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
2025-09-04 04:28:58 +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/document_loaders/max_compute.py
+++ b/libs/community/langchain_community/document_loaders/max_compute.py
@@ -0,0 +1,83 @@
+from __future__ import annotations
+
+from typing import Any, Iterator, List, Optional, Sequence
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.base import BaseLoader
+from langchain_community.utilities.max_compute import MaxComputeAPIWrapper
+
+
+class MaxComputeLoader(BaseLoader):
+    """Load from `Alibaba Cloud MaxCompute` table."""
+
+    def __init__(
+        self,
+        query: str,
+        api_wrapper: MaxComputeAPIWrapper,
+        *,
+        page_content_columns: Optional[Sequence[str]] = None,
+        metadata_columns: Optional[Sequence[str]] = None,
+    ):
+        """Initialize Alibaba Cloud MaxCompute document loader.
+
+        Args:
+            query: SQL query to execute.
+            api_wrapper: MaxCompute API wrapper.
+            page_content_columns: The columns to write into the `page_content` of the
+                Document. If unspecified, all columns will be written to `page_content`.
+            metadata_columns: The columns to write into the `metadata` of the Document.
+                If unspecified, all columns not added to `page_content` will be written.
+        """
+        self.query = query
+        self.api_wrapper = api_wrapper
+        self.page_content_columns = page_content_columns
+        self.metadata_columns = metadata_columns
+
+    @classmethod
+    def from_params(
+        cls,
+        query: str,
+        endpoint: str,
+        project: str,
+        *,
+        access_id: Optional[str] = None,
+        secret_access_key: Optional[str] = None,
+        **kwargs: Any,
+    ) -> MaxComputeLoader:
+        """Convenience constructor that builds the MaxCompute API wrapper from
+            given parameters.
+
+        Args:
+            query: SQL query to execute.
+            endpoint: MaxCompute endpoint.
+            project: A project is a basic organizational unit of MaxCompute, which is
+                similar to a database.
+            access_id: MaxCompute access ID. Should be passed in directly or set as the
+                environment variable `MAX_COMPUTE_ACCESS_ID`.
+            secret_access_key: MaxCompute secret access key. Should be passed in
+                directly or set as the environment variable
+                `MAX_COMPUTE_SECRET_ACCESS_KEY`.
+        """
+        api_wrapper = MaxComputeAPIWrapper.from_params(
+            endpoint, project, access_id=access_id, secret_access_key=secret_access_key
+        )
+        return cls(query, api_wrapper, **kwargs)
+
+    def lazy_load(self) -> Iterator[Document]:
+        for row in self.api_wrapper.query(self.query):
+            if self.page_content_columns:
+                page_content_data = {
+                    k: v for k, v in row.items() if k in self.page_content_columns
+                }
+            else:
+                page_content_data = row
+            page_content = "\n".join(f"{k}: {v}" for k, v in page_content_data.items())
+            if self.metadata_columns:
+                metadata = {k: v for k, v in row.items() if k in self.metadata_columns}
+            else:
+                metadata = {k: v for k, v in row.items() if k not in page_content_data}
+            yield Document(page_content=page_content, metadata=metadata)
+
+    def load(self) -> List[Document]:
+        return list(self.lazy_load())