langchain-dev-utils 1.2.5__tar.gz → 1.2.6__tar.gz

{langchain_dev_utils-1.2.5 → langchain_dev_utils-1.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langchain-dev-utils
-Version: 1.2.5
+Version: 1.2.6
 Summary: A practical utility library for LangChain and LangGraph development
 Project-URL: Source Code, https://github.com/TBice123123/langchain-dev-utils
 Project-URL: repository, https://github.com/TBice123123/langchain-dev-utils
@@ -157,6 +157,8 @@ For stream responses obtained using `stream()` and `astream()`, you can use `mer
 | `chunks` | List[AIMessageChunk] | Yes | - | List of AIMessageChunk objects |
 
 ```python
+from langchain_dev_utils.message_convert import merge_ai_message_chunk
+
 chunks = list(model.stream("Hello"))
 merged = merge_ai_message_chunk(chunks)
 ```
@@ -174,6 +176,7 @@ For a list, you can use `format_sequence` to format it.
 | `with_num` | bool | No | False | If True, add a numeric prefix to each item (e.g., "1. Hello") |
 
 ```python
+from langchain_dev_utils.message_convert import format_sequence
 text = format_sequence([
     "str1",
     "str2",
@@ -205,7 +208,7 @@ Includes the following features:
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
 | `message` | AIMessage | Yes | - | AIMessage object |
-| `first_tool_call_only` | bool | No | False | Whether to only check the first tool call |
+| `first_tool_call_only` | bool | No | False | Whether to only parse the first tool call |
 
 ```python
 import datetime
@@ -234,7 +237,7 @@ if has_tool_calling(response):
 Both can accept a `handler` parameter for custom breakpoint return and response handling logic.
 
 ```python
-from langchain_dev_utils import human_in_the_loop
+from langchain_dev_utils.tool_calling import human_in_the_loop
 from langchain_core.tools import tool
 import datetime
 
@@ -262,7 +265,7 @@ In LangChain v1, the officially provided `create_agent` function can be used to
 
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `model` | str \| BaseChatModel | Yes | - | Model name or model instance. Can be a string identifier for a model registered with `register_model_provider` or a BaseChatModel instance. |
+| `model` | str  | Yes | - | Model name or model instance. Can be a string identifier for a model registered with `register_model_provider` or a BaseChatModel instance. |
 | Other parameters | Various | No | - | All other parameters are the same as in `langchain.agents.create_agent` |
 
 Usage example:
@@ -317,7 +320,7 @@ Uses `create_sequential_pipeline`, supported parameters:
 
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `sub_graphs` | List[StateGraph] | Yes | - | List of state graphs to combine (must be StateGraph instances) |
+| `sub_graphs` | List[StateGraph\|CompiledStateGraph] | Yes | - | List of state graphs to combine (must be StateGraph instances or CompiledStateGraph instances) |
 | `state_schema` | type | Yes | - | State Schema for the final generated graph |
 | `graph_name` | str | No | - | Name of the final generated graph |
 | `context_schema` | type | No | - | Context Schema for the final generated graph |
@@ -378,7 +381,7 @@ Uses `create_parallel_pipeline`, supported parameters:
 
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `sub_graphs` | List[StateGraph] | Yes | - | List of state graphs to combine |
+| `sub_graphs` | List[StateGraph\|CompiledStateGraph] | Yes | - | List of state graphs to combine (must be StateGraph instances or CompiledStateGraph instances) |
 | `state_schema` | type | Yes | - | State Schema for the final generated graph |
 | `branches_fn` | Callable | Yes | - | Parallel branch function, returns a list of Send objects to control parallel execution |
 | `graph_name` | str | No | - | Name of the final generated graph |

{langchain_dev_utils-1.2.5 → langchain_dev_utils-1.2.6}/README.md

@@ -141,6 +141,8 @@ For stream responses obtained using `stream()` and `astream()`, you can use `mer
 | `chunks` | List[AIMessageChunk] | Yes | - | List of AIMessageChunk objects |
 
 ```python
+from langchain_dev_utils.message_convert import merge_ai_message_chunk
+
 chunks = list(model.stream("Hello"))
 merged = merge_ai_message_chunk(chunks)
 ```
@@ -158,6 +160,7 @@ For a list, you can use `format_sequence` to format it.
 | `with_num` | bool | No | False | If True, add a numeric prefix to each item (e.g., "1. Hello") |
 
 ```python
+from langchain_dev_utils.message_convert import format_sequence
 text = format_sequence([
     "str1",
     "str2",
@@ -189,7 +192,7 @@ Includes the following features:
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
 | `message` | AIMessage | Yes | - | AIMessage object |
-| `first_tool_call_only` | bool | No | False | Whether to only check the first tool call |
+| `first_tool_call_only` | bool | No | False | Whether to only parse the first tool call |
 
 ```python
 import datetime
@@ -218,7 +221,7 @@ if has_tool_calling(response):
 Both can accept a `handler` parameter for custom breakpoint return and response handling logic.
 
 ```python
-from langchain_dev_utils import human_in_the_loop
+from langchain_dev_utils.tool_calling import human_in_the_loop
 from langchain_core.tools import tool
 import datetime
 
@@ -246,7 +249,7 @@ In LangChain v1, the officially provided `create_agent` function can be used to
 
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `model` | str \| BaseChatModel | Yes | - | Model name or model instance. Can be a string identifier for a model registered with `register_model_provider` or a BaseChatModel instance. |
+| `model` | str  | Yes | - | Model name or model instance. Can be a string identifier for a model registered with `register_model_provider` or a BaseChatModel instance. |
 | Other parameters | Various | No | - | All other parameters are the same as in `langchain.agents.create_agent` |
 
 Usage example:
@@ -301,7 +304,7 @@ Uses `create_sequential_pipeline`, supported parameters:
 
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `sub_graphs` | List[StateGraph] | Yes | - | List of state graphs to combine (must be StateGraph instances) |
+| `sub_graphs` | List[StateGraph\|CompiledStateGraph] | Yes | - | List of state graphs to combine (must be StateGraph instances or CompiledStateGraph instances) |
 | `state_schema` | type | Yes | - | State Schema for the final generated graph |
 | `graph_name` | str | No | - | Name of the final generated graph |
 | `context_schema` | type | No | - | Context Schema for the final generated graph |
@@ -362,7 +365,7 @@ Uses `create_parallel_pipeline`, supported parameters:
 
 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `sub_graphs` | List[StateGraph] | Yes | - | List of state graphs to combine |
+| `sub_graphs` | List[StateGraph\|CompiledStateGraph] | Yes | - | List of state graphs to combine (must be StateGraph instances or CompiledStateGraph instances) |
 | `state_schema` | type | Yes | - | State Schema for the final generated graph |
 | `branches_fn` | Callable | Yes | - | Parallel branch function, returns a list of Send objects to control parallel execution |
 | `graph_name` | str | No | - | Name of the final generated graph |

{langchain_dev_utils-1.2.5 → langchain_dev_utils-1.2.6}/README_cn.md

@@ -141,6 +141,7 @@ print(emb)
 | `chunks` | List[AIMessageChunk] | 是 | - | AIMessageChunk 列表 |
 
 ```python
+from langchain_dev_utils.message_convert import merge_ai_message_chunk
 chunks = list(model.stream("Hello"))
 merged = merge_ai_message_chunk(chunks)
 ```
@@ -158,6 +159,7 @@ merged = merge_ai_message_chunk(chunks)
 | `with_num` | bool | 否 | False | 如果为 True，为每个项目添加数字前缀（例如 "1. 你好"） |
 
 ```python
+from langchain_dev_utils.message_convert import format_sequence
 text = format_sequence([
     "str1",
     "str2",
@@ -189,7 +191,7 @@ text = format_sequence([
 | 参数名 | 类型 | 必填 | 默认值 | 描述 |
 |--------|------|------|--------|------|
 | `message` | AIMessage | 是 | - | AIMessage 对象 |
-| `first_tool_call_only` | bool | 否 | False | 是否只检查第一个工具调用 |
+| `first_tool_call_only` | bool | 否 | False | 是否只解析第一个工具调用 |
 
 ```python
 import datetime
@@ -218,7 +220,7 @@ if has_tool_calling(response):
 其中都可以传递`handler`参数，用于自定义断点返回和响应处理逻辑。
 
 ```python
-from langchain_dev_utils import human_in_the_loop
+from langchain_dev_utils.tool_calling import human_in_the_loop
 from langchain_core.tools import tool
 import datetime
 
@@ -246,9 +248,9 @@ LangChain v1 版本中，官方提供的 `create_agent` 函数可以用于创建
 
 | 参数名 | 类型 | 必填 | 默认值 | 描述 |
 |--------|------|------|--------|------|
-| `model` | str \| BaseChatModel | 是 | - | 模型名称或模型实例 |
+| `model` | str  | 是 | - | 模型名称|
+| 其余参数 | Various | No | - | 其余参数与 `langchain.agents.create_agent` 函数相同|
 
-**其余参数与 `langchain.agents.create_agent` 函数相同。**
 
 使用示例：
 
@@ -302,7 +304,7 @@ print(response)
 
 | 参数名 | 类型 | 必填 | 默认值 | 描述 |
 |--------|------|------|--------|------|
-| `sub_graphs` | List[StateGraph] | 是 | - | 要组合的状态图列表（必须是 StateGraph 实例） |
+| `sub_graphs` | List[StateGraph\|CompiledStateGraph] | 是 | - | 要组合的状态图列表（必须是 StateGraph 实例 或 CompiledStateGraph 实例） |
 | `state_schema` | type | 是 | - | 最终生成图的 State Schema |
 | `graph_name` | str | 否 | - | 最终生成图的名称 |
 | `context_schema` | type | 否 | - | 最终生成图的 Context Schema |
@@ -363,7 +365,7 @@ print(response)
 
 | 参数名 | 类型 | 必填 | 默认值 | 描述 |
 |--------|------|------|--------|------|
-| `sub_graphs` | List[StateGraph] | 是 | - | 要组合的状态图列表 |
+| `sub_graphs` | List[StateGraph\|CompiledStateGraph] | 是 | - | 要组合的状态图列表（必须是 StateGraph 实例 或 CompiledStateGraph 实例） |
 | `state_schema` | type | 是 | - | 最终生成图的 State Schema |
 | `branches_fn` | Callable | 是 | - | 并行分支函数，返回 Send 对象列表控制并行执行 |
 | `graph_name` | str | 否 | - | 最终生成图的名称 |

{langchain_dev_utils-1.2.5 → langchain_dev_utils-1.2.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langchain-dev-utils"
-version = "1.2.5"
+version = "1.2.6"
 description = "A practical utility library for LangChain and LangGraph development"
 readme = "README.md"
 authors = [{ name = "tiebingice", email = "tiebingice123@outlook.com" }]

langchain_dev_utils-1.2.6/src/langchain_dev_utils/__init__.py

@@ -0,0 +1 @@
+__version__ = "1.2.6"

langchain_dev_utils-1.2.6/src/langchain_dev_utils/_utils.py

@@ -0,0 +1,39 @@
+from importlib import util
+
+from pydantic import BaseModel
+
+
+def _check_langchain_openai_install() -> None:
+    if not util.find_spec("langchain_openai"):
+        msg = (
+            "Please install langchain_dev_utils[standard],when use 'openai-compatible'"
+        )
+        raise ImportError(msg)
+
+
+def _get_base_url_field_name(model_cls: type[BaseModel]) -> str | None:
+    """
+    Return 'base_url' if the model has a field named or aliased as 'base_url',
+    else return 'api_base' if it has a field named or aliased as 'api_base',
+    else return None.
+    The return value is always either 'base_url', 'api_base', or None.
+    """
+    model_fields = model_cls.model_fields
+
+    # try model_fields first
+    if "base_url" in model_fields:
+        return "base_url"
+
+    if "api_base" in model_fields:
+        return "api_base"
+
+    # then try aliases
+    for field_info in model_fields.values():
+        if field_info.alias == "base_url":
+            return "base_url"
+
+    for field_info in model_fields.values():
+        if field_info.alias == "api_base":
+            return "api_base"
+
+    return None

{langchain_dev_utils-1.2.5 → langchain_dev_utils-1.2.6}/src/langchain_dev_utils/chat_models/base.py

@@ -3,7 +3,11 @@ from typing import Any, NotRequired, Optional, TypedDict, cast
 from langchain.chat_models.base import _SUPPORTED_PROVIDERS, _init_chat_model_helper
 from langchain_core.language_models.chat_models import BaseChatModel
 from langchain_core.utils import from_env
-from pydantic import BaseModel
+
+from langchain_dev_utils._utils import (
+    _check_langchain_openai_install,
+    _get_base_url_field_name,
+)
 
 from .types import ChatModelType, CompatibilityOptions
 
@@ -18,34 +22,6 @@ class ChatModelProvider(TypedDict):
     compatibility_options: NotRequired[CompatibilityOptions]
 
 
-def _get_base_url_field_name(model_cls: type[BaseModel]) -> str | None:
-    """
-    Return 'base_url' if the model has a field named or aliased as 'base_url',
-    else return 'api_base' if it has a field named or aliased as 'api_base',
-    else return None.
-    The return value is always either 'base_url', 'api_base', or None.
-    """
-    model_fields = model_cls.model_fields
-
-    # try model_fields first
-    if "base_url" in model_fields:
-        return "base_url"
-
-    if "api_base" in model_fields:
-        return "api_base"
-
-    # then try aliases
-    for field_info in model_fields.values():
-        if field_info.alias == "base_url":
-            return "base_url"
-
-    for field_info in model_fields.values():
-        if field_info.alias == "api_base":
-            return "api_base"
-
-    return None
-
-
 def _parse_model(model: str, model_provider: Optional[str]) -> tuple[str, str]:
     """Parse model string and provider.
 
@@ -89,7 +65,7 @@ def _load_chat_model_helper(
         BaseChatModel: Initialized chat model instance
     """
     model, model_provider = _parse_model(model, model_provider)
-    if model_provider in _MODEL_PROVIDERS_DICT.keys():
+    if model_provider in _MODEL_PROVIDERS_DICT:
         chat_model = _MODEL_PROVIDERS_DICT[model_provider]["chat_model"]
         if base_url := _MODEL_PROVIDERS_DICT[model_provider].get("base_url"):
             url_key = _get_base_url_field_name(chat_model)
@@ -98,7 +74,7 @@ def _load_chat_model_helper(
         if model_profiles := _MODEL_PROVIDERS_DICT[model_provider].get(
             "model_profiles"
         ):
-            if model in model_profiles:
+            if model in model_profiles and "profile" not in kwargs:
                 kwargs.update({"profile": model_profiles[model]})
         return chat_model(model=model, **kwargs)
 
@@ -145,12 +121,9 @@ def register_model_provider(
     """
     base_url = base_url or from_env(f"{provider_name.upper()}_API_BASE", default=None)()
     if isinstance(chat_model, str):
-        try:
-            from .adapters.openai_compatible import _create_openai_compatible_model
-        except ImportError:
-            raise ImportError(
-                "Please install langchain_dev_utils[standard],when chat_model is a 'openai-compatible'"
-            )
+        _check_langchain_openai_install()
+        from .adapters.openai_compatible import _create_openai_compatible_model
+
         if base_url is None:
             raise ValueError(
                 f"base_url must be provided or set {provider_name.upper()}_API_BASE environment variable when chat_model is a string"

{langchain_dev_utils-1.2.5 → langchain_dev_utils-1.2.6}/src/langchain_dev_utils/embeddings/base.py

@@ -2,7 +2,11 @@ from typing import Any, Literal, NotRequired, Optional, TypedDict, Union
 
 from langchain.embeddings.base import Embeddings, _SUPPORTED_PROVIDERS, init_embeddings
 from langchain_core.utils import from_env, secret_from_env
-from pydantic import BaseModel
+
+from langchain_dev_utils._utils import (
+    _check_langchain_openai_install,
+    _get_base_url_field_name,
+)
 
 _EMBEDDINGS_PROVIDERS_DICT = {}
 
@@ -15,34 +19,6 @@ class EmbeddingProvider(TypedDict):
     base_url: NotRequired[str]
 
 
-def _get_base_url_field_name(model_cls: type[BaseModel]) -> str | None:
-    """
-    Return 'base_url' if the model has a field named or aliased as 'base_url',
-    else return 'api_base' if it has a field named or aliased as 'api_base',
-    else return None.
-    The return value is always either 'base_url', 'api_base', or None.
-    """
-    model_fields = model_cls.model_fields
-
-    # try model_fields first
-    if "base_url" in model_fields:
-        return "base_url"
-
-    if "api_base" in model_fields:
-        return "api_base"
-
-    # then try aliases
-    for field_info in model_fields.values():
-        if field_info.alias == "base_url":
-            return "base_url"
-
-    for field_info in model_fields.values():
-        if field_info.alias == "api_base":
-            return "api_base"
-
-    return None
-
-
 def _parse_model_string(model_name: str) -> tuple[str, str]:
     """Parse model string into provider and model name.
 
@@ -119,6 +95,8 @@ def register_embeddings_provider(
                 "when embeddings_model is a string, the value must be 'openai-compatible'"
             )
 
+        _check_langchain_openai_install()
+
         _EMBEDDINGS_PROVIDERS_DICT.update(
             {
                 provider_name: {
@@ -238,7 +216,6 @@ def load_embeddings(
             if embeddings == "openai-compatible":
                 kwargs["check_embedding_ctx_length"] = False
                 embeddings = "openai"
-
         return init_embeddings(
             model=model,
             provider=embeddings,

langchain_dev_utils-1.2.5/src/langchain_dev_utils/__init__.py

@@ -1 +0,0 @@
-__version__ = "1.2.5"