RAG
by Nicolay Gerold · updated 4mo ago
RAG
- Pipeline RobustQA Avg. score Avg. response time (secs) Azure Cognitive Search Retriever + GPT4 + Ada 72.36 >1.0s Canopy (Pinecone) 59.61 >1.0s Langchain + Pinecone + OpenAI 61.42 <0.8s Langchain + Pinecone + Cohere 69.02 <0.6s LlamaIndex + Weaviate Vector Store - Hybrid Search 75.89 <1.0s RAG Google Cloud VertexAI... See more
from arXiv:2405.02048v1 [cs.IR] 3 May 2024
Nicolay Gerold added 5mo ago
- 1. Synthetic Data for Baseline Metrics¶
Synthetic data can be used to establish baseline precision and recall metrics for your reverse search. The simplest kind of synthetic data is to take existing text chunks, generate synthetic questions, and verify that when we query our synthetic questions, the sourced text chunk is retrieved correctly.
Benefi... See morefrom Low-Hanging Fruit for RAG Search - jxnl.co
Nicolay Gerold added 5mo ago
- Ensuring relevant metadata (e.g., date ranges, file names, ownership) is extracted and searchable is crucial for improving search results.
- Extract relevant metadata from your documents
- Include metadata in your search indexes
- Use query understanding to extract metadata from user queries
- Expand search queries with relevant metadata to improve results
For... See morefrom Systematically Improving Your RAG - jxnl.co
Nicolay Gerold added 4mo ago
- All the recommendation systems you see at Twitter, Facebook, TikTok, YouTube, etc. have a similar high-level architecture.
They have a layered architecture that looks something like the following- Retrieval - Narrow down the candidates of what to show a user to thousands of potential items
- First Stage Ranking - Apply a low-level ranking system to
from The Engineering behind Instagram's Recommendation Algorithm
Nicolay Gerold added 5mo ago
- Unlike some other popular algorithms, DiskANN is designed to keep memory usage to a minimum. This makes it a great match for use cases where Turso already excels at.
#Multitenancy
Turso allows for an easy implementation of a database-per-tenant pattern, where databases can be cheaply created on-demand. Keeping memory consumption at bay is critical f... See morefrom Turso brings Native Vector Search to SQLite
Nicolay Gerold added 4mo ago
- LLMs struggle when handling tasks which require extensive knowledge. This limitation highlights the need to supplement LLMs with non-parametric knowledge. This paper Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts analyze the effects of different types of non-parametric knowledge, such as textu... See more
from Shortwave — rajhesh.panchanadhan@gmail.com [Gmail alternative]
Nicolay Gerold added 5mo ago
- Welcome to RAGatouille
Easily use and train state of the art retrieval methods in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
The main motivation of RAGatouille is simple: bridging the gap between state-of-the-art research and alchemical RAG pipeline practices. RAG is complex, and there are many moving parts. To g... See morefrom GitHub - bclavie/RAGatouille: Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
Nicolay Gerold added 4mo ago
- #################################
# Definition of used LLM
#################################
##########################################################################
def graphPrompt(input: str, metadata={}, model="mixtral:latest"):
if model == None:
model = "mixtral:latest"
chunk_id = metadata.get('chunk_id', None)
# model_info = client.show(model_name=m... See morefrom Knowledge Graph Extraction & Visualization with local LLM from Unstructured Text: a History example
Nicolay Gerold added 5mo ago
Knowledge graph prompt.
- Fast full-text search engine library written in Rust
If you are looking for an alternative to Elasticsearch or Apache Solr, check out Quickwit, our distributed search engine built on top of Tantivy.
Tantivy is closer to Apache Lucene than to Elasticsearch or Apache Solr in the sense it is not an off-the-shelf search engine server, but rather a crat... See morefrom GitHub - quickwit-oss/tantivy: Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust
Nicolay Gerold added 4mo ago