Add DocumentTransformer abstraction so that in #2915 we don't have to
wrap TextSplitter and RedundantEmbeddingFilter (neither of which uses
the query) in the contextual doc compression abstractions. with this
change, doc filter (doc extractor, whatever we call it) would look
something like
```python
class BaseDocumentFilter(BaseDocumentTransformer[_RetrievedDocument], ABC):
@abstractmethod
def filter(self, documents: List[_RetrievedDocument], query: str) -> List[_RetrievedDocument]:
...
def transform_documents(self, documents: List[_RetrievedDocument], query: Optional[str] = None, **kwargs: Any) -> List[_RetrievedDocument]:
if query is None:
raise ValueError("Must pass in non-null query to DocumentFilter")
return self.filter(documents, query)
```
re
https://github.com/hwchase17/langchain/issues/439#issuecomment-1510442791
I think it's not polite for a library to use the root logger
both of these forms are also used:
```
logger = logging.getLogger(__name__)
logger = logging.getLogger(__file__)
```
I am not sure if there is any reason behind one vs the other? (...I am
guessing maybe just contributed by different people)
it seems to me it'd be better to consistently use
`logging.getLogger(__name__)`
this makes it easier for consumers of the library to set up log
handlers, e.g. for everything with `langchain.` prefix
Fixes a bug I was seeing when the `TokenTextSplitter` was correctly
splitting text under the gpt3.5-turbo token limit, but when firing the
prompt off too openai, it'd come back with an error that we were over
the context limit.
gpt3.5-turbo and gpt-4 use `cl100k_base` tokenizer, and so the counts
are just always off with the default `gpt-2` encoder.
It's possible to pass along the encoding to the `TokenTextSplitter`, but
it's much simpler to pass the model name of the LLM. No more concern
about keeping the tokenizer and llm model in sync :)
This does not involve a separator, and will naively chunk input text at
the appropriate boundaries in token space.
This is helpful if we have strict token length limits that we need to
strictly follow the specified chunk size, and we can't use aggressive
separators like spaces to guarantee the absence of long strings.
CharacterTextSplitter will let these strings through without splitting
them, which could cause overflow errors downstream.
Splitting at arbitrary token boundaries is not ideal but is hopefully
mitigated by having a decent overlap quantity. Also this results in
chunks which has exact number of tokens desired, instead of sometimes
overcounting if we concatenate shorter strings.
Potentially also helps with #528.
Davis Chase