-
In the `where` clause, the SQL query can access arbitrarily nested fields, but this is not possible with the dataframe, e.g. I want to be able to do:
```
df = tbl.search().to_pandas()
```
and be…
-
### 🚀 The feature
[LanceDB](https://lancedb.com/) is a developer-friendly, serverless vector database.
### Motivation, pitch
We can integrate with its APIs to allow experimentation on various confi…
-
Python: 3.8.9
pylance: 0.8.17
File "create_index.py", line 6, in
full_ds.create_index(
File "/usr/local/lib/python3.8/dist-packages/lance/dataset.py", line 992, in create_index
ivf_c…
-
## Summary
I am currently using a GitHub Action in my workflow, but I'm encountering an unexpected response. Despite having a balance in my account, the action defaults to using `gpt-3.5-turbo-16k`…
-
Is it possible to filter and retrieve from the database only based on SQL where clause and without the vector similarity search?
Does the delete SQL query perform full DB scan to find the rows to b…
-
Hello, LanceDb maintainers! Thanks for a great package, I use it every day.
## The issue
We have found a fascinating issue in your dependencies that is mostly caused by errors beyond your contr…
-
### Description
This pattern demonstates an implementation of Retrieval Augmented Generation, making usage of Bedrock, Lambda, and LanceDB embedding store backed by S3.
### language
English
### ru…
-
Hi community, love this amazing tool! Just a nit while using the API, seems LanceDB are mixing to_pandas() and to_df() together. Was wondering, shall we unify these two interface for a cleaner API int…
-
For this piece of typescript:
```
const testSchema = new Schema([
new Field(
"vector",
new FixedSizeList(128, new Field("float32", new Float32()))
),
]);
const newTable…
-
Steps:
1) Add a pdf file to hotdir with Python watch.py running
2) Check to make sure the file is processed through the terminal message running watch.py
3) Go back to anything-llm tab in browser …