This PR adds support for passing through a set of ordering fields at
index time (unsigned ints that tantivity can use as fast_fields) that at
query time you can sort your results on. This is useful for cases where
you want to get related hits, i.e by keyword, but order those hits by
some other score, such as popularity.
I.e search for songs descriptions that match on "sad AND jazz AND 1920"
and then order those by number of times played. Example usage can be
seen in the fts tests.
---------
Co-authored-by: Nat Roth <natroth@Nats-MacBook-Pro.local>
Co-authored-by: Chang She <759245+changhiskhan@users.noreply.github.com>
Added a small bit of documentation for the `dim` feature which is
provided by the new `text-embedding-3` model series that allows users to
shorten an embedding.
Happy to discuss a bit on the phrasing but I struggled quite a bit with
getting it to work so wanted to help others who might want to use the
newer model too
The renaming of `vectordb` to `lancedb` broke the [quick start
docs](https://lancedb.github.io/lancedb/basic/#__tabbed_5_3) (it's
pointing to a non-existent directory). This PR fixes the code snippets
and the paths in the docs page.
Additionally, more fixes related to indexing docs below 👇🏽.
This PR adds the same consistency semantics as was added in #828. It
*does not* add the same lazy-loading of tables, since that breaks some
existing tests.
This closes#998.
---------
Co-authored-by: Weston Pace <weston.pace@gmail.com>
I think this should work. Need to deploy it to be sure as it can be
tested locally. Can be tested here.
2 things about this solution:
* All pages have a same meta tag, i.e, lancedb banner
* If needed, we can automatically use the first image of each page and
generate meta tags using the ultralytics mkdocs plugin that we did for
this purpose - https://github.com/ultralytics/mkdocs
Got some user feedback that the `implicit` / `explicit` distinction is
confusing.
Instead I was thinking we would just deprecate the `with_embeddings` API
and then organize working with embeddings into 3 buckets:
1. manually generate embeddings
2. use a provided embedding function
3. define your own custom embedding function
- Fixed typos and added some clarity to the hybrid search docs
- Changed "Airbnb" case to be as per the [official company
name](https://en.wikipedia.org/wiki/Airbnb) (the "bnb" shouldn't be
capitalized", and the text in the document aligns with this
- Fixed headers in nav bar
- Rename safe_import -> attempt_import_or_raise (closes
https://github.com/lancedb/lancedb/pull/923)
- Update docs
- Add Notebook example (@changhiskhan you can use it for the talk. Comes
with "open in colab" button)
- Latency benchmark & results comparison, sanity check on real-world
data
- Updates the default openai model to gpt-4
based on https://github.com/lancedb/lancedb/pull/713
- The Reranker api can be plugged into vector only or fts only search
but this PR doesn't do that (see example -
https://txt.cohere.com/rerank/)
### Default reranker -- `LinearCombinationReranker(weight=0.7,
fill=1.0)`
```
table.search("hello", query_type="hybrid").rerank(normalize="score").to_pandas()
```
### Available rerankers
LinearCombinationReranker
```
from lancedb.rerankers import LinearCombinationReranker
# Same as default
table.search("hello", query_type="hybrid").rerank(
normalize="score",
reranker=LinearCombinationReranker()
).to_pandas()
# with custom params
reranker = LinearCombinationReranker(weight=0.3, fill=1.0)
table.search("hello", query_type="hybrid").rerank(
normalize="score",
reranker=reranker
).to_pandas()
```
Cohere Reranker
```
from lancedb.rerankers import CohereReranker
# default model.. English and multi-lingual supported. See docstring for available custom params
table.search("hello", query_type="hybrid").rerank(
normalize="rank", # score or rank
reranker=CohereReranker()
).to_pandas()
```
CrossEncoderReranker
```
from lancedb.rerankers import CrossEncoderReranker
table.search("hello", query_type="hybrid").rerank(
normalize="rank",
reranker=CrossEncoderReranker()
).to_pandas()
```
## Using custom Reranker
```
from lancedb.reranker import Reranker
class CustomReranker(Reranker):
def rerank_hybrid(self, vector_result, fts_result):
combined_res = self.merge_results(vector_results, fts_results) # or use custom combination logic
# Custom rerank logic here
return combined_res
```
- [x] Expand testing
- [x] Make sure usage makes sense
- [x] Run simple benchmarks for correctness (Seeing weird result from
cohere reranker in the toy example)
- Support diverse rerankers by default:
- [x] Cross encoding
- [x] Cohere
- [x] Reciprocal Rank Fusion
---------
Co-authored-by: Chang She <759245+changhiskhan@users.noreply.github.com>
Co-authored-by: Prashanth Rao <35005448+prrao87@users.noreply.github.com>
Minor fix to change the background color for an image in the docs. It's
now readable in both light and dark modes (earlier version made it
impossible to read in dark mode).
have added testing and an example in the docstring, will be pushing a
separate PR in recipe repo for rag example
---------
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
