RRepoGEO

REPOGEO REPORT · LITE

ggozad/haiku.rag

Default branch main · commit 61f27085 · scanned 6/14/2026, 4:27:11 PM

GitHub: 538 stars · 36 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface ggozad/haiku.rag, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Rewrite README intro to clarify scope, 'Haiku' meaning, and core differentiators

    Why:

    CURRENT
    Agentic RAG built on LanceDB, Pydantic AI, and Docling.
    COPY-PASTE FIX
    Haiku RAG is an opinionated, advanced agentic RAG *system* (not just an example) built on LanceDB, Pydantic AI, and Docling. The 'Haiku' in its name refers to Google Gemini Haiku, emphasizing its compact and efficient design. It excels at multimodal and cross-modal search, vision QA, complex multi-document analysis via sandboxed Python, and conversational AI, making it suitable for sophisticated RAG applications.
  • mediumhomepage#2
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    https://github.com/ggozad/haiku.rag
  • lowtopics#3
    Refine repository topics to better reflect advanced and multimodal capabilities

    Why:

    CURRENT
    ai, docling, lancedb, mcp, mcp-server, ml, pydantic-ai, rag
    COPY-PASTE FIX
    ai, rag, agentic-ai, multimodal-ai, vision-qa, conversational-ai, lancedb, pydantic-ai, docling, llm-applications

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface ggozad/haiku.rag
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
LlamaIndex
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. LlamaIndex · recommended 2×
  2. Haystack · recommended 2×
  3. LangChain · recommended 2×
  4. CLIP · recommended 1×
  5. OpenCLIP · recommended 1×
  • CATEGORY QUERY
    How can I build a RAG system that understands both text and images?
    you: not recommended
    AI recommended (in order):
    1. LlamaIndex
    2. CLIP
    3. OpenCLIP
    4. LLaVA
    5. Fuyu-8B
    6. GPT-4V
    7. Haystack
    8. InMemoryDocumentStore
    9. ElasticsearchDocumentStore
    10. PineconeDocumentStore
    11. DensePassageRetriever
    12. PromptNode
    13. LangChain
    14. Chroma
    15. Pinecone
    16. FAISS
    17. MultimodalRetriever
    18. Hugging Face Transformers
    19. CLIPModel
    20. CLIPProcessor
    21. Annoy
    22. Google Cloud Vertex AI Multimodal Embeddings
    23. Gemini Pro Vision
    24. Vertex AI Vector Search
    25. Azure AI Vision
    26. Azure OpenAI Service
    27. Azure AI Search

    AI recommended 27 alternatives but never named ggozad/haiku.rag. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking an advanced RAG framework for complex multi-document analysis and conversational AI.
    you: not recommended
    AI recommended (in order):
    1. LlamaIndex
    2. LangChain
    3. Haystack
    4. RAGatouille
    5. DSPy

    AI recommended 5 alternatives but never named ggozad/haiku.rag. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of ggozad/haiku.rag?
    pass
    AI named ggozad/haiku.rag explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts ggozad/haiku.rag in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ggozad/haiku.rag explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo ggozad/haiku.rag solve, and who is the primary audience?
    pass
    AI named ggozad/haiku.rag explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of ggozad/haiku.rag. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/ggozad/haiku.rag.svg)](https://repogeo.com/en/r/ggozad/haiku.rag)
HTML
<a href="https://repogeo.com/en/r/ggozad/haiku.rag"><img src="https://repogeo.com/badge/ggozad/haiku.rag.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ggozad/haiku.rag — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite