Vector Operations & Embeddings

Vector embeddings enable powerful semantic search and similarity matching capabilities in graph databases. Geode supports storing and querying high-dimensional vector embeddings alongside graph data, enabling AI-powered applications that combine relationship traversal with semantic similarity. <h3 id="vector-embedding-fundamentals" class="position-relative d-flex align-items-center group"> Vector Embedding Fundamentals <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="vector-embedding-fundamentals" aria-haspopup="dialog" aria-label="Share link: Vector Embedding Fundamentals"> Share link </button> </h3><div id="headingShareModal" class="heading-share-modal" role="dialog" aria-modal="true" aria-labelledby="headingShareTitle" hidden> <div class="hsm-dialog" role="document"> <div class="hsm-header"> <h2 id="headingShareTitle" class="h6 mb-0 fw-bold">Share this section</h2> <button type="button" class="hsm-close" aria-label="Close"> </button> </div> <div class="hsm-body"> <label for="headingShareInput" class="form-label small text-muted mb-1 text-uppercase fw-bold" style="font-size: 0.7rem; letter-spacing: 0.5px;">Permalink</label> <div class="input-group mb-4 hsm-url-group"> <input id="headingShareInput" type="text" class="form-control font-monospace" readonly aria-readonly="true" style="font-size: 0.85rem;" /> <button class="btn btn-primary hsm-copy" type="button" aria-label="Copy" title="Copy"> </button> </div> <div class="small fw-bold mb-2 text-muted text-uppercase" style="font-size: 0.7rem; letter-spacing: 0.5px;">Share via</div> <div class="hsm-share-grid"> <a id="share-twitter" class="btn btn-outline-secondary w-100" target="_blank" rel="noopener noreferrer"> Twitter </a> <a id="share-linkedin" class="btn btn-outline-secondary w-100" target="_blank" rel="noopener noreferrer"> LinkedIn </a> <a id="share-facebook" class="btn btn-outline-secondary w-100" target="_blank" rel="noopener noreferrer"> Facebook </a> </div> </div> </div> </div> <style> .heading-share-modal { position: fixed; inset: 0; display: flex; justify-content: center; align-items: center; background: rgba(0, 0, 0, 0.6); z-index: 1050; padding: 1rem; backdrop-filter: blur(4px); -webkit-backdrop-filter: blur(4px); } .heading-share-modal[hidden] { display: none !important; } .hsm-dialog { max-width: 420px; width: 100%; background: var(--bs-body-bg, #fff); color: var(--bs-body-color, #212529); border: 1px solid var(--bs-border-color, rgba(0,0,0,0.1)); border-radius: 1rem; box-shadow: 0 25px 50px -12px rgba(0, 0, 0, 0.25); overflow: hidden; animation: hsm-fade-in 0.2s ease-out; } @keyframes hsm-fade-in { from { opacity: 0; transform: scale(0.95); } to { opacity: 1; transform: scale(1); } } [data-bs-theme="dark"] .hsm-dialog { background: #1e293b; border-color: rgba(255,255,255,0.1); color: #f8f9fa; } .hsm-header { display: flex; justify-content: space-between; align-items: center; padding: 1rem 1.5rem; border-bottom: 1px solid var(--bs-border-color, rgba(0,0,0,0.1)); background: rgba(0,0,0,0.02); } [data-bs-theme="dark"] .hsm-header { background: rgba(255,255,255,0.02); border-color: rgba(255,255,255,0.1); } .hsm-close { background: transparent; border: none; color: inherit; opacity: 0.5; padding: 0.25rem 0.5rem; border-radius: 0.25rem; font-size: 1.2rem; line-height: 1; transition: opacity 0.2s; } .hsm-close:hover { opacity: 1; } .hsm-body { padding: 1.5rem; } .hsm-url-group { display: flex !important; align-items: stretch; } .hsm-url-group .form-control { flex: 1; min-width: 0; margin: 0; background: var(--bs-secondary-bg, #f8f9fa); border-color: var(--bs-border-color, #dee2e6); border-top-right-radius: 0; border-bottom-right-radius: 0; height: 42px; } .hsm-url-group .btn { flex: 0 0 auto; margin: 0; margin-left: -1px; border-top-left-radius: 0; border-bottom-left-radius: 0; height: 42px; display: flex; align-items: center; justify-content: center; padding: 0 1.25rem; z-index: 2; } [data-bs-theme="dark"] .hsm-url-group .form-control { background: #0f172a; border-color: #334155; color: #e2e8f0; } .hsm-share-grid { display: flex; flex-direction: column; gap: 0.5rem; } .hsm-share-grid .btn { display: flex; align-items: center; justify-content: center; font-size: 0.9rem; padding: 0.6rem; border-color: var(--bs-border-color); width: 100%; } [data-bs-theme="dark"] .hsm-share-grid .btn { color: #e2e8f0; border-color: #475569; } [data-bs-theme="dark"] .hsm-share-grid .btn:hover { background: #334155; border-color: #cbd5e1; } </style> <script> (function(){ const modal = document.getElementById('headingShareModal'); if(!modal) return; const input = modal.querySelector('#headingShareInput'); const copyBtn = modal.querySelector('.hsm-copy'); const twitter = modal.querySelector('#share-twitter'); const linkedin = modal.querySelector('#share-linkedin'); const facebook = modal.querySelector('#share-facebook'); const closeBtn = modal.querySelector('.hsm-close'); let lastFocus=null; let trapBound=false; function buildUrl(id){ return window.location.origin + window.location.pathname + '#' + id; } function isOpen(){ return !modal.hasAttribute('hidden'); } function hydrate(id){ const url=buildUrl(id); input.value=url; const enc=encodeURIComponent(url); const text=encodeURIComponent(document.title); if(twitter) twitter.href=`https://twitter.com/intent/tweet?url=${enc}&text=${text}`; if(linkedin) linkedin.href=`https://www.linkedin.com/sharing/share-offsite/?url=${enc}`; if(facebook) facebook.href=`https://www.facebook.com/sharer/sharer.php?u=${enc}`; } function openModal(id){ lastFocus=document.activeElement; hydrate(id); if(!isOpen()){ modal.removeAttribute('hidden'); } requestAnimationFrame(()=>{ input.focus(); }); trapFocus(); } function closeModal(){ if(!isOpen()) return; modal.setAttribute('hidden',''); if(lastFocus && typeof lastFocus.focus==='function') lastFocus.focus(); } function copyCurrent(){ try{ navigator.clipboard.writeText(input.value).then(()=>feedback(true),()=>fallback()); } catch(e){ fallback(); } } function fallback(){ input.select(); try{ document.execCommand('copy'); feedback(true);}catch(e){ feedback(false);} } function feedback(ok){ if(!copyBtn) return; const icon=copyBtn.querySelector('i'); if(!icon) return; const prev=copyBtn.getAttribute('data-prev')||icon.className; if(!copyBtn.getAttribute('data-prev')) copyBtn.setAttribute('data-prev',prev); icon.className= ok ? 'fa-duotone fa-clipboard-check':'fa-duotone fa-circle-exclamation'; setTimeout(()=>{ icon.className=prev; },1800); } function handleShareClick(e){ e.preventDefault(); const btn=e.currentTarget; const id=btn.getAttribute('data-share-target'); if(id) openModal(id); } function bindShareButtons(){ document.querySelectorAll('.h-share').forEach(btn=>{ if(!btn.dataset.hShareBound){ btn.addEventListener('click', handleShareClick); btn.dataset.hShareBound='1'; } }); } bindShareButtons(); if(document.readyState==='loading'){ document.addEventListener('DOMContentLoaded', bindShareButtons); } else { requestAnimationFrame(bindShareButtons); } document.addEventListener('click', function(e){ const shareBtn=e.target.closest && e.target.closest('.h-share'); if(shareBtn && !shareBtn.dataset.hShareBound){ handleShareClick.call(shareBtn, e); } }, true); document.addEventListener('click', e=>{ if(e.target===modal) closeModal(); if(e.target.closest && e.target.closest('.hsm-close')){ e.preventDefault(); closeModal(); } if(copyBtn && (e.target===copyBtn || (e.target.closest && e.target.closest('.hsm-copy')))) { e.preventDefault(); copyCurrent(); } }); document.addEventListener('keydown', e=>{ if(e.key==='Escape' && isOpen()) closeModal(); }); function trapFocus(){ if(trapBound) return; trapBound=true; modal.addEventListener('keydown', f=>{ if(f.key==='Tab' && isOpen()){ const focusable=[...modal.querySelectorAll('a[href],button,input,textarea,select,[tabindex]:not([tabindex="-1"])')].filter(el=>!el.hasAttribute('disabled')); if(!focusable.length) return; const first=focusable[0]; const last=focusable[focusable.length-1]; if(f.shiftKey && document.activeElement===first){ f.preventDefault(); last.focus(); } else if(!f.shiftKey && document.activeElement===last){ f.preventDefault(); first.focus(); } } }); } if(closeBtn) closeBtn.addEventListener('click', e=>{ e.preventDefault(); closeModal(); }); })(); </script>Vector embeddings are numerical representations of data (text, images, or other content) in high-dimensional space where semantic similarity corresponds to geometric proximity. <h4 id="use-cases-for-vector-embeddings" class="position-relative d-flex align-items-center group"> Use Cases for Vector Embeddings <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="use-cases-for-vector-embeddings" aria-haspopup="dialog" aria-label="Share link: Use Cases for Vector Embeddings"> Share link </button> </h4>Semantic Search Find content based on meaning rather than exact keyword matches: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Store document with embedding CREATE (:Document { id: 'doc123', title: 'Introduction to Graph Databases', content: 'Graph databases excel at modeling...', embedding: [0.23, -0.45, 0.67, ...] -- 384-dimensional vector }) -- Find similar documents using cosine similarity MATCH (d:Document) WHERE d.id <> $query_doc_id WITH d, cosine_similarity(d.embedding, $query_embedding) as similarity WHERE similarity > 0.75 RETURN d.title, d.content, similarity ORDER BY similarity DESC LIMIT 10 </code></pre></div>Recommendation Systems Combine collaborative filtering with content similarity: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Recommend based on semantic similarity and graph relationships MATCH (user:User {id: $user_id})-[:LIKED]->(item:Product) WITH avg(item.embedding) as user_preference_vector MATCH (candidate:Product) WHERE NOT (user)-[:LIKED|:PURCHASED]->(candidate) WITH candidate, cosine_similarity(candidate.embedding, user_preference_vector) as content_sim, size((candidate)<-[:LIKED]-(:User)-[:LIKED]->(item)) as collab_score RETURN candidate.name, content_sim, collab_score, (content_sim * 0.6 + collab_score * 0.4) as combined_score ORDER BY combined_score DESC LIMIT 10 </code></pre></div>Question Answering Match questions to relevant knowledge base articles: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Store FAQ with question embedding CREATE (:FAQ { question: 'How do I create an index in Geode?', answer: 'Use CREATE INDEX command...', question_embedding: [...] -- Vector from embedding model }) -- Find best matching FAQ MATCH (faq:FAQ) WITH faq, cosine_similarity(faq.question_embedding, $user_question_embedding) as score WHERE score > 0.7 RETURN faq.question, faq.answer, score ORDER BY score DESC LIMIT 1 </code></pre></div> <h3 id="storing-vector-embeddings" class="position-relative d-flex align-items-center group"> Storing Vector Embeddings <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="storing-vector-embeddings" aria-haspopup="dialog" aria-label="Share link: Storing Vector Embeddings"> Share link </button> </h3>Geode stores vectors as property arrays on nodes and relationships. <h4 id="embedding-models" class="position-relative d-flex align-items-center group"> Embedding Models <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="embedding-models" aria-haspopup="dialog" aria-label="Share link: Embedding Models"> Share link </button> </h4>Common embedding models and their dimensions: Text Embeddings: <ul> <li><code>sentence-transformers/all-MiniLM-L6-v2</code>: 384 dimensions</li> <li><code>text-embedding-ada-002</code> (OpenAI): 1536 dimensions</li> <li><code>bert-base-uncased</code>: 768 dimensions</li> </ul> Image Embeddings: <ul> <li><code>CLIP</code>: 512 dimensions</li> <li><code>ResNet-50</code>: 2048 dimensions</li> </ul> Code Embeddings: <ul> <li><code>codebert-base</code>: 768 dimensions</li> </ul> <h4 id="embedding-generation" class="position-relative d-flex align-items-center group"> Embedding Generation <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="embedding-generation" aria-haspopup="dialog" aria-label="Share link: Embedding Generation"> Share link </button> </h4>Generate embeddings using external models before storing: Python Example with SentenceTransformers: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">from sentence_transformers import SentenceTransformer from geode_client import Client model = SentenceTransformer('all-MiniLM-L6-v2') async def store_document_with_embedding(client, doc_id, title, content): # Generate embedding embedding = model.encode(content).tolist() # Store in Geode async with client.connection() as conn: await conn.execute(""" CREATE (:Document { id: $id, title: $title, content: $content, embedding: $embedding }) """, { "id": doc_id, "title": title, "content": content, "embedding": embedding }) </code></pre></div>Go Example with OpenAI: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-go" data-lang="go">import ( "context" openai "github.com/sashabaranov/go-openai" "geodedb.com/geode" ) func storeProductWithEmbedding(ctx context.Context, db *sql.DB, product Product) error { client := openai.NewClient(apiKey) // Generate embedding resp, err := client.CreateEmbeddings(ctx, openai.EmbeddingRequest{ Model: openai.AdaEmbeddingV2, Input: []string{product.Description}, }) if err != nil { return err } embedding := resp.Data[0].Embedding // Store in Geode _, err = db.ExecContext(ctx, ` CREATE (:Product { id: $1, name: $2, description: $3, embedding: $4 }) `, product.ID, product.Name, product.Description, embedding) return err } </code></pre></div> <h3 id="vector-similarity-functions" class="position-relative d-flex align-items-center group"> Vector Similarity Functions <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="vector-similarity-functions" aria-haspopup="dialog" aria-label="Share link: Vector Similarity Functions"> Share link </button> </h3>Geode provides built-in functions for computing vector similarity. <h4 id="cosine-similarity" class="position-relative d-flex align-items-center group"> Cosine Similarity <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="cosine-similarity" aria-haspopup="dialog" aria-label="Share link: Cosine Similarity"> Share link </button> </h4>Measures angle between vectors (range: -1 to 1): <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Find similar products MATCH (p:Product) WITH p, cosine_similarity(p.embedding, $query_embedding) as similarity WHERE similarity > 0.8 RETURN p.name, similarity ORDER BY similarity DESC </code></pre></div>Properties: <ul> <li>Range: -1 (opposite) to 1 (identical)</li> <li>Normalized by vector magnitude</li> <li>Best for normalized embeddings</li> </ul> <h4 id="euclidean-distance" class="position-relative d-flex align-items-center group"> Euclidean Distance <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="euclidean-distance" aria-haspopup="dialog" aria-label="Share link: Euclidean Distance"> Share link </button> </h4>Measures geometric distance between vectors: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">MATCH (p:Product) WITH p, euclidean_distance(p.embedding, $query_embedding) as distance WHERE distance < 10.0 RETURN p.name, distance ORDER BY distance ASC </code></pre></div>Properties: <ul> <li>Range: 0 (identical) to infinity</li> <li>Sensitive to vector magnitude</li> <li>Useful for absolute distance metrics</li> </ul> <h4 id="dot-product" class="position-relative d-flex align-items-center group"> Dot Product <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="dot-product" aria-haspopup="dialog" aria-label="Share link: Dot Product"> Share link </button> </h4>Computes inner product of vectors: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">MATCH (p:Product) WITH p, dot_product(p.embedding, $query_embedding) as score WHERE score > 0.5 RETURN p.name, score ORDER BY score DESC </code></pre></div>Properties: <ul> <li>Range: unbounded</li> <li>Faster computation than cosine similarity</li> <li>Best when embeddings are pre-normalized</li> </ul> <h3 id="hybrid-graph-vector-queries" class="position-relative d-flex align-items-center group"> Hybrid Graph-Vector Queries <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="hybrid-graph-vector-queries" aria-haspopup="dialog" aria-label="Share link: Hybrid Graph-Vector Queries"> Share link </button> </h3>Combine graph traversal with vector similarity for powerful queries. <h4 id="multi-hop-similarity-search" class="position-relative d-flex align-items-center group"> Multi-Hop Similarity Search <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="multi-hop-similarity-search" aria-haspopup="dialog" aria-label="Share link: Multi-Hop Similarity Search"> Share link </button> </h4>Find similar content through relationship paths: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Find related papers via citation network with semantic similarity MATCH (start:Paper {id: $paper_id})-[:CITES*1..3]->(related:Paper) WITH related, length(path) as citation_distance, cosine_similarity(related.embedding, start.embedding) as semantic_similarity WHERE semantic_similarity > 0.6 RETURN related.title, citation_distance, semantic_similarity, (1.0 / citation_distance) * semantic_similarity as combined_score ORDER BY combined_score DESC LIMIT 10 </code></pre></div> <h4 id="relationship-aware-recommendations" class="position-relative d-flex align-items-center group"> Relationship-Aware Recommendations <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="relationship-aware-recommendations" aria-haspopup="dialog" aria-label="Share link: Relationship-Aware Recommendations"> Share link </button> </h4>Use graph structure to filter similarity candidates: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Recommend users with similar interests who share connections MATCH (user:User {id: $user_id})-[:FRIENDS_WITH*1..2]->(connection:User) WHERE connection <> user WITH connection, cosine_similarity(connection.interest_embedding, user.interest_embedding) as similarity WHERE similarity > 0.7 AND NOT (user)-[:FRIENDS_WITH]->(connection) RETURN connection.name, similarity, size((user)-[:FRIENDS_WITH*1..2]-(connection)) as mutual_connections ORDER BY similarity DESC, mutual_connections DESC LIMIT 20 </code></pre></div> <h4 id="semantic-community-detection" class="position-relative d-flex align-items-center group"> Semantic Community Detection <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="semantic-community-detection" aria-haspopup="dialog" aria-label="Share link: Semantic Community Detection"> Share link </button> </h4>Identify clusters based on semantic similarity: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Find users with similar interests forming communities MATCH (u1:User)-[:INTERESTED_IN]->(topic:Topic) MATCH (u2:User)-[:INTERESTED_IN]->(topic) WHERE u1.id < u2.id WITH u1, u2, cosine_similarity(u1.profile_embedding, u2.profile_embedding) as similarity WHERE similarity > 0.75 CREATE (u1)-[:SIMILAR_TO {score: similarity}]->(u2) CREATE (u2)-[:SIMILAR_TO {score: similarity}]->(u1) -- Detect communities using connected components MATCH (user:User)-[:SIMILAR_TO*]-(community_member:User) RETURN collect(DISTINCT community_member.id) as community </code></pre></div> <h3 id="vector-indexing-and-performance" class="position-relative d-flex align-items-center group"> Vector Indexing and Performance <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="vector-indexing-and-performance" aria-haspopup="dialog" aria-label="Share link: Vector Indexing and Performance"> Share link </button> </h3>Optimize vector similarity search through indexing strategies. <h4 id="approximate-nearest-neighbor-ann-indexes" class="position-relative d-flex align-items-center group"> Approximate Nearest Neighbor (ANN) Indexes <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="approximate-nearest-neighbor-ann-indexes" aria-haspopup="dialog" aria-label="Share link: Approximate Nearest Neighbor (ANN) Indexes"> Share link </button> </h4>For large-scale vector search, use ANN indexes: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Create HNSW index for fast similarity search CREATE VECTOR INDEX product_embedding_idx ON Product(embedding) USING HNSW WITH { dimensions: 384, distance_metric: 'cosine', m: 16, -- Number of connections per layer ef_construction: 200 -- Size of dynamic candidate list } </code></pre></div>Index Types: HNSW (Hierarchical Navigable Small World) <ul> <li>Fast approximate search</li> <li>Good recall/performance trade-off</li> <li>Memory intensive</li> </ul> IVF (Inverted File Index) <ul> <li>Partitions vector space into clusters</li> <li>Lower memory footprint</li> <li>Configurable speed/accuracy trade-off</li> </ul> <h4 id="query-performance-tuning" class="position-relative d-flex align-items-center group"> Query Performance Tuning <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="query-performance-tuning" aria-haspopup="dialog" aria-label="Share link: Query Performance Tuning"> Share link </button> </h4>Optimize vector queries for performance: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Use index hints for vector search MATCH (p:Product) USING INDEX product_embedding_idx WITH p, cosine_similarity(p.embedding, $query_embedding) as similarity WHERE similarity > 0.8 RETURN p.name, similarity ORDER BY similarity DESC LIMIT 10 </code></pre></div>Performance Tips: <ul> <li>Pre-normalize embeddings when using cosine similarity</li> <li>Use appropriate similarity thresholds to limit candidates</li> <li>Consider approximate search for large datasets (>100K vectors)</li> <li>Batch vector operations when possible</li> </ul> <h4 id="memory-considerations" class="position-relative d-flex align-items-center group"> Memory Considerations <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="memory-considerations" aria-haspopup="dialog" aria-label="Share link: Memory Considerations"> Share link </button> </h4>Vector storage requirements: <table> <thead> <tr> <th>Dimension</th> <th>Data Type</th> <th>Memory per Vector</th> </tr> </thead> <tbody> <tr> <td>384</td> <td>float32</td> <td>1.5 KB</td> </tr> <tr> <td>768</td> <td>float32</td> <td>3 KB</td> </tr> <tr> <td>1536</td> <td>float32</td> <td>6 KB</td> </tr> </tbody> </table> For 1M documents with 384-dim embeddings: ~1.5 GB vector storage. <h3 id="embedding-update-strategies" class="position-relative d-flex align-items-center group"> Embedding Update Strategies <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="embedding-update-strategies" aria-haspopup="dialog" aria-label="Share link: Embedding Update Strategies"> Share link </button> </h3>Handle embedding updates as content changes. <h4 id="incremental-updates" class="position-relative d-flex align-items-center group"> Incremental Updates <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="incremental-updates" aria-haspopup="dialog" aria-label="Share link: Incremental Updates"> Share link </button> </h4>Update embeddings when content changes: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">async def update_document_embedding(client, doc_id, new_content): # Generate new embedding new_embedding = model.encode(new_content).tolist() # Update in transaction async with client.connection() as conn: await conn.begin() try: await conn.execute(""" MATCH (d:Document {id: $doc_id}) SET d.content = $content, d.embedding = $embedding, d.updated_at = current_timestamp() """, { "doc_id": doc_id, "content": new_content, "embedding": new_embedding }) await conn.commit() except Exception: await conn.rollback() raise </code></pre></div> <h4 id="batch-reindexing" class="position-relative d-flex align-items-center group"> Batch Reindexing <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="batch-reindexing" aria-haspopup="dialog" aria-label="Share link: Batch Reindexing"> Share link </button> </h4>Regenerate all embeddings when upgrading models: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">async def reindex_all_documents(client, batch_size=100): # Fetch documents without embeddings or old model async with client.connection() as conn: result, _ = await conn.query(""" MATCH (d:Document) WHERE d.embedding IS NULL OR d.embedding_model <> $current_model RETURN d.id, d.content """, {"current_model": "all-MiniLM-L6-v2"}) docs = [ {"id": row["d.id"].raw_value, "content": row["d.content"].raw_value} for row in result.rows ] # Process in batches for i in range(0, len(docs), batch_size): batch = docs[i:i+batch_size] # Generate embeddings contents = [doc['content'] for doc in batch] embeddings = model.encode(contents).tolist() # Update in transaction async with client.connection() as conn: await conn.begin() try: for doc, embedding in zip(batch, embeddings): await conn.execute(""" MATCH (d:Document {id: $doc_id}) SET d.embedding = $embedding, d.embedding_model = $model """, { "doc_id": doc['id'], "embedding": embedding, "model": "all-MiniLM-L6-v2" }) await conn.commit() except Exception: await conn.rollback() raise </code></pre></div> <h3 id="real-world-applications" class="position-relative d-flex align-items-center group"> Real-World Applications <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="real-world-applications" aria-haspopup="dialog" aria-label="Share link: Real-World Applications"> Share link </button> </h3> <h4 id="semantic-code-search" class="position-relative d-flex align-items-center group"> Semantic Code Search <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="semantic-code-search" aria-haspopup="dialog" aria-label="Share link: Semantic Code Search"> Share link </button> </h4>Search codebases by functionality rather than syntax: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Store code snippets with embeddings CREATE (:CodeSnippet { id: 'snippet123', language: 'python', code: 'def calculate_similarity(vec1, vec2): return cosine(vec1, vec2)', description: 'Calculate cosine similarity between two vectors', embedding: [...] -- Generated from code + description }) -- Search by natural language query MATCH (snippet:CodeSnippet) WHERE snippet.language = $language WITH snippet, cosine_similarity(snippet.embedding, $query_embedding) as relevance WHERE relevance > 0.7 RETURN snippet.code, snippet.description, relevance ORDER BY relevance DESC LIMIT 5 </code></pre></div> <h4 id="multi-modal-search" class="position-relative d-flex align-items-center group"> Multi-Modal Search <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="multi-modal-search" aria-haspopup="dialog" aria-label="Share link: Multi-Modal Search"> Share link </button> </h4>Combine text and image embeddings: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Store product with text and image embeddings CREATE (:Product { id: 'prod456', name: 'Red Running Shoes', description: 'Lightweight athletic footwear...', text_embedding: [...], -- From description image_embedding: [...] -- From product images }) -- Search using text or image query MATCH (p:Product) WITH p, cosine_similarity(p.text_embedding, $text_query_embedding) as text_sim, cosine_similarity(p.image_embedding, $image_query_embedding) as image_sim WITH p, CASE WHEN $query_type = 'text' THEN text_sim WHEN $query_type = 'image' THEN image_sim ELSE (text_sim + image_sim) / 2 END as similarity WHERE similarity > 0.75 RETURN p.name, similarity ORDER BY similarity DESC </code></pre></div> <h4 id="conversational-ai-context" class="position-relative d-flex align-items-center group"> Conversational AI Context <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="conversational-ai-context" aria-haspopup="dialog" aria-label="Share link: Conversational AI Context"> Share link </button> </h4>Maintain conversation context using embeddings: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Store conversation turns with embeddings CREATE (turn:ConversationTurn { id: 'turn123', user_id: 'user456', message: 'How do I optimize graph queries?', embedding: [...], timestamp: current_timestamp() }) -- Find relevant context for current query MATCH (turn:ConversationTurn) WHERE turn.user_id = $user_id AND turn.timestamp > current_timestamp() - duration('PT1H') WITH turn, cosine_similarity(turn.embedding, $current_query_embedding) as relevance WHERE relevance > 0.6 RETURN turn.message, turn.response, relevance ORDER BY relevance DESC, turn.timestamp DESC LIMIT 5 </code></pre></div> <h3 id="best-practices" class="position-relative d-flex align-items-center group"> Best Practices <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="best-practices" aria-haspopup="dialog" aria-label="Share link: Best Practices"> Share link </button> </h3> <h4 id="choose-appropriate-embedding-models" class="position-relative d-flex align-items-center group"> Choose Appropriate Embedding Models <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="choose-appropriate-embedding-models" aria-haspopup="dialog" aria-label="Share link: Choose Appropriate Embedding Models"> Share link </button> </h4>Select models based on requirements: <ul> <li>Speed-critical applications: Use smaller models (384-dim)</li> <li>High-accuracy needs: Use larger models (768-1536-dim)</li> <li>Multi-lingual: Use models trained on multiple languages</li> <li>Domain-specific: Fine-tune models on domain data</li> </ul> <h4 id="normalize-embeddings" class="position-relative d-flex align-items-center group"> Normalize Embeddings <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="normalize-embeddings" aria-haspopup="dialog" aria-label="Share link: Normalize Embeddings"> Share link </button> </h4>Pre-normalize embeddings for cosine similarity: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">def normalize_embedding(embedding): norm = np.linalg.norm(embedding) return (embedding / norm).tolist() embedding = model.encode(text) normalized = normalize_embedding(embedding) </code></pre></div> <h4 id="set-appropriate-similarity-thresholds" class="position-relative d-flex align-items-center group"> Set Appropriate Similarity Thresholds <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="set-appropriate-similarity-thresholds" aria-haspopup="dialog" aria-label="Share link: Set Appropriate Similarity Thresholds"> Share link </button> </h4>Tune thresholds based on precision/recall requirements: <ul> <li>High precision: threshold > 0.85 (fewer, more relevant results)</li> <li>High recall: threshold > 0.65 (more results, some less relevant)</li> <li>Balanced: threshold > 0.75</li> </ul> <h4 id="monitor-embedding-quality" class="position-relative d-flex align-items-center group"> Monitor Embedding Quality <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="monitor-embedding-quality" aria-haspopup="dialog" aria-label="Share link: Monitor Embedding Quality"> Share link </button> </h4>Track embedding quality metrics: <ul> <li>Average similarity scores</li> <li>Precision/recall for known test cases</li> <li>User engagement with recommended content</li> <li>A/B test different embedding models</li> </ul> <h3 id="future-enhancements" class="position-relative d-flex align-items-center group"> Future Enhancements <button type="button" class="h-share btn btn-link p-0 text-decoration-none link-secondary opacity-50 hover-opacity-100 transition-all ms-1" data-share-target="future-enhancements" aria-haspopup="dialog" aria-label="Share link: Future Enhancements"> Share link </button> </h3>Geode’s vector capabilities continue to evolve: <ul> <li>Native ANN index support (HNSW, IVF-PQ)</li> <li>Quantized embedding storage for reduced memory</li> <li>GPU-accelerated similarity computation</li> <li>Multi-vector queries (combine multiple embeddings)</li> <li>Embedding versioning and A/B testing</li> </ul> Vector embeddings combined with Geode’s graph capabilities enable powerful AI-enhanced applications that leverage both semantic similarity and relationship structure for superior results.

Popular

Related Articles

Data Model and Types