AI and Machine Learning Integration with Geode

<h2 id="ai-and-machine-learning-integration-with-geode" class="position-relative d-flex align-items-center group"> AI and Machine Learning Integration with Geode <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="ai-and-machine-learning-integration-with-geode" aria-haspopup="dialog" aria-label="Share link: AI and Machine Learning Integration with Geode"> Share link </button> </h2><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>Geode provides native support for AI and machine learning workloads through vector similarity search, embedding storage, and seamless integration with modern ML pipelines. This page covers the patterns and best practices for building intelligent applications that combine graph traversals with AI capabilities. <h3 id="introduction-to-ai-powered-graph-applications" class="position-relative d-flex align-items-center group"> Introduction to AI-Powered Graph 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="introduction-to-ai-powered-graph-applications" aria-haspopup="dialog" aria-label="Share link: Introduction to AI-Powered Graph Applications"> Share link </button> </h3>Graph databases and artificial intelligence are natural partners. While graphs excel at modeling relationships and enabling complex traversals, AI adds semantic understanding, pattern recognition, and predictive capabilities. Geode bridges these worlds with: <ul> <li>Native Vector Search: HNSW indexes for efficient similarity search over embeddings</li> <li>Hybrid Queries: Combine graph traversals with vector similarity in single queries</li> <li>ML Pipeline Integration: Connect to embedding models, LLMs, and ML frameworks</li> <li>Knowledge Graph Support: Store and query structured knowledge for AI applications</li> </ul> <h4 id="why-combine-graphs-with-ai" class="position-relative d-flex align-items-center group"> Why Combine Graphs with AI? <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="why-combine-graphs-with-ai" aria-haspopup="dialog" aria-label="Share link: Why Combine Graphs with AI?"> Share link </button> </h4>Traditional AI applications often struggle with: <ul> <li>Context: Understanding relationships between entities</li> <li>Explainability: Tracing how conclusions were reached</li> <li>Knowledge Integration: Combining learned patterns with structured facts</li> <li>Multi-hop Reasoning: Following chains of relationships</li> </ul> Geode addresses these challenges by providing a unified platform where AI models can leverage graph structure for richer, more accurate results. <h3 id="vector-search-and-embeddings" class="position-relative d-flex align-items-center group"> Vector Search and 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="vector-search-and-embeddings" aria-haspopup="dialog" aria-label="Share link: Vector Search and Embeddings"> Share link </button> </h3> <h4 id="storing-embeddings-in-geode" class="position-relative d-flex align-items-center group"> Storing Embeddings in Geode <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-embeddings-in-geode" aria-haspopup="dialog" aria-label="Share link: Storing Embeddings in Geode"> Share link </button> </h4>Embeddings transform complex data into dense numerical vectors that capture semantic meaning. Store them as node or relationship properties: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Create a document with text embedding CREATE (d:Document { doc_id: 'doc_001', title: 'Introduction to Graph Databases', content: 'Graph databases model data as nodes and relationships...', embedding: $embedding, -- 384 or 1536 dimensional vector embedding_model: 'text-embedding-3-small', created_at: datetime() }); -- Create a product with image embedding CREATE (p:Product { product_id: 'prod_456', name: 'Wireless Headphones', image_url: '/images/headphones.jpg', image_embedding: $clip_embedding, -- CLIP model output text_embedding: $text_embedding }); </code></pre></div> <h4 id="creating-vector-indexes" class="position-relative d-flex align-items-center group"> Creating Vector 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="creating-vector-indexes" aria-haspopup="dialog" aria-label="Share link: Creating Vector Indexes"> Share link </button> </h4>Enable fast similarity search with HNSW indexes: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Create HNSW index for document embeddings CREATE VECTOR INDEX document_embeddings ON Document(embedding) WITH ( metric = 'cosine', dimensions = 1536, ef_construction = 200, m = 16 ); -- Create index for multi-modal search CREATE VECTOR INDEX product_images ON Product(image_embedding) WITH ( metric = 'cosine', dimensions = 512, ef_construction = 256, m = 24 ); </code></pre></div> <h4 id="similarity-search-queries" class="position-relative d-flex align-items-center group"> Similarity Search 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="similarity-search-queries" aria-haspopup="dialog" aria-label="Share link: Similarity Search Queries"> Share link </button> </h4>Find semantically similar items: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Semantic document search MATCH (d:Document) WITH d, vector_similarity(d.embedding, $query_embedding, 'cosine') AS score WHERE score > 0.7 RETURN d.doc_id, d.title, score ORDER BY score DESC LIMIT 10; -- Find similar products combining text and image MATCH (p:Product) WITH p, vector_similarity(p.text_embedding, $text_query, 'cosine') AS text_score, vector_similarity(p.image_embedding, $image_query, 'cosine') AS image_score WITH p, 0.6 * text_score + 0.4 * image_score AS combined_score WHERE combined_score > 0.65 RETURN p.name, p.product_id, combined_score ORDER BY combined_score DESC LIMIT 20; </code></pre></div> <h3 id="retrieval-augmented-generation-rag" class="position-relative d-flex align-items-center group"> Retrieval-Augmented Generation (RAG) <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="retrieval-augmented-generation-rag" aria-haspopup="dialog" aria-label="Share link: Retrieval-Augmented Generation (RAG)"> Share link </button> </h3>RAG combines the knowledge retrieval capabilities of databases with the generation abilities of large language models. Geode is ideal for RAG because it can: <ol> <li>Store document chunks with embeddings</li> <li>Retrieve relevant context via vector search</li> <li>Provide graph-based context for richer answers</li> </ol> <h4 id="rag-pipeline-architecture" class="position-relative d-flex align-items-center group"> RAG Pipeline Architecture <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="rag-pipeline-architecture" aria-haspopup="dialog" aria-label="Share link: RAG Pipeline Architecture"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">from geode_client import Client import openai async def rag_query(question: str) -> str: client = Client(host="localhost", port=3141) # Step 1: Generate query embedding query_embedding = await generate_embedding(question) async with client.connection() as conn: # Step 2: Retrieve relevant documents result, _ = await conn.query(""" MATCH (chunk:DocumentChunk) WITH chunk, vector_similarity(chunk.embedding, $query_emb, 'cosine') AS relevance WHERE relevance > 0.7 ORDER BY relevance DESC LIMIT 5 -- Step 3: Get document context via graph MATCH (chunk)-[:PART_OF]->(doc:Document) OPTIONAL MATCH (doc)-[:RELATED_TO]->(related:Document) RETURN chunk.content AS text, doc.title AS source, relevance, collect(DISTINCT related.title)[0..3] AS related_docs """, {"query_emb": query_embedding}) # Step 4: Build context for LLM context = "\n\n".join([ f"Source: {row['source']}\n{row['text']}" for row in result.rows ]) # Step 5: Generate answer with LLM response = await openai.ChatCompletion.acreate( model="gpt-4", messages=[ {"role": "system", "content": "Answer based on the provided context."}, {"role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}"} ] ) return response.choices[0].message.content </code></pre></div> <h4 id="graph-enhanced-rag" class="position-relative d-flex align-items-center group"> Graph-Enhanced RAG <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="graph-enhanced-rag" aria-haspopup="dialog" aria-label="Share link: Graph-Enhanced RAG"> Share link </button> </h4>Leverage graph relationships for better context: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Retrieve chunks with related entities MATCH (chunk:DocumentChunk) WHERE vector_similarity(chunk.embedding, $query_emb, 'cosine') > 0.7 WITH chunk ORDER BY vector_similarity(chunk.embedding, $query_emb, 'cosine') DESC LIMIT 5 -- Expand context via graph relationships MATCH (chunk)-[:MENTIONS]->(entity:Entity) OPTIONAL MATCH (entity)-[:RELATED_TO]-(related_entity:Entity) OPTIONAL MATCH (related_entity)<-[:MENTIONS]-(related_chunk:DocumentChunk) RETURN chunk.content AS primary_content, collect(DISTINCT entity.name) AS mentioned_entities, collect(DISTINCT related_chunk.content)[0..3] AS related_content; </code></pre></div> <h4 id="multi-hop-rag" class="position-relative d-flex align-items-center group"> Multi-Hop RAG <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-rag" aria-haspopup="dialog" aria-label="Share link: Multi-Hop RAG"> Share link </button> </h4>Answer complex questions requiring reasoning across multiple documents: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Question: "What companies did the CEO of TechCorp previously work for?" MATCH (chunk:DocumentChunk) WHERE vector_similarity(chunk.embedding, $query_emb, 'cosine') > 0.6 -- Extract entity relationships MATCH (chunk)-[:MENTIONS]->(person:Person)-[:CEO_OF]->(company:Company {name: 'TechCorp'}) MATCH (person)-[:WORKED_AT]->(prev_company:Company) RETURN person.name AS ceo, collect(DISTINCT prev_company.name) AS previous_companies, chunk.content AS source_text; </code></pre></div> <h3 id="recommendation-systems" class="position-relative d-flex align-items-center group"> Recommendation Systems <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="recommendation-systems" aria-haspopup="dialog" aria-label="Share link: Recommendation Systems"> Share link </button> </h3>Geode excels at building recommendation engines that combine collaborative filtering with content-based approaches. <h4 id="collaborative-filtering-with-graph" class="position-relative d-flex align-items-center group"> Collaborative Filtering with Graph <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="collaborative-filtering-with-graph" aria-haspopup="dialog" aria-label="Share link: Collaborative Filtering with Graph"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- User-based collaborative filtering MATCH (target_user:User {user_id: $user_id})-[:PURCHASED]->(item:Product) MATCH (similar_user:User)-[:PURCHASED]->(item) WHERE similar_user <> target_user WITH similar_user, count(item) AS shared_purchases -- Find what similar users bought that target hasn't MATCH (similar_user)-[:PURCHASED]->(recommended:Product) WHERE NOT (target_user)-[:PURCHASED]->(recommended) AND shared_purchases >= 3 RETURN recommended.product_id, recommended.name, count(DISTINCT similar_user) AS recommender_count, sum(shared_purchases) AS affinity_score ORDER BY affinity_score DESC LIMIT 10; </code></pre></div> <h4 id="content-based-with-embeddings" class="position-relative d-flex align-items-center group"> Content-Based with 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="content-based-with-embeddings" aria-haspopup="dialog" aria-label="Share link: Content-Based with Embeddings"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Find products similar to user's purchase history MATCH (user:User {user_id: $user_id})-[:PURCHASED]->(bought:Product) WITH user, collect(bought.embedding) AS purchase_embeddings -- Calculate average preference vector WITH user, [i IN range(0, size(purchase_embeddings[0])-1) | avg([emb IN purchase_embeddings | emb[i]])] AS preference_vector -- Find similar products MATCH (candidate:Product) WHERE NOT (user)-[:PURCHASED]->(candidate) WITH candidate, vector_similarity(candidate.embedding, preference_vector, 'cosine') AS similarity WHERE similarity > 0.75 RETURN candidate.product_id, candidate.name, similarity ORDER BY similarity DESC LIMIT 20; </code></pre></div> <h4 id="hybrid-recommendations" class="position-relative d-flex align-items-center group"> Hybrid 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="hybrid-recommendations" aria-haspopup="dialog" aria-label="Share link: Hybrid Recommendations"> Share link </button> </h4>Combine multiple signals: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Hybrid recommendation combining graph and embeddings MATCH (user:User {user_id: $user_id}) -- Get collaborative score OPTIONAL MATCH (user)-[:PURCHASED]->()<-[:PURCHASED]-(similar:User) OPTIONAL MATCH (similar)-[:PURCHASED]->(rec:Product) WHERE NOT (user)-[:PURCHASED]->(rec) WITH user, rec, count(DISTINCT similar) AS collab_score -- Get content-based score MATCH (user)-[:PURCHASED]->(bought:Product) WITH user, rec, collab_score, avg(vector_similarity(rec.embedding, bought.embedding, 'cosine')) AS content_score -- Combine scores WITH rec, 0.6 * collab_score / 10.0 + 0.4 * content_score AS hybrid_score WHERE hybrid_score > 0.5 RETURN rec.product_id, rec.name, hybrid_score ORDER BY hybrid_score DESC LIMIT 15; </code></pre></div> <h3 id="knowledge-graphs-for-ai" class="position-relative d-flex align-items-center group"> Knowledge Graphs for AI <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="knowledge-graphs-for-ai" aria-haspopup="dialog" aria-label="Share link: Knowledge Graphs for AI"> Share link </button> </h3> <h4 id="building-knowledge-graphs" class="position-relative d-flex align-items-center group"> Building Knowledge Graphs <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="building-knowledge-graphs" aria-haspopup="dialog" aria-label="Share link: Building Knowledge Graphs"> Share link </button> </h4>Structure domain knowledge for AI consumption: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Create entities and relationships CREATE (company:Company { name: 'Anthropic', founded: 2021, description: 'AI safety company', embedding: $company_embedding }); CREATE (person:Person { name: 'Dario Amodei', role: 'CEO', embedding: $person_embedding }); CREATE (company)-[:FOUNDED_BY]->(person); CREATE (person)-[:LEADS]->(company); -- Add facts as typed relationships CREATE (company)-[:HEADQUARTERED_IN {since: 2021}]->(:City {name: 'San Francisco'}); CREATE (company)-[:DEVELOPS]->(:Product {name: 'Claude', type: 'LLM'}); </code></pre></div> <h4 id="querying-knowledge-graphs" class="position-relative d-flex align-items-center group"> Querying Knowledge Graphs <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="querying-knowledge-graphs" aria-haspopup="dialog" aria-label="Share link: Querying Knowledge Graphs"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Entity resolution with embeddings MATCH (e:Entity) WHERE vector_similarity(e.embedding, $query_embedding, 'cosine') > 0.85 RETURN e.name, labels(e) AS types, e.description; -- Multi-hop knowledge queries MATCH path = (start:Company {name: 'Anthropic'})-[*1..3]-(end:Entity) WHERE end:Person OR end:Product OR end:Company RETURN [n IN nodes(path) | n.name] AS entity_path, [r IN relationships(path) | type(r)] AS relationship_types; -- Find related facts MATCH (entity:Entity) WHERE entity.name = $entity_name MATCH (entity)-[r]-(related) RETURN type(r) AS relationship, related.name AS related_entity, labels(related) AS entity_types; </code></pre></div> <h3 id="llm-integration-patterns" class="position-relative d-flex align-items-center group"> LLM Integration Patterns <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="llm-integration-patterns" aria-haspopup="dialog" aria-label="Share link: LLM Integration Patterns"> Share link </button> </h3> <h4 id="structured-output-from-llms" class="position-relative d-flex align-items-center group"> Structured Output from LLMs <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="structured-output-from-llms" aria-haspopup="dialog" aria-label="Share link: Structured Output from LLMs"> Share link </button> </h4>Store LLM-extracted information in Geode: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">async def extract_and_store_entities(text: str, doc_id: str): # Use LLM to extract entities extraction = await openai.ChatCompletion.acreate( model="gpt-4", messages=[ {"role": "system", "content": "Extract entities and relationships as JSON."}, {"role": "user", "content": text} ], response_format={"type": "json_object"} ) entities = json.loads(extraction.choices[0].message.content) async with client.connection() as conn: # Store entities for entity in entities['entities']: await conn.execute(""" MERGE (e:Entity {name: $name}) SET e.type = $type, e.embedding = $embedding """, { "name": entity['name'], "type": entity['type'], "embedding": await generate_embedding(entity['name']) }) # Store relationships for rel in entities['relationships']: await conn.execute(""" MATCH (source:Entity {name: $source}) MATCH (target:Entity {name: $target}) MERGE (source)-[r:RELATED {type: $rel_type}]->(target) """, rel) </code></pre></div> <h4 id="agent-tool-integration" class="position-relative d-flex align-items-center group"> Agent Tool Integration <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="agent-tool-integration" aria-haspopup="dialog" aria-label="Share link: Agent Tool Integration"> Share link </button> </h4>Expose Geode queries as LLM tools: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">tools = [ { "type": "function", "function": { "name": "search_knowledge_base", "description": "Search the knowledge graph for information", "parameters": { "type": "object", "properties": { "query": {"type": "string", "description": "Natural language query"}, "entity_types": {"type": "array", "items": {"type": "string"}} }, "required": ["query"] } } }, { "type": "function", "function": { "name": "find_relationships", "description": "Find relationships between entities", "parameters": { "type": "object", "properties": { "entity_name": {"type": "string"}, "relationship_types": {"type": "array", "items": {"type": "string"}}, "max_hops": {"type": "integer", "default": 2} }, "required": ["entity_name"] } } } ] async def handle_tool_call(tool_name: str, args: dict): async with client.connection() as conn: if tool_name == "search_knowledge_base": query_emb = await generate_embedding(args['query']) result, _ = await conn.query(""" MATCH (e:Entity) WHERE vector_similarity(e.embedding, $emb, 'cosine') > 0.7 RETURN e.name, e.type, e.description ORDER BY vector_similarity(e.embedding, $emb, 'cosine') DESC LIMIT 10 """, {"emb": query_emb}) return result.rows elif tool_name == "find_relationships": result, _ = await conn.query(""" MATCH (e:Entity {name: $name})-[r*1..$hops]-(related) RETURN DISTINCT related.name, labels(related), [rel IN r | type(rel)] AS path """, {"name": args['entity_name'], "hops": args.get('max_hops', 2)}) return result.rows </code></pre></div> <h3 id="graph-neural-networks" class="position-relative d-flex align-items-center group"> Graph Neural Networks <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="graph-neural-networks" aria-haspopup="dialog" aria-label="Share link: Graph Neural Networks"> Share link </button> </h3> <h4 id="preparing-data-for-gnns" class="position-relative d-flex align-items-center group"> Preparing Data for GNNs <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="preparing-data-for-gnns" aria-haspopup="dialog" aria-label="Share link: Preparing Data for GNNs"> Share link </button> </h4>Export graph data for GNN training: <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">async def export_for_gnn(client): # Export node features nodes, _ = await client.query(""" MATCH (n:Entity) RETURN id(n) AS node_id, n.embedding AS features, labels(n) AS node_type """) # Export edges edges, _ = await client.query(""" MATCH (source)-[r]->(target) RETURN id(source) AS source_id, id(target) AS target_id, type(r) AS edge_type """) return { 'nodes': nodes.rows, 'edges': edges.rows } </code></pre></div> <h4 id="storing-gnn-embeddings" class="position-relative d-flex align-items-center group"> Storing GNN 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-gnn-embeddings" aria-haspopup="dialog" aria-label="Share link: Storing GNN Embeddings"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-gql" data-lang="gql">-- Store learned node embeddings from GNN MATCH (n:Entity {entity_id: $entity_id}) SET n.gnn_embedding = $gnn_vector, n.gnn_model_version = 'graphsage-v2', n.gnn_updated_at = datetime(); -- Use GNN embeddings for link prediction MATCH (a:Entity), (b:Entity) WHERE a <> b AND NOT (a)-[:RELATED]-(b) WITH a, b, vector_similarity(a.gnn_embedding, b.gnn_embedding, 'cosine') AS link_score WHERE link_score > 0.8 RETURN a.name, b.name, link_score ORDER BY link_score DESC LIMIT 100; </code></pre></div> <h3 id="performance-optimization" class="position-relative d-flex align-items-center group"> Performance Optimization <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="performance-optimization" aria-haspopup="dialog" aria-label="Share link: Performance Optimization"> Share link </button> </h3> <h4 id="batch-embedding-generation" class="position-relative d-flex align-items-center group"> Batch 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="batch-embedding-generation" aria-haspopup="dialog" aria-label="Share link: Batch Embedding Generation"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">async def batch_embed_documents(client, batch_size=100): async with client.connection() as conn: # Find documents needing embeddings docs, _ = await conn.query(""" MATCH (d:Document) WHERE d.embedding IS NULL AND d.content IS NOT NULL RETURN d.doc_id AS id, d.content AS text LIMIT $batch_size """, {"batch_size": batch_size}) if not docs.rows: return 0 # Batch embed with model texts = [row['text'] for row in docs.rows] embeddings = embedding_model.encode(texts, batch_size=32) # Update in transaction async with conn.transaction() as tx: for doc, emb in zip(docs.rows, embeddings): await tx.execute(""" MATCH (d:Document {doc_id: $id}) SET d.embedding = $embedding, d.embedding_model = 'text-embedding-3-small', d.embedded_at = datetime() """, {"id": doc['id'], "embedding": emb.tolist()}) return len(docs.rows) </code></pre></div> <h4 id="caching-strategies" class="position-relative d-flex align-items-center group"> Caching 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="caching-strategies" aria-haspopup="dialog" aria-label="Share link: Caching Strategies"> Share link </button> </h4><div class="highlight"><pre tabindex="0" class="chroma"><code class="language-python" data-lang="python">from functools import lru_cache import hashlib @lru_cache(maxsize=10000) def get_cached_embedding(text_hash: str): # Cache hit return embedding_cache.get(text_hash) async def smart_embed(text: str): text_hash = hashlib.md5(text.encode()).hexdigest() cached = get_cached_embedding(text_hash) if cached: return cached embedding = await generate_embedding(text) embedding_cache[text_hash] = embedding return embedding </code></pre></div> <h3 id="related-topics" class="position-relative d-flex align-items-center group"> Related Topics <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="related-topics" aria-haspopup="dialog" aria-label="Share link: Related Topics"> Share link </button> </h3><ul> <li><a href="/tags/vector-search/" >Vector Search</a> : Deep dive into HNSW indexes and similarity queries</li> <li><a href="/tags/embeddings/" >Embeddings</a> : Best practices for storing and querying embeddings</li> <li><a href="/tags/recommendations/" >Recommendations</a> : Building recommendation systems</li> <li><a href="/tags/knowledge-graphs/" >Knowledge Graphs</a> : Structuring knowledge for AI</li> <li><a href="/tags/performance/" >Performance</a> : Optimizing AI workloads</li> </ul> <h3 id="further-reading" class="position-relative d-flex align-items-center group"> Further Reading <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="further-reading" aria-haspopup="dialog" aria-label="Share link: Further Reading"> Share link </button> </h3><ul> <li>RAG Best Practices: Building production RAG systems with Geode</li> <li>Vector Index Tuning: Optimizing HNSW parameters for your workload</li> <li>LLM Integration Guide: Connecting Geode to OpenAI, Anthropic, and other providers</li> <li>Graph Neural Networks: Training GNNs on Geode data</li> <li>Knowledge Graph Construction: Automated knowledge extraction and storage</li> </ul> Browse the tagged content below to explore AI and machine learning documentation, tutorials, and examples for Geode.

Popular

Related Articles

Claude Code Plugin