mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
60c5d964a8
### Description Changed the value specified for `content_key` in JSONLoader from a single key to a value based on jq schema. I created [similar PR](https://github.com/langchain-ai/langchain/pull/11255) before, but it has several conflicts because of the architectural change associated stable version release, so I re-create this PR to fit new architecture. ### Why For json data like the following, specify `.data[].attributes.message` for page_content and `.data[].attributes.id` or `.data[].attributes.attributes. tags`, etc., the `content_key` must also parse the json structure. <details> <summary>sample json data</summary> ```json { "data": [ { "attributes": { "message": "message1", "tags": [ "tag1" ] }, "id": "1" }, { "attributes": { "message": "message2", "tags": [ "tag2" ] }, "id": "2" } ] } ``` </details> <details> <summary>sample code</summary> ```python def metadata_func(record: dict, metadata: dict) -> dict: metadata["source"] = None metadata["id"] = record.get("id") metadata["tags"] = record["attributes"].get("tags") return metadata sample_file = "sample1.json" loader = JSONLoader( file_path=sample_file, jq_schema=".data[]", content_key=".attributes.message", ## content_key is parsable into jq schema is_content_key_jq_parsable=True, ## this is added parameter metadata_func=metadata_func ) data = loader.load() data ``` </details> ### Dependencies none ### Twitter handle [kzk_maeda](https://twitter.com/kzk_maeda)
180 lines
7.1 KiB
Python
180 lines
7.1 KiB
Python
import json
|
|
from pathlib import Path
|
|
from typing import Any, Callable, Dict, List, Optional, Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
class JSONLoader(BaseLoader):
|
|
"""Load a `JSON` file using a `jq` schema.
|
|
|
|
Example:
|
|
[{"text": ...}, {"text": ...}, {"text": ...}] -> schema = .[].text
|
|
{"key": [{"text": ...}, {"text": ...}, {"text": ...}]} -> schema = .key[].text
|
|
["", "", ""] -> schema = .[]
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: Union[str, Path],
|
|
jq_schema: str,
|
|
content_key: Optional[str] = None,
|
|
is_content_key_jq_parsable: Optional[bool] = False,
|
|
metadata_func: Optional[Callable[[Dict, Dict], Dict]] = None,
|
|
text_content: bool = True,
|
|
json_lines: bool = False,
|
|
):
|
|
"""Initialize the JSONLoader.
|
|
|
|
Args:
|
|
file_path (Union[str, Path]): The path to the JSON or JSON Lines file.
|
|
jq_schema (str): The jq schema to use to extract the data or text from
|
|
the JSON.
|
|
content_key (str): The key to use to extract the content from
|
|
the JSON if the jq_schema results to a list of objects (dict).
|
|
If is_content_key_jq_parsable is True, this has to be a jq compatible
|
|
schema. If is_content_key_jq_parsable is False, this should be a simple
|
|
string key.
|
|
is_content_key_jq_parsable (bool): A flag to determine if
|
|
content_key is parsable by jq or not. If True, content_key is
|
|
treated as a jq schema and compiled accordingly. If False or if
|
|
content_key is None, content_key is used as a simple string.
|
|
Default is False.
|
|
metadata_func (Callable[Dict, Dict]): A function that takes in the JSON
|
|
object extracted by the jq_schema and the default metadata and returns
|
|
a dict of the updated metadata.
|
|
text_content (bool): Boolean flag to indicate whether the content is in
|
|
string format, default to True.
|
|
json_lines (bool): Boolean flag to indicate whether the input is in
|
|
JSON Lines format.
|
|
"""
|
|
try:
|
|
import jq # noqa:F401
|
|
|
|
self.jq = jq
|
|
except ImportError:
|
|
raise ImportError(
|
|
"jq package not found, please install it with `pip install jq`"
|
|
)
|
|
|
|
self.file_path = Path(file_path).resolve()
|
|
self._jq_schema = jq.compile(jq_schema)
|
|
self._is_content_key_jq_parsable = is_content_key_jq_parsable
|
|
self._content_key = content_key
|
|
self._metadata_func = metadata_func
|
|
self._text_content = text_content
|
|
self._json_lines = json_lines
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load and return documents from the JSON file."""
|
|
docs: List[Document] = []
|
|
if self._json_lines:
|
|
with self.file_path.open(encoding="utf-8") as f:
|
|
for line in f:
|
|
line = line.strip()
|
|
if line:
|
|
self._parse(line, docs)
|
|
else:
|
|
self._parse(self.file_path.read_text(encoding="utf-8"), docs)
|
|
return docs
|
|
|
|
def _parse(self, content: str, docs: List[Document]) -> None:
|
|
"""Convert given content to documents."""
|
|
data = self._jq_schema.input(json.loads(content))
|
|
|
|
# Perform some validation
|
|
# This is not a perfect validation, but it should catch most cases
|
|
# and prevent the user from getting a cryptic error later on.
|
|
if self._content_key is not None:
|
|
self._validate_content_key(data)
|
|
if self._metadata_func is not None:
|
|
self._validate_metadata_func(data)
|
|
|
|
for i, sample in enumerate(data, len(docs) + 1):
|
|
text = self._get_text(sample=sample)
|
|
metadata = self._get_metadata(
|
|
sample=sample, source=str(self.file_path), seq_num=i
|
|
)
|
|
docs.append(Document(page_content=text, metadata=metadata))
|
|
|
|
def _get_text(self, sample: Any) -> str:
|
|
"""Convert sample to string format"""
|
|
if self._content_key is not None:
|
|
if self._is_content_key_jq_parsable:
|
|
compiled_content_key = self.jq.compile(self._content_key)
|
|
content = compiled_content_key.input(sample).first()
|
|
else:
|
|
content = sample[self._content_key]
|
|
else:
|
|
content = sample
|
|
|
|
if self._text_content and not isinstance(content, str):
|
|
raise ValueError(
|
|
f"Expected page_content is string, got {type(content)} instead. \
|
|
Set `text_content=False` if the desired input for \
|
|
`page_content` is not a string"
|
|
)
|
|
|
|
# In case the text is None, set it to an empty string
|
|
elif isinstance(content, str):
|
|
return content
|
|
elif isinstance(content, dict):
|
|
return json.dumps(content) if content else ""
|
|
else:
|
|
return str(content) if content is not None else ""
|
|
|
|
def _get_metadata(
|
|
self, sample: Dict[str, Any], **additional_fields: Any
|
|
) -> Dict[str, Any]:
|
|
"""
|
|
Return a metadata dictionary base on the existence of metadata_func
|
|
:param sample: single data payload
|
|
:param additional_fields: key-word arguments to be added as metadata values
|
|
:return:
|
|
"""
|
|
if self._metadata_func is not None:
|
|
return self._metadata_func(sample, additional_fields)
|
|
else:
|
|
return additional_fields
|
|
|
|
def _validate_content_key(self, data: Any) -> None:
|
|
"""Check if a content key is valid"""
|
|
|
|
sample = data.first()
|
|
if not isinstance(sample, dict):
|
|
raise ValueError(
|
|
f"Expected the jq schema to result in a list of objects (dict), \
|
|
so sample must be a dict but got `{type(sample)}`"
|
|
)
|
|
|
|
if (
|
|
not self._is_content_key_jq_parsable
|
|
and sample.get(self._content_key) is None
|
|
):
|
|
raise ValueError(
|
|
f"Expected the jq schema to result in a list of objects (dict) \
|
|
with the key `{self._content_key}`"
|
|
)
|
|
if (
|
|
self._is_content_key_jq_parsable
|
|
and self.jq.compile(self._content_key).input(sample).text() is None
|
|
):
|
|
raise ValueError(
|
|
f"Expected the jq schema to result in a list of objects (dict) \
|
|
with the key `{self._content_key}` which should be parsable by jq"
|
|
)
|
|
|
|
def _validate_metadata_func(self, data: Any) -> None:
|
|
"""Check if the metadata_func output is valid"""
|
|
|
|
sample = data.first()
|
|
if self._metadata_func is not None:
|
|
sample_metadata = self._metadata_func(sample, {})
|
|
if not isinstance(sample_metadata, dict):
|
|
raise ValueError(
|
|
f"Expected the metadata_func to return a dict but got \
|
|
`{type(sample_metadata)}`"
|
|
)
|