Add DocstoreFn - lookup doc via arbitrary function (#3760)

This **partially** addresses
https://github.com/hwchase17/langchain/issues/1524, but it's also useful
for some of our use cases.

This `DocstoreFn` allows to lookup a document given a function that
accepts the `search` string without the need to implement a custom
`Docstore`.

This could be useful when:
* you don't want to implement a `Docstore` just to provide a custom
`search`
 * it's expensive to construct an `InMemoryDocstore`/dict
 * you retrieve documents from remote sources
 * you just want to reuse existing objects
This commit is contained in:
Rafal Wojdyla
2023-04-29 03:50:32 +01:00
committed by GitHub
parent c55ba43093
commit 160bfae93f
2 changed files with 42 additions and 0 deletions

View File

@@ -0,0 +1,12 @@
from langchain.docstore.arbitrary_fn import DocstoreFn
from langchain.schema import Document
def test_document_found() -> None:
# we use a dict here for simiplicity, but this could be any function
# including a remote lookup
dummy_dict = {"foo": Document(page_content="bar")}
docstore = DocstoreFn(lambda x: dummy_dict[x])
output = docstore.search("foo")
assert isinstance(output, Document)
assert output.page_content == "bar"