-
I'm tracking down a weird bug on a big query, running search locally connected via tunnel to prod ES index. I'm seeing a log message that seems to indicate the query is being chunked into lots of chun…
-
### Is your feature request related to a problem? Please describe
## Background
Current OpenSearch Core support field value configuration in multiple processors, e.g. AppendProcessor, SetProcessor…
-
Is it right to expect llama to be fine tuned to knowledge in the form of unstructured text data from a proprietary text document (chunking text in fixed lengths with langchain text splitter and fi…
-
Hi Greg,
Thanks a lot for you work!
I want to share with more optimized version of your function `combine_sentences` from the [tutorial about text splitting](https://github.com/FullStackRetrieva…
-
**Describe the bug**
Whilst looking into https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/543 I noticed that in ParseNode the chunking functionality is passing `token_counter=lambda text: len(t…
-
Thank you for the amazing work. I'm currently using Langchain's `RecursiveCharacterTextSplitter` to generate chunks for completion. It is currently the bottleneck of my application, so I've been looki…
-
We need to decide how the viewer will know how to split up texts into pages for viewing. For Calpurnius, it's fairly straightforward: obviously, each poem is a reasonable viewing "chunk". But it will …
-
### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a sim…
-
## This is a continuation of the conversation at: https://github.com/josacar/lita-jobs/issues/3
At the moment, any messages larger than MAX_MESSAGE_BYTES are dropped, with an exception raised:
https:…
-
[ghost-draw.txt](https://github.com/SoarGroup/VisualSoar/files/15265960/ghost-draw.txt)
The above file is a .soar file with the extension changed to .txt so github will accept it.
When I try to…