github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-08-19 16:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

more fixes

Browse Source
This commit is contained in:
Javier Martínez Álvarez 2024-03-27 18:26:20 +01:00
parent d7908bcefa
commit 93db41483a
No known key found for this signature in database
1 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
private_gpt/components/ingest/readers/rdfreader.py
View File

@ -10,6 +10,7 @@ Original code:
https://github.com/run-llama/llama-hub https://github.com/run-llama/llama-hub
""" """
import logging
from pathlib import Path from pathlib import Path
from typing import Any from typing import Any
@ -18,6 +19,8 @@ from llama_index.core.schema import Document
from rdflib import Graph, URIRef from rdflib import Graph, URIRef
from rdflib.namespace import RDF, RDFS from rdflib.namespace import RDF, RDFS
logger = logging.getLogger(__name__)
class RDFReader(BaseReader): class RDFReader(BaseReader):
"""RDF reader.""" """RDF reader."""
@ -46,11 +49,17 @@ class RDFReader(BaseReader):
if len(labels) > 0: if len(labels) > 0:
return labels[0].value return labels[0].value
return None # Return None if label not found return str(uri)
def load_data(self, file: Path, extra_info: dict | None = None) -> list[Document]: def load_data(self, file: Path, extra_info: dict | None = None) -> list[Document]:
"""Parse file.""" """Parse file."""
lang = extra_info["lang"] if extra_info is not None else "en" extra_info = extra_info or {}
extra_info["graph_type"] = "rdf"
lang = (
extra_info["lang"]
if extra_info is not None and "lang" in extra_info
else "en"
)
self.g_local = Graph() self.g_local = Graph()
self.g_local.parse(file) self.g_local.parse(file)
@ -62,6 +71,7 @@ class RDFReader(BaseReader):
text_list = [] text_list = []
for s, p, o in self.g_local: for s, p, o in self.g_local:
logger.debug("s=%s, p=%s, o=%s", s, p, o)
if p == RDFS.label: if p == RDFS.label:
continue continue