krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-29 16:08:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update semantic-cache-ai-data-retrieval.md

Browse Source 
added rag guide link
This commit is contained in:
Maddie Duhon
2024-09-20 10:16:56 -04:00
committed by GitHub
parent 6dd00c133d
commit b135fc0bc2
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/blog/semantic-cache-ai-data-retrieval.md
+2 -2
View File
@@ -39,9 +39,9 @@ In this blog and video, we will walk you through how to use Qdrant to implement
Semantic cache is increasingly used in Retrieval-Augmented Generation (RAG) applications. In RAG, when a user asks a question, we embed it and search our vector database, either by using keyword, semantic, or hybrid search methods. The matched context is then passed to a Language Model (LLM) along with the prompt and user question for response generation.
Qdrant is recommended for setting up semantic cache as semantically evaluates the response. When semantic cache is implemented, we store common questions and their corresponding answers in a key-value cache. This way, when a user asks a question, we can retrieve the response from the cache if it already exists.
Qdrant is recommended for setting up semantic cache as semantically [evaluates](https://qdrant.tech/rag/rag-evaluation-guide/) the response. When semantic cache is implemented, we store common questions and their corresponding answers in a key-value cache. This way, when a user asks a question, we can retrieve the response from the cache if it already exists.
**Diagram:** Semantic cache improves RAG by directly retrieving stored answers to the user. **Follow along with the gif** and see how semantic cache stores and retrieves answers.
**Diagram:** Semantic cache improves [RAG](https://qdrant.tech/rag/rag-evaluation-guide/) by directly retrieving stored answers to the user. **Follow along with the gif** and see how semantic cache stores and retrieves answers.
![Alt Text](/blog/semantic-cache-ai-data-retrieval/semantic-cache.gif)