-
Retrieval augmented generation (RAG) is a technique to enrich LLMs with the apps/org own data. It has become very popular as it lowers the complexity entry to enriching input in LLM apps, allows for b…
-
we know if we have more data ,time and power we can do more accuracy predictions, we can do pre-computations and creating one powerful model, but the behavior of each sensor is different
we think how…
-
Hi Barry Menglong Yao
I am a student working on a project on Fact-Checking. We really look up to your project and we think it's a really good model that we would like to reference in our work. We …
f-tes updated
11 months ago
-
1. Prompt Engineering
a. Zero-shot learning
Few-shot learning
Select appropriate key wors
Do not change weights
2. Fine-tuning
a. Instruction-based
b. Domain based
Change the …
-
Code to transform the code graph into database relations.
Should create necessary indices
parent issue: #5
-
Add datasets not yet in MTEB from https://github.com/sdadas/pirb! Would be cool to support this as a benchmark too.
cc @rafalposwiata maybe you know which ones are still missing here? Amazing work on…
-
### 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…
-
Hello,
i am trying to use LlamaIndex and FlagEmbedding together but it is really difficult. Could you provide a simple example of it?
Is there a possibility to train a FlagEmbedding model in python…
-
Hi,
I've trained and evaluated the network with the Shapenet data. Somehow the performance decreases in the retrieval and attention phase, is that something that is supposed to happen? The performa…
-
We all know that the rank will enhance the output of the retrieval model. But how can we see that in the case of MovieLens dataset?