Repository navigation
RDBTC-265 Guide: Building a RAG solution with RavenDB - #2709
Merged
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Issue link
RDBTC-265 Guide: Building a RAG solution with RavenDB
Additional description
SEO re-review: Building a RAG solution with RavenDB
Content quality score: 84/100 (unchanged)
E-E-A-T breakdown
gpt-5.5without saying why.if (this.Summary)guard, the requiredChunkingOptionsForQuerying.AI citation readiness: 76/100 (+4)
The definition under "What is RAG?" is now a clean, quotable sentence. The steps table, the measured results table and the "What we never had to write" table were already easy to quote.
Issues found
Internal links are still thin. This was recommendation 4 last time, which you didn't pick. Step 4 is the core of the guide, and it still has no link to the vector search docs. Candidates:
./embeddings-generation-with-ravendb./new-in-7-0-ravendbs-vector-searchandhttps://docs.ravendb.net/ai-integration/vector-search/vector-search-using-dynamic-query./practical-look-at-ai-agents-with-ravendb./multi-agentsStep 6 doesn't say why it uses
gpt-5.5(line 486). The paragraph explains what the agent model has to handle, then just says "We usegpt-5.5." If you have the result from your 20 answer questions, one clause like "it answered N of 20 correctly" would restore the evidence without mentioning any model that failed. I don't have that number, so I didn't add it.Minor, carried over:
imagein the frontmatter, which guide cards and social previews could use.github.com/poissoncorp, not under theravendborg.Type of change
/templatesor readme)Changes in docs URLs
/scripts/redirects.jsonfile, setDocuments MovedPR label)Changes in UX/UI