n        \"Data\": [\n            {\n                \"Embedding\": [\n                    0\n                ]\n            }\n        ],\n        \"RequestId\": \"3c140219-cfe9-470e-b241-907877d6fb03\",\n        \"Usage\": {\n            \"TotalTokens\": 3\n        }\n    }\n}",
+        "title": "Obtain The Embeddings"
+      },
+      {
+        "document": "",
+        "input": "POST / HTTP/1.1\nHost: lkeap.tencentcloudapi.com\nContent-Type: application/json\nX-TC-Action: GetEmbedding\n<Common request parameters>\n\n{\n    \"Model\": \"adp-text-embedding-0.5b\",\n    \"Inputs\": [\n        \"Hello\",\n        \"Word\"\n    ]\n}",
+        "output": "{\n    \"Response\": {\n        \"Data\": [\n            {\n                \"Embedding\": [\n                    0\n                ]\n            },\n            {\n                \"Embedding\": [\n                    0\n                ]\n            }\n        ],\n        \"RequestId\": \"3c140219-cfe9-470e-b241-907877d6fb03\",\n        \"Usage\": {\n            \"TotalTokens\": 3\n        }\n    }\n}",
+        "title": "Obtain The Embeddings1"
+      },
+      {
+        "document": "",
+        "input": "POST / HTTP/1.1\nHost: lkeap.tencentcloudapi.com\nContent-Type: application/json\nX-TC-Action: GetEmbedding\n<Common request parameters>\n\n{\n    \"Model\": \"adp-text-embedding-0.5b\",\n    \"Inputs\": [\n        \"Hello\",\n        \"Word\"\n    ]\n}",
+        "output": "{\n    \"Response\": {\n        \"Data\": [\n            {\n                \"Embedding\": [\n                    0\n                ]\n            },\n            {\n                \"Embedding\": [\n                    0\n                ]\n            }\n        ],\n        \"RequestId\": \"3c140219-cfe9-470e-b241-907877d6fb03\",\n        \"Usage\": {\n            \"TotalTokens\": 3\n        }\n    }\n}",
+        "title": "Obtain The Embeddings2"
+      }
+    ],
     "GetReconstructDocumentResult": [
       {
         "document": "",
@@ -69,4 +89,4 @@
       }
     ]
   }
-}
+}