community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)

Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
2025-09-06 13:33:37 +00:00 · 2023-12-11 13:53:30 -08:00
parent c0f4b95aa9
commit ed58eeb9c5
2446 changed files with 171805 additions and 137118 deletions
--- a/libs/community/langchain_community/utilities/apify.py
+++ b/libs/community/langchain_community/utilities/apify.py
@@ -0,0 +1,204 @@
+from typing import TYPE_CHECKING, Any, Callable, Dict, Optional
+
+from langchain_core.documents import Document
+from langchain_core.pydantic_v1 import BaseModel, root_validator
+from langchain_core.utils import get_from_dict_or_env
+
+if TYPE_CHECKING:
+    from langchain_community.document_loaders import ApifyDatasetLoader
+
+
+class ApifyWrapper(BaseModel):
+    """Wrapper around Apify.
+    To use, you should have the ``apify-client`` python package installed,
+    and the environment variable ``APIFY_API_TOKEN`` set with your API key, or pass
+    `apify_api_token` as a named parameter to the constructor.
+    """
+
+    apify_client: Any
+    apify_client_async: Any
+
+    @root_validator()
+    def validate_environment(cls, values: Dict) -> Dict:
+        """Validate environment.
+        Validate that an Apify API token is set and the apify-client
+        Python package exists in the current environment.
+        """
+        apify_api_token = get_from_dict_or_env(
+            values, "apify_api_token", "APIFY_API_TOKEN"
+        )
+
+        try:
+            from apify_client import ApifyClient, ApifyClientAsync
+
+            values["apify_client"] = ApifyClient(apify_api_token)
+            values["apify_client_async"] = ApifyClientAsync(apify_api_token)
+        except ImportError:
+            raise ImportError(
+                "Could not import apify-client Python package. "
+                "Please install it with `pip install apify-client`."
+            )
+
+        return values
+
+    def call_actor(
+        self,
+        actor_id: str,
+        run_input: Dict,
+        dataset_mapping_function: Callable[[Dict], Document],
+        *,
+        build: Optional[str] = None,
+        memory_mbytes: Optional[int] = None,
+        timeout_secs: Optional[int] = None,
+    ) -> "ApifyDatasetLoader":
+        """Run an Actor on the Apify platform and wait for results to be ready.
+        Args:
+            actor_id (str): The ID or name of the Actor on the Apify platform.
+            run_input (Dict): The input object of the Actor that you're trying to run.
+            dataset_mapping_function (Callable): A function that takes a single
+                dictionary (an Apify dataset item) and converts it to an
+                instance of the Document class.
+            build (str, optional): Optionally specifies the actor build to run.
+                It can be either a build tag or build number.
+            memory_mbytes (int, optional): Optional memory limit for the run,
+                in megabytes.
+            timeout_secs (int, optional): Optional timeout for the run, in seconds.
+        Returns:
+            ApifyDatasetLoader: A loader that will fetch the records from the
+                Actor run's default dataset.
+        """
+        from langchain_community.document_loaders import ApifyDatasetLoader
+
+        actor_call = self.apify_client.actor(actor_id).call(
+            run_input=run_input,
+            build=build,
+            memory_mbytes=memory_mbytes,
+            timeout_secs=timeout_secs,
+        )
+
+        return ApifyDatasetLoader(
+            dataset_id=actor_call["defaultDatasetId"],
+            dataset_mapping_function=dataset_mapping_function,
+        )
+
+    async def acall_actor(
+        self,
+        actor_id: str,
+        run_input: Dict,
+        dataset_mapping_function: Callable[[Dict], Document],
+        *,
+        build: Optional[str] = None,
+        memory_mbytes: Optional[int] = None,
+        timeout_secs: Optional[int] = None,
+    ) -> "ApifyDatasetLoader":
+        """Run an Actor on the Apify platform and wait for results to be ready.
+        Args:
+            actor_id (str): The ID or name of the Actor on the Apify platform.
+            run_input (Dict): The input object of the Actor that you're trying to run.
+            dataset_mapping_function (Callable): A function that takes a single
+                dictionary (an Apify dataset item) and converts it to
+                an instance of the Document class.
+            build (str, optional): Optionally specifies the actor build to run.
+                It can be either a build tag or build number.
+            memory_mbytes (int, optional): Optional memory limit for the run,
+                in megabytes.
+            timeout_secs (int, optional): Optional timeout for the run, in seconds.
+        Returns:
+            ApifyDatasetLoader: A loader that will fetch the records from the
+                Actor run's default dataset.
+        """
+        from langchain_community.document_loaders import ApifyDatasetLoader
+
+        actor_call = await self.apify_client_async.actor(actor_id).call(
+            run_input=run_input,
+            build=build,
+            memory_mbytes=memory_mbytes,
+            timeout_secs=timeout_secs,
+        )
+
+        return ApifyDatasetLoader(
+            dataset_id=actor_call["defaultDatasetId"],
+            dataset_mapping_function=dataset_mapping_function,
+        )
+
+    def call_actor_task(
+        self,
+        task_id: str,
+        task_input: Dict,
+        dataset_mapping_function: Callable[[Dict], Document],
+        *,
+        build: Optional[str] = None,
+        memory_mbytes: Optional[int] = None,
+        timeout_secs: Optional[int] = None,
+    ) -> "ApifyDatasetLoader":
+        """Run a saved Actor task on Apify and wait for results to be ready.
+        Args:
+            task_id (str): The ID or name of the task on the Apify platform.
+            task_input (Dict): The input object of the task that you're trying to run.
+                Overrides the task's saved input.
+            dataset_mapping_function (Callable): A function that takes a single
+                dictionary (an Apify dataset item) and converts it to an
+                instance of the Document class.
+            build (str, optional): Optionally specifies the actor build to run.
+                It can be either a build tag or build number.
+            memory_mbytes (int, optional): Optional memory limit for the run,
+                in megabytes.
+            timeout_secs (int, optional): Optional timeout for the run, in seconds.
+        Returns:
+            ApifyDatasetLoader: A loader that will fetch the records from the
+                task run's default dataset.
+        """
+        from langchain_community.document_loaders import ApifyDatasetLoader
+
+        task_call = self.apify_client.task(task_id).call(
+            task_input=task_input,
+            build=build,
+            memory_mbytes=memory_mbytes,
+            timeout_secs=timeout_secs,
+        )
+
+        return ApifyDatasetLoader(
+            dataset_id=task_call["defaultDatasetId"],
+            dataset_mapping_function=dataset_mapping_function,
+        )
+
+    async def acall_actor_task(
+        self,
+        task_id: str,
+        task_input: Dict,
+        dataset_mapping_function: Callable[[Dict], Document],
+        *,
+        build: Optional[str] = None,
+        memory_mbytes: Optional[int] = None,
+        timeout_secs: Optional[int] = None,
+    ) -> "ApifyDatasetLoader":
+        """Run a saved Actor task on Apify and wait for results to be ready.
+        Args:
+            task_id (str): The ID or name of the task on the Apify platform.
+            task_input (Dict): The input object of the task that you're trying to run.
+                Overrides the task's saved input.
+            dataset_mapping_function (Callable): A function that takes a single
+                dictionary (an Apify dataset item) and converts it to an
+                instance of the Document class.
+            build (str, optional): Optionally specifies the actor build to run.
+                It can be either a build tag or build number.
+            memory_mbytes (int, optional): Optional memory limit for the run,
+                in megabytes.
+            timeout_secs (int, optional): Optional timeout for the run, in seconds.
+        Returns:
+            ApifyDatasetLoader: A loader that will fetch the records from the
+                task run's default dataset.
+        """
+        from langchain_community.document_loaders import ApifyDatasetLoader
+
+        task_call = await self.apify_client_async.task(task_id).call(
+            task_input=task_input,
+            build=build,
+            memory_mbytes=memory_mbytes,
+            timeout_secs=timeout_secs,
+        )
+
+        return ApifyDatasetLoader(
+            dataset_id=task_call["defaultDatasetId"],
+            dataset_mapping_function=dataset_mapping_function,
+        )