mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-07 14:03:26 +00:00
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
This commit is contained in:
@@ -0,0 +1,33 @@
|
||||
import json
|
||||
import uuid
|
||||
from typing import List
|
||||
|
||||
from langchain_core.documents import Document
|
||||
|
||||
from langchain_community.document_loaders.base import BaseLoader
|
||||
from langchain_community.tools.nuclia.tool import NucliaUnderstandingAPI
|
||||
|
||||
|
||||
class NucliaLoader(BaseLoader):
|
||||
"""Load from any file type using `Nuclia Understanding API`."""
|
||||
|
||||
def __init__(self, path: str, nuclia_tool: NucliaUnderstandingAPI):
|
||||
self.nua = nuclia_tool
|
||||
self.id = str(uuid.uuid4())
|
||||
self.nua.run({"action": "push", "id": self.id, "path": path, "text": None})
|
||||
|
||||
def load(self) -> List[Document]:
|
||||
"""Load documents."""
|
||||
data = self.nua.run(
|
||||
{"action": "pull", "id": self.id, "path": None, "text": None}
|
||||
)
|
||||
if not data:
|
||||
return []
|
||||
obj = json.loads(data)
|
||||
text = obj["extracted_text"][0]["body"]["text"]
|
||||
print(text)
|
||||
metadata = {
|
||||
"file": obj["file_extracted_data"][0],
|
||||
"metadata": obj["field_metadata"][0],
|
||||
}
|
||||
return [Document(page_content=text, metadata=metadata)]
|
Reference in New Issue
Block a user