docs: add FAQ covering algorithms, integrations, and deployment#36
Merged
Siddhant-K-code merged 7 commits intomainfrom Feb 22, 2026
Merged
docs: add FAQ covering algorithms, integrations, and deployment#36Siddhant-K-code merged 7 commits intomainfrom
Siddhant-K-code merged 7 commits intomainfrom
Conversation
Covers common questions about: - How the dedup pipeline works (clustering, MMR, compression) - LangChain/LlamaIndex integration paths (MCP, HTTP API, planned SDK) - Performance, cost, and scaling characteristics - Deployment and observability options Also links FAQ from README. Co-authored-by: Ona <no-reply@ona.com>
8 key questions inline with <details> toggles, linking to FAQ.md for the full list. Co-authored-by: Ona <no-reply@ona.com>
GitHub renders all details content as underlined when strong is nested inside summary. Co-authored-by: Ona <no-reply@ona.com>
Co-authored-by: Ona <no-reply@ona.com>
Remove cost/latency and embeddings questions. Add cosine vs Euclidean, time complexity, and context window questions. Switch from HTML details/summary to plain markdown. Co-authored-by: Ona <no-reply@ona.com>
Use <p> tags for answer content instead of markdown inside HTML blocks. This prevents GitHub from rendering content as underlined. Co-authored-by: Ona <no-reply@ona.com>
…012) Co-authored-by: Ona <no-reply@ona.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
FAQ.mdwith answers to common questions, organized into five sections:General — What Distill does, semantic vs exact dedup, why not use an LLM for compression
Algorithms — Why agglomerative clustering over K-Means, threshold meaning, MMR formula, time complexity, how rule-based compression works
Integration — Three LangChain integration paths (MCP, HTTP API, planned Python SDK), comparison with LangChain's built-in MMR, support for LlamaIndex/CrewAI/AutoGen, local model compatibility
Performance & Cost — Latency breakdown (~12ms), cost with/without pre-computed embeddings, scaling characteristics
Deployment — Self-hosting options, API key protection, observability stack (Prometheus, OTEL, Grafana)
Also adds:
<details>toggles, linking to FAQ.md for the full list