-
As we know, data used in RAG applications comes from all kinds of sources, and while its easy to work with unstructured data that is in a text format like markdown, html, txt, json, etc, it is not so …
Hisma updated
6 months ago
-
I use spacy-llm for RAG, so I have integrated pretty deeply into it and 0.7.0 broke my method of prompt generation. In the process of fixing it, I've noticed something that may be a more general bug.
…
-
Through Ollama, there is a wide selection of embedding models available, and the operation is very efficient. Supporting Ollama's embedding models will effectively enhance the convenience of use.
-
_posting for Prof Izbicki but all feedback is welcome_
I’m working on a project that aims to preserve memories by allowing users to upload stories about loved ones who have passed away. The system…
-
# Problem
I've been toying around with RAG using `ollama` and `llama-index`.
The results I am getting with `llama3 8b` are not that good, so I was happy to see `llama3-chatqa` being added in `v0.1.…
-
- keep a hideable screen that keeps track of the suggested metrics
- Add ability to approve, reject, edit suggested metrics
- look at the feasibility of adding ability to chat about a particular…
-
Hello,
As I was trying to work this into a Graph LLM Rag. I was thinking on doing some queries based on data type (example: node is a 'person', 'skill', ...).
The idea was to have a person A, id…
-
**Is your feature request related to a problem? Please describe.**
Measuring search quality is changing quickly in the world of vectors and embeddings and LLMs. What do we need as search engineers …
epugh updated
9 months ago
-
**Bug Description**
An error occurred:
**To Reproduce**
```python
from trulens.apps.langchain import TruChain
from langchain_community.vectorstores import Qdrant
def invoke_conv…
-
### Describe the bug
The `langchain_community.callbacks.tracers.wandb.WandbTracer` fails to log any trace or model information to WandB for langchain models. The tracer is incompatible with the lat…