-
A new BM25 (called [BM25s](https://github.com/xhluca/bm25s)) has been developed recently.
We leverage BM25 a lot in our pipeline. It could be interesting to see if we could integrate it.
Easiest…
-
``` python
from rank_bm25 import BM25Okapi
corpus = [
"Hello there good man!",
"It is quite windy in London"
"How is the weather today?"
]
tokenized_corpus = [doc.split(" ") for…
-
code:
```
analyzer = build_default_analyzer(language="zh")
bm25_ef = BM25EmbeddingFunction(analyzer)
bm25_ef.load("D:/Downloads/bm25_msmarco_v1.json")
def test():
entities = [....]
for en…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Hi, I have a (typical) use-case where vector index mostly works, but there are tim…
-
### What happens?
```
Query 1 ERROR at Line 1: : ERROR: could not parse query: WrongFieldType("data.enriched.email")
CONTEXT: SQL statement "SELECT * FROM public.raw_contacts WHERE id @@@ __para…
-
I am using Elasticsearch BM25 to fetch relevant documents. How can I add a parameter to tell the retriever to return only first n matching docs?
-
### What happens?
When I ran create_bm25 from Quick Start, I got an error
### To Reproduce
CALL paradedb.create_bm25_test_table(
schema_name => 'public',
table_name => 'mock_items'
);
…
-
### What happens?
Hi, referencing this [Issue](https://github.com/duckdb/duckdb/issues/7384) that was closed.
Steps to reproduce error is the same as such I have copied over the steps.
The foll…
-
请问在bm25建索引的时候去停用词并加载用户词典了吗
-
**Describe the bug**
We want to set custom 'averageFieldLength' via [ranking.properties](https://docs.vespa.ai/en/reference/query-api-reference.html#ranking.properties) but it doesn't seem to be work…