-
also I tried both `method="llama.cpp"` and without.
trying LLM from local path gives:
```
Traceback (most recent call last):
File "/Users/szymon/git/my-first-llm-rag/query.py", line 7, in
…
-
### Description
With this repo I want to showcase how to implement a streaming serverless Retrieval Augmented Generation (RAG) architecture.
Customers asked for a way to quickly test RAG capabilitie…
-
Here is my HF format of exllamav2 model
```python
import torch, os
from contextlib import contextmanager
from pathlib import Path
from typing import Optional, List, Union, Dict
from transforme…
-
### The Feature
A new endpoint that allows users to generate embeddings for text, code, or other data formats. Embeddings are vector representations of data that can be used for a variety of tasks, s…
-
I created a retriever implementing the langchain_community.retrievers.bedrock AmazonKnowledgeBasesRetriever. This is then ran through the RetrievalQA chain from LangChain, but when being wrapped by th…
-
**Is your feature request related to a problem?**
The RAG pipeline does not know how to pass "inputs" and return "completion" from Bedrock's Anthropic model.
**What solution would you like?**
As …
-
Hi, I encounter the same problem as in https://github.com/facebookresearch/LAMA/issues/10.
And I found the reason why 2 examples are filtered is that the `obj_label` are `1970s` and `1990s`. And in `…
-
**What do you want to do?**
- [x ] Request a change to existing documentation
- [ ] Add new documentation
- [ ] Report a technical problem with the documentation
- [ ] Other
**Tell us about…
-
### Feature Description
LlamaIndex can be thought of as an orchestrator and prompt management system across various subtasks.
Here is a proposed ontology of a retrieval pipeline:
1. `session`: …
-
I want to evaluate a single completion of my LLM.
Code:
```python
from ragas import evaluate
from datasets import Dataset
import os
# prepare your huggingface dataset in the format
# Datase…