vectorvein 0.3.18__tar.gz → 0.3.20__tar.gz

{vectorvein-0.3.18 → vectorvein-0.3.20}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectorvein
-Version: 0.3.18
+Version: 0.3.20
 Summary: VectorVein Python SDK
 Author-Email: Anderson <andersonby@163.com>
 License: MIT

{vectorvein-0.3.18 → vectorvein-0.3.20}/pyproject.toml

@@ -17,7 +17,7 @@ description = "VectorVein Python SDK"
 name = "vectorvein"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "0.3.18"
+version = "0.3.20"
 
 [project.license]
 text = "MIT"

{vectorvein-0.3.18 → vectorvein-0.3.20}/src/vectorvein/chat_clients/utils.py

@@ -158,7 +158,19 @@ def get_token_counts(text: str | dict, model: str = "", use_token_server_first:
             ],
         }
 
-        _, response = Retry(httpx.post).args(url=tokenize_url, headers=headers, json=request_body, timeout=None).retry_times(5).sleep_time(10).run()
+        _, response = (
+            Retry(httpx.post)
+            .args(
+                url=tokenize_url,
+                headers=headers,
+                json=request_body,
+                timeout=None,
+                proxy=endpoint.proxy,
+            )
+            .retry_times(5)
+            .sleep_time(10)
+            .run()
+        )
         if response is None:
             return 1000
         result = response.json()
@@ -178,7 +190,19 @@ def get_token_counts(text: str | dict, model: str = "", use_token_server_first:
                 {"role": "user", "content": text},
             ],
         }
-        _, response = Retry(httpx.post).args(url=tokenize_url, headers=headers, json=request_body, timeout=None).retry_times(5).sleep_time(10).run()
+        _, response = (
+            Retry(httpx.post)
+            .args(
+                url=tokenize_url,
+                headers=headers,
+                json=request_body,
+                timeout=None,
+                proxy=endpoint.proxy,
+            )
+            .retry_times(5)
+            .sleep_time(10)
+            .run()
+        )
         if response is None:
             return 1000
         result = response.json()
@@ -202,7 +226,19 @@ def get_token_counts(text: str | dict, model: str = "", use_token_server_first:
                 ],
             },
         }
-        _, response = Retry(httpx.post).args(base_url, json=request_body, params=params, timeout=None).retry_times(5).sleep_time(10).run()
+        _, response = (
+            Retry(httpx.post)
+            .args(
+                base_url,
+                json=request_body,
+                params=params,
+                timeout=None,
+                proxy=endpoint.proxy,
+            )
+            .retry_times(5)
+            .sleep_time(10)
+            .run()
+        )
         if response is None:
             return 1000
         result = response.json()
@@ -226,10 +262,12 @@ def get_token_counts(text: str | dict, model: str = "", use_token_server_first:
                 if endpoint.is_vertex or endpoint.is_bedrock or endpoint.endpoint_type == "anthropic_vertex" or endpoint.endpoint_type == "anthropic_bedrock":
                     continue
                 elif endpoint.endpoint_type in ("default", "anthropic"):
+                    http_client = httpx.Client(proxy=endpoint.proxy)
                     return (
                         Anthropic(
                             api_key=endpoint.api_key,
                             base_url=endpoint.api_base,
+                            http_client=http_client,
                         )
                         .beta.messages.count_tokens(messages=[{"role": "user", "content": text}], model=model)
                         .input_tokens
@@ -264,7 +302,19 @@ def get_token_counts(text: str | dict, model: str = "", use_token_server_first:
                 {"role": "user", "content": text},
             ],
         }
-        _, response = Retry(httpx.post).args(url=tokenize_url, headers=headers, json=request_body, timeout=None).retry_times(5).sleep_time(10).run()
+        _, response = (
+            Retry(httpx.post)
+            .args(
+                url=tokenize_url,
+                headers=headers,
+                json=request_body,
+                timeout=None,
+                proxy=endpoint.proxy,
+            )
+            .retry_times(5)
+            .sleep_time(10)
+            .run()
+        )
         if response is None:
             return 1000
         result = response.json()
@@ -286,7 +336,19 @@ def get_token_counts(text: str | dict, model: str = "", use_token_server_first:
                 {"role": "user", "content": text},
             ],
         }
-        _, response = Retry(httpx.post).args(url=tokenize_url, headers=headers, json=request_body, timeout=None).retry_times(5).sleep_time(10).run()
+        _, response = (
+            Retry(httpx.post)
+            .args(
+                url=tokenize_url,
+                headers=headers,
+                json=request_body,
+                timeout=None,
+                proxy=endpoint.proxy,
+            )
+            .retry_times(5)
+            .sleep_time(10)
+            .run()
+        )
         if response is None:
             return 1000
         result = response.json()

{vectorvein-0.3.18 → vectorvein-0.3.20}/src/vectorvein/types/defaults.py

@@ -658,6 +658,14 @@ ZHIPUAI_MODELS: Final[dict[str, ModelSettingDict]] = {
         "max_output_tokens": 96000,
         "native_multimodal": False,
     },
+    "glm-4.5v": {
+        "id": "glm-4.5v",
+        "context_length": 64000,
+        "function_call_available": True,
+        "response_format_available": True,
+        "max_output_tokens": 16384,
+        "native_multimodal": True,
+    },
 }
 
 # Mistral models