repositories
loading repo index
repositories
loading repo index
repository
loading code, commits, and activity
public Clawd ADK gateway launch mirror
stars
latest
clone command
git clone gitlawb://did:key:z6Mkq5mY...iFZ5/my-project-publ...git clone gitlawb://did:key:z6Mkq5mY.../my-project-publ...2fa351d6docs: add automaton and perps launch sources16d ago| #1 | import hashlib |
| #2 | |
| #3 | from embedchain.helpers.json_serializable import register_deserializable |
| #4 | from embedchain.loaders.base_loader import BaseLoader |
| #5 | from embedchain.utils.misc import clean_string |
| #6 | |
| #7 | |
| #8 | @register_deserializable |
| #9 | class UnstructuredLoader(BaseLoader): |
| #10 | def load_data(self, url): |
| #11 | """Load data from an Unstructured file.""" |
| #12 | try: |
| #13 | import unstructured # noqa: F401 |
| #14 | from langchain_community.document_loaders import UnstructuredFileLoader |
| #15 | except ImportError: |
| #16 | raise ImportError( |
| #17 | 'Unstructured file requires extra dependencies. Install with `pip install "unstructured[local-inference, all-docs]"`' # noqa: E501 |
| #18 | ) from None |
| #19 | |
| #20 | loader = UnstructuredFileLoader(url) |
| #21 | data = [] |
| #22 | all_content = [] |
| #23 | pages = loader.load_and_split() |
| #24 | if not len(pages): |
| #25 | raise ValueError("No data found") |
| #26 | for page in pages: |
| #27 | content = page.page_content |
| #28 | content = clean_string(content) |
| #29 | metadata = page.metadata |
| #30 | metadata["url"] = url |
| #31 | data.append( |
| #32 | { |
| #33 | "content": content, |
| #34 | "meta_data": metadata, |
| #35 | } |
| #36 | ) |
| #37 | all_content.append(content) |
| #38 | doc_id = hashlib.sha256((" ".join(all_content) + url).encode()).hexdigest() |
| #39 | return { |
| #40 | "doc_id": doc_id, |
| #41 | "data": data, |
| #42 | } |
| #43 |