-
We should support incremental indexing of large corpuses. We can already save a corpus
to an io.Writer and load a corpus from an io.Reader, but once we have a large, saved
Corpus, there is no way to …
-
Currently we use the minisearch library to generate full text indexes for text fields. This works great but we have clients requesting text search support for non-english languages. The lunr.js librar…
na9da updated
3 years ago
-
We have a collection online,The information is as follows:
```
curl -X GET 'http://localhost:6333/collections/questions_embeddings_v01_orionstar_text-embedding-bge_39' \
-H 'Content-Type: applica…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Hi,
I have used this code https://docs.llamaindex.ai/en/stable/examples/callbacks/Tok…
-
### How are you using the lua-language-server?
NeoVim
### Which OS are you using?
MacOS
### What is the issue affecting?
Completion
### Expected Behaviour
Get back a completion item which does …
-
Hi,
I added the stardict dictionary files of OED 2nd Ed. into the goldendict, and the full-text search indexing is running for ever and the golderdict failed to response for query.
How to solv…
-
There are a number of items in `wgpu` whose documentation contain examples using GLSL syntax or other references to GLSL elements. Since WGSL is now the standard shading language for WebGPU, it would …
-
When I use the plugin to attach the felix bundles as dependencies, they do not get searched in when doing a find in Project and Libraries.
An often used case is that you want to search for a string…
-
I still don't know if there is room for optimization there but the performance drop is significant. I observed on a dataset with documents containing a big array of small text, a drop of 25% in indexi…
-
When using code to get PRF:
```
prf_rank = pytcolbert.prf(rerank=False,fb_docs=10,fb_embs=10)
df=prf_rank.search(query).head(1)
query_toks=df.iloc[0]['query_toks']
```
The resulting query_toke…