Update api references (#8646)

Update API reference documentation. This PR will pick up a number of missing classes, it also applies selective formatting based on the class / object type.

docs/api_reference/conf.py

@@ -100,6 +100,9 @@ extensions = [
 ]
 source_suffix = [".rst"]
 
+# some autodoc pydantic options are repeated in the actual template.
+# potentially user error, but there may be bugs in the sphinx extension
+# with options not being passed through correctly (from either the location in the code)
 autodoc_pydantic_model_show_json = False
 autodoc_pydantic_field_list_validators = False
 autodoc_pydantic_config_members = False
@@ -112,13 +115,6 @@ autodoc_member_order = "groupwise"
 autoclass_content = "both"
 autodoc_typehints_format = "short"
 
-autodoc_default_options = {
-    "members": True,
-    "show-inheritance": True,
-    "inherited-members": "BaseModel",
-    "undoc-members": True,
-    "special-members": "__call__",
-}
 # autodoc_typehints = "description"
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ["templates"]

docs/api_reference/create_api_rst.py

@@ -1,49 +1,209 @@
-"""Script for auto-generating api_reference.rst"""
+"""Script for auto-generating api_reference.rst."""
-import glob
+import importlib
-import re
+import inspect
+import typing
 from pathlib import Path
+from typing import TypedDict, Sequence, List, Dict, Literal, Union
+from enum import Enum
+
+from pydantic import BaseModel
 
 ROOT_DIR = Path(__file__).parents[2].absolute()
+HERE = Path(__file__).parent
+
 PKG_DIR = ROOT_DIR / "libs" / "langchain" / "langchain"
 EXP_DIR = ROOT_DIR / "libs" / "experimental" / "langchain_experimental"
-WRITE_FILE = Path(__file__).parent / "api_reference.rst"
+WRITE_FILE = HERE / "api_reference.rst"
-EXP_WRITE_FILE = Path(__file__).parent / "experimental_api_reference.rst"
+EXP_WRITE_FILE = HERE / "experimental_api_reference.rst"
-
+
-
+
-def load_members(dir: Path) -> dict:
+ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
-    members: dict = {}
+
-    for py in glob.glob(str(dir) + "/**/*.py", recursive=True):
+
-        module = py[len(str(dir)) + 1 :].replace(".py", "").replace("/", ".")
+class ClassInfo(TypedDict):
-        top_level = module.split(".")[0]
+    """Information about a class."""
-        if top_level not in members:
+
-            members[top_level] = {"classes": [], "functions": []}
+    name: str
-        with open(py, "r") as f:
+    """The name of the class."""
-            for line in f.readlines():
+    qualified_name: str
-                cls = re.findall(r"^class ([^_].*)\(", line)
+    """The fully qualified name of the class."""
-                members[top_level]["classes"].extend([module + "." + c for c in cls])
+    kind: ClassKind
-                func = re.findall(r"^def ([^_].*)\(", line)
+    """The kind of the class."""
-                afunc = re.findall(r"^async def ([^_].*)\(", line)
+    is_public: bool
-                func_strings = [module + "." + f for f in func + afunc]
+    """Whether the class is public or not."""
-                members[top_level]["functions"].extend(func_strings)
+
-    return members
+
-
+class FunctionInfo(TypedDict):
-
+    """Information about a function."""
-def construct_doc(pkg: str, members: dict) -> str:
+
+    name: str
+    """The name of the function."""
+    qualified_name: str
+    """The fully qualified name of the function."""
+    is_public: bool
+    """Whether the function is public or not."""
+
+
+class ModuleMembers(TypedDict):
+    """A dictionary of module members."""
+
+    classes_: Sequence[ClassInfo]
+    functions: Sequence[FunctionInfo]
+
+
+def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
+    """Load all members of a module.
+
+    Args:
+        module_path: Path to the module.
+        namespace: the namespace of the module.
+
+    Returns:
+        list: A list of loaded module objects.
+    """
+    classes_: List[ClassInfo] = []
+    functions: List[FunctionInfo] = []
+    module = importlib.import_module(module_path)
+    for name, type_ in inspect.getmembers(module):
+        if not hasattr(type_, "__module__"):
+            continue
+        if type_.__module__ != module_path:
+            continue
+
+        if inspect.isclass(type_):
+            if type(type_) == typing._TypedDictMeta:  # type: ignore
+                kind: ClassKind = "TypedDict"
+            elif issubclass(type_, Enum):
+                kind = "enum"
+            elif issubclass(type_, BaseModel):
+                kind = "Pydantic"
+            else:
+                kind = "Regular"
+
+            classes_.append(
+                ClassInfo(
+                    name=name,
+                    qualified_name=f"{namespace}.{name}",
+                    kind=kind,
+                    is_public=not name.startswith("_"),
+                )
+            )
+        elif inspect.isfunction(type_):
+            functions.append(
+                FunctionInfo(
+                    name=name,
+                    qualified_name=f"{namespace}.{name}",
+                    is_public=not name.startswith("_"),
+                )
+            )
+        else:
+            continue
+
+    return ModuleMembers(
+        classes_=classes_,
+        functions=functions,
+    )
+
+
+def _merge_module_members(
+    module_members: Sequence[ModuleMembers],
+) -> ModuleMembers:
+    """Merge module members."""
+    classes_: List[ClassInfo] = []
+    functions: List[FunctionInfo] = []
+    for module in module_members:
+        classes_.extend(module["classes_"])
+        functions.extend(module["functions"])
+
+    return ModuleMembers(
+        classes_=classes_,
+        functions=functions,
+    )
+
+
+def _load_package_modules(
+    package_directory: Union[str, Path]
+) -> Dict[str, ModuleMembers]:
+    """Recursively load modules of a package based on the file system.
+
+    Traversal based on the file system makes it easy to determine which
+    of the modules/packages are part of the package vs. 3rd party or built-in.
+
+    Parameters:
+        package_directory: Path to the package directory.
+
+    Returns:
+        list: A list of loaded module objects.
+    """
+    package_path = (
+        Path(package_directory)
+        if isinstance(package_directory, str)
+        else package_directory
+    )
+    modules_by_namespace = {}
+
+    package_name = package_path.name
+
+    for file_path in package_path.rglob("*.py"):
+        if not file_path.name.startswith("__"):
+            relative_module_name = file_path.relative_to(package_path)
+            # Get the full namespace of the module
+            namespace = str(relative_module_name).replace(".py", "").replace("/", ".")
+            # Keep only the top level namespace
+            top_namespace = namespace.split(".")[0]
+
+            try:
+                module_members = _load_module_members(
+                    f"{package_name}.{namespace}", namespace
+                )
+                # Merge module members if the namespace already exists
+                if top_namespace in modules_by_namespace:
+                    existing_module_members = modules_by_namespace[top_namespace]
+                    _module_members = _merge_module_members(
+                        [existing_module_members, module_members]
+                    )
+                else:
+                    _module_members = module_members
+
+                modules_by_namespace[top_namespace] = _module_members
+
+            except ImportError as e:
+                print(f"Error: Unable to import module '{namespace}' with error: {e}")
+
+    return modules_by_namespace
+
+
+def _construct_doc(pkg: str, members_by_namespace: Dict[str, ModuleMembers]) -> str:
+    """Construct the contents of the reference.rst file for the given package.
+
+    Args:
+        pkg: The package name
+        members_by_namespace: The members of the package, dict organized by top level
+                              module contains a list of classes and functions
+                              inside of the top level namespace.
+
+    Returns:
+        The contents of the reference.rst file.
+    """
     full_doc = f"""\
-=============
+=======================
 ``{pkg}`` API Reference
-=============
+=======================
 
 """
-    for module, _members in sorted(members.items(), key=lambda kv: kv[0]):
+    namespaces = sorted(members_by_namespace)
-        classes = _members["classes"]
+
+    for module in namespaces:
+        _members = members_by_namespace[module]
+        classes = _members["classes_"]
         functions = _members["functions"]
         if not (classes or functions):
             continue
         section = f":mod:`{pkg}.{module}`"
+        underline = "=" * (len(section) + 1)
         full_doc += f"""\
 {section}
-{'=' * (len(section) + 1)}
+{underline}
 
 .. automodule:: {pkg}.{module}
     :no-members:
@@ -52,7 +212,6 @@ def construct_doc(pkg: str, members: dict) -> str:
 """
 
         if classes:
-            cstring = "\n    ".join(sorted(classes))
             full_doc += f"""\
 Classes
 --------------
@@ -60,13 +219,31 @@ Classes
 
 .. autosummary::
     :toctree: {module}
-    :template: class.rst
+"""
+
+            for class_ in classes:
+                if not class_['is_public']:
+                    continue
+                    
+                if class_["kind"] == "TypedDict":
+                    template = "typeddict.rst"
+                elif class_["kind"] == "enum":
+                    template = "enum.rst"
+                elif class_["kind"] == "Pydantic":
+                    template = "pydantic.rst"
+                else:
+                    template = "class.rst"
 
-    {cstring}
+                full_doc += f"""\
+    :template: {template}
+    
+    {class_["qualified_name"]}
     
 """
+
         if functions:
-            fstring = "\n    ".join(sorted(functions))
+            _functions = [f["qualified_name"] for f in functions if f["is_public"]]
+            fstring = "\n    ".join(sorted(_functions))
             full_doc += f"""\
 Functions
 --------------
@@ -83,12 +260,15 @@ Functions
 
 
 def main() -> None:
-    lc_members = load_members(PKG_DIR)
+    """Generate the reference.rst file for each package."""
-    lc_doc = ".. _api_reference:\n\n" + construct_doc("langchain", lc_members)
+    lc_members = _load_package_modules(PKG_DIR)
+    lc_doc = ".. _api_reference:\n\n" + _construct_doc("langchain", lc_members)
     with open(WRITE_FILE, "w") as f:
         f.write(lc_doc)
-    exp_members = load_members(EXP_DIR)
+    exp_members = _load_package_modules(EXP_DIR)
-    exp_doc = ".. _experimental_api_reference:\n\n" + construct_doc("langchain_experimental", exp_members)
+    exp_doc = ".. _experimental_api_reference:\n\n" + _construct_doc(
+        "langchain_experimental", exp_members
+    )
     with open(EXP_WRITE_FILE, "w") as f:
         f.write(exp_doc)
 

docs/api_reference/requirements.txt

@@ -1,4 +1,5 @@
 -e libs/langchain
+-e libs/experimental
 autodoc_pydantic==1.8.0
 myst_parser
 nbsphinx==0.8.9

docs/api_reference/templates/class.rst

@@ -5,26 +5,32 @@
 
 .. autoclass:: {{ objname }}
 
-   {% block methods %}
+   {% block attributes %}
-   {% if methods %}
+   {% if attributes %}
-   .. rubric:: {{ _('Methods') }}
+   .. rubric:: {{ _('Attributes') }}
 
    .. autosummary::
-   {% for item in methods %}
+   {% for item in attributes %}
       ~{{ name }}.{{ item }}
    {%- endfor %}
    {% endif %}
    {% endblock %}
 
-   {% block attributes %}
+   {% block methods %}
-   {% if attributes %}
+   {% if methods %}
-   .. rubric:: {{ _('Attributes') }}
+   .. rubric:: {{ _('Methods') }}
 
    .. autosummary::
-   {% for item in attributes %}
+   {% for item in methods %}
       ~{{ name }}.{{ item }}
    {%- endfor %}
+
+   {% for item in methods %}
+   .. automethod:: {{ name }}.{{ item }}
+   {%- endfor %}
+
    {% endif %}
    {% endblock %}
 
+
 .. example_links:: {{ objname }}

docs/api_reference/templates/enum.rst

@@ -0,0 +1,14 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+    {% block attributes %}
+    {% for item in attributes %}
+    .. autoattribute:: {{ item }}
+    {% endfor %}
+    {% endblock %}
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/pydantic.rst

@@ -0,0 +1,22 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autopydantic_model:: {{ objname }}
+    :model-show-json: False
+    :model-show-config-summary: False
+    :model-show-validator-members: False
+    :model-show-field-summary: False
+    :field-signature-prefix: param
+    :members:
+    :undoc-members:
+    :inherited-members:
+    :member-order: groupwise
+    :show-inheritance: True
+    :special-members: __call__
+
+    {% block attributes %}
+    {% endblock %}
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/typeddict.rst

@@ -0,0 +1,14 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+    {% block attributes %}
+   {% for item in attributes %}
+  .. autoattribute:: {{ item }}
+   {% endfor %}
+   {% endblock %}
+
+.. example_links:: {{ objname }}