mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-28 23:07:11 +00:00
bf5193bb99
Upgrade to using a literal for specifying the extra which is the
recommended approach in pydantic 2.
This works correctly also in pydantic v1.
```python
from pydantic.v1 import BaseModel
class Foo(BaseModel, extra="forbid"):
x: int
Foo(x=5, y=1)
```
And
```python
from pydantic.v1 import BaseModel
class Foo(BaseModel):
x: int
class Config:
extra = "forbid"
Foo(x=5, y=1)
```
## Enum -> literal using grit pattern:
```
engine marzano(0.1)
language python
or {
`extra=Extra.allow` => `extra="allow"`,
`extra=Extra.forbid` => `extra="forbid"`,
`extra=Extra.ignore` => `extra="ignore"`
}
```
Resorted attributes in config and removed doc-string in case we will
need to deal with going back and forth between pydantic v1 and v2 during
the 0.3 release. (This will reduce merge conflicts.)
## Sort attributes in Config:
```
engine marzano(0.1)
language python
function sort($values) js {
return $values.text.split(',').sort().join("\n");
}
class_definition($name, $body) as $C where {
$name <: `Config`,
$body <: block($statements),
$values = [],
$statements <: some bubble($values) assignment() as $A where {
$values += $A
},
$body => sort($values),
}
```
103 lines
3.6 KiB
Python
103 lines
3.6 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any, Callable, Dict, Iterable, List, Optional
|
|
|
|
from langchain_core.callbacks import CallbackManagerForRetrieverRun
|
|
from langchain_core.documents import Document
|
|
from langchain_core.pydantic_v1 import Field
|
|
from langchain_core.retrievers import BaseRetriever
|
|
|
|
|
|
def default_preprocessing_func(text: str) -> List[str]:
|
|
return text.split()
|
|
|
|
|
|
class BM25Retriever(BaseRetriever):
|
|
"""`BM25` retriever without Elasticsearch."""
|
|
|
|
vectorizer: Any
|
|
""" BM25 vectorizer."""
|
|
docs: List[Document] = Field(repr=False)
|
|
""" List of documents."""
|
|
k: int = 4
|
|
""" Number of documents to return."""
|
|
preprocess_func: Callable[[str], List[str]] = default_preprocessing_func
|
|
""" Preprocessing function to use on the text before BM25 vectorization."""
|
|
|
|
class Config:
|
|
arbitrary_types_allowed = True
|
|
|
|
@classmethod
|
|
def from_texts(
|
|
cls,
|
|
texts: Iterable[str],
|
|
metadatas: Optional[Iterable[dict]] = None,
|
|
bm25_params: Optional[Dict[str, Any]] = None,
|
|
preprocess_func: Callable[[str], List[str]] = default_preprocessing_func,
|
|
**kwargs: Any,
|
|
) -> BM25Retriever:
|
|
"""
|
|
Create a BM25Retriever from a list of texts.
|
|
Args:
|
|
texts: A list of texts to vectorize.
|
|
metadatas: A list of metadata dicts to associate with each text.
|
|
bm25_params: Parameters to pass to the BM25 vectorizer.
|
|
preprocess_func: A function to preprocess each text before vectorization.
|
|
**kwargs: Any other arguments to pass to the retriever.
|
|
|
|
Returns:
|
|
A BM25Retriever instance.
|
|
"""
|
|
try:
|
|
from rank_bm25 import BM25Okapi
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import rank_bm25, please install with `pip install "
|
|
"rank_bm25`."
|
|
)
|
|
|
|
texts_processed = [preprocess_func(t) for t in texts]
|
|
bm25_params = bm25_params or {}
|
|
vectorizer = BM25Okapi(texts_processed, **bm25_params)
|
|
metadatas = metadatas or ({} for _ in texts)
|
|
docs = [Document(page_content=t, metadata=m) for t, m in zip(texts, metadatas)]
|
|
return cls(
|
|
vectorizer=vectorizer, docs=docs, preprocess_func=preprocess_func, **kwargs
|
|
)
|
|
|
|
@classmethod
|
|
def from_documents(
|
|
cls,
|
|
documents: Iterable[Document],
|
|
*,
|
|
bm25_params: Optional[Dict[str, Any]] = None,
|
|
preprocess_func: Callable[[str], List[str]] = default_preprocessing_func,
|
|
**kwargs: Any,
|
|
) -> BM25Retriever:
|
|
"""
|
|
Create a BM25Retriever from a list of Documents.
|
|
Args:
|
|
documents: A list of Documents to vectorize.
|
|
bm25_params: Parameters to pass to the BM25 vectorizer.
|
|
preprocess_func: A function to preprocess each text before vectorization.
|
|
**kwargs: Any other arguments to pass to the retriever.
|
|
|
|
Returns:
|
|
A BM25Retriever instance.
|
|
"""
|
|
texts, metadatas = zip(*((d.page_content, d.metadata) for d in documents))
|
|
return cls.from_texts(
|
|
texts=texts,
|
|
bm25_params=bm25_params,
|
|
metadatas=metadatas,
|
|
preprocess_func=preprocess_func,
|
|
**kwargs,
|
|
)
|
|
|
|
def _get_relevant_documents(
|
|
self, query: str, *, run_manager: CallbackManagerForRetrieverRun
|
|
) -> List[Document]:
|
|
processed_query = self.preprocess_func(query)
|
|
return_docs = self.vectorizer.get_top_n(processed_query, self.docs, n=self.k)
|
|
return return_docs
|