@lunora/ai 1.0.0-alpha.127 → 1.0.0-alpha.129

package/dist/packem_shared/{defineRag-BzrVmcfR.mjs → defineRag-CJudmmcj.mjs}

@@ -1,4 +1,4 @@
-import{tool as Re,jsonSchema as De}from"@ai-sdk/provider-utils";import{LunoraError as w,isLunoraError as Ce}from"@lunora/errors";import{s as Be}from"./stable-key-B_BlboiY.mjs";import{r as de,m as L}from"./usage-GPnTSqR8.mjs";import $e from"./fixedWindowChunks-C461ahRE.mjs";import{c as Oe,I as Ke}from"./concurrent-C6nqBv41.mjs";import{contentHash as Ue}from"./contentHash-BIn6ECP8.mjs";import{hybridRank as Qe}from"./hybridRank-B4skyCLx.mjs";import{VECTORIZE_CAPABILITIES as le,vectorizeStore as Ve}from"./VECTORIZE_CAPABILITIES-l9ceRO5j.mjs";const Fe=1e3,Le=200,ze=5,ue=1e3,Pe=4,me=le.maxMetadataBytes===!1?Number.POSITIVE_INFINITY:le.maxMetadataBytes,je=2*1024,we="__ragChunk",be="__ragSource",K="__ragText",q="__ragHash",W="__ragChunks",V="__ragImportance",ve="__ragModel",He=new Set([we,W,q,V,ve,be,K]),Ye=async(e,c,u,m)=>{if(c.length===0)return;const h=c.slice(1);if(!e.upsertMany){await Oe(h,Ke,async(E,A)=>{await e.upsert(E,m),u(A+1)}),await e.upsert(c[0],m),u(0);return}for(let E=0;E<h.length;E+=ue){const A=Math.min(E+ue,h.length);await e.upsertMany(h.slice(E,A),m);for(let U=E;U<A;U+=1)u(U+1)}await e.upsertMany([c[0]],m),u(0)},qe=(e,c,u,m)=>{if(m===!1)return;const h=new TextEncoder().encode(JSON.stringify(e)).length;if(h<=m)return;const A=(typeof e[K]=="string"?new TextEncoder().encode(e[K]).length:0)*2>h?"lower `chunkSize` (it counts characters, not bytes — multibyte text costs up to 3 bytes each), or supply `textStore` to move chunk text out of metadata entirely":"attach less per-source `metadata`";throw new w("BAD_REQUEST",`@lunora/ai/rag: chunk ${String(c)} of "${u}" carries ${String(h)} bytes of metadata, over the store's ${String(m)}-byte per-vector ceiling — ${A}`)},We=(e,c,u)=>{if(u===!1)return;const m=new TextEncoder().encode(e).length;if(!(m<=u))throw new w("BAD_REQUEST",`@lunora/ai/rag: chunk id "${e}" for source "${c}" is ${String(m)} bytes, over the store's ${String(u)}-byte per-vector id ceiling — shorten the source id (hash long keys before indexing them) or shorten the \`namespace\`, which is prefixed onto every chunk id`)},Ze=/^[\w.-]{1,40}$/,ye=e=>e===void 0?"":`${encodeURIComponent(e)}#`,O=(e,c,u)=>`${ye(e)}${c}#${String(u)}`,he=(e,c)=>{const u=ye(c),m=u!==""&&e.startsWith(u)?e.slice(u.length):e,h=m.lastIndexOf("#"),E=h===-1?Number.NaN:Number(m.slice(h+1));return h===-1||!Number.isInteger(E)||E<0?{chunkIndex:0,sourceId:m}:{chunkIndex:E,sourceId:m.slice(0,h)}},Xe=async e=>Ue(new TextEncoder().encode(e)),Je=e=>{try{return Be([e.text,e.metadata,e.importance])}catch{return}},Ge=(e,c)=>{const u=[],m=[];for(const h of e)h.score>=c?u.push(h):m.push(h.id);return{kept:u,rejectedIds:m}},et=e=>e!==void 0&&Object.keys(e).length>0,H=e=>{if(!e)return;const c=Object.entries(e).filter(([u])=>!He.has(u));return c.length>0?Object.fromEntries(c):void 0},pe=new Set,tt=e=>{pe.has(e)||(pe.add(e),console.warn(`[@lunora/ai/rag] index "${e}" is used without a namespace — in a multi-tenant/sharded
+import{tool as Re,jsonSchema as De}from"@ai-sdk/provider-utils";import{LunoraError as w,isLunoraError as Ce}from"@lunora/errors";import{stableStringify as Be}from"@lunora/wire";import{r as de,m as L}from"./usage-GPnTSqR8.mjs";import $e from"./fixedWindowChunks-C461ahRE.mjs";import{c as Oe,I as Ke}from"./concurrent-C6nqBv41.mjs";import{contentHash as Ue}from"./contentHash-BIn6ECP8.mjs";import{hybridRank as Qe}from"./hybridRank-B4skyCLx.mjs";import{VECTORIZE_CAPABILITIES as le,vectorizeStore as Ve}from"./VECTORIZE_CAPABILITIES-l9ceRO5j.mjs";const Fe=1e3,Le=200,ze=5,ue=1e3,Pe=4,me=le.maxMetadataBytes===!1?Number.POSITIVE_INFINITY:le.maxMetadataBytes,je=2*1024,we="__ragChunk",be="__ragSource",K="__ragText",q="__ragHash",W="__ragChunks",V="__ragImportance",ve="__ragModel",He=new Set([we,W,q,V,ve,be,K]),Ye=async(e,c,u,m)=>{if(c.length===0)return;const h=c.slice(1);if(!e.upsertMany){await Oe(h,Ke,async(E,A)=>{await e.upsert(E,m),u(A+1)}),await e.upsert(c[0],m),u(0);return}for(let E=0;E<h.length;E+=ue){const A=Math.min(E+ue,h.length);await e.upsertMany(h.slice(E,A),m);for(let U=E;U<A;U+=1)u(U+1)}await e.upsertMany([c[0]],m),u(0)},qe=(e,c,u,m)=>{if(m===!1)return;const h=new TextEncoder().encode(JSON.stringify(e)).length;if(h<=m)return;const A=(typeof e[K]=="string"?new TextEncoder().encode(e[K]).length:0)*2>h?"lower `chunkSize` (it counts characters, not bytes — multibyte text costs up to 3 bytes each), or supply `textStore` to move chunk text out of metadata entirely":"attach less per-source `metadata`";throw new w("BAD_REQUEST",`@lunora/ai/rag: chunk ${String(c)} of "${u}" carries ${String(h)} bytes of metadata, over the store's ${String(m)}-byte per-vector ceiling — ${A}`)},We=(e,c,u)=>{if(u===!1)return;const m=new TextEncoder().encode(e).length;if(!(m<=u))throw new w("BAD_REQUEST",`@lunora/ai/rag: chunk id "${e}" for source "${c}" is ${String(m)} bytes, over the store's ${String(u)}-byte per-vector id ceiling — shorten the source id (hash long keys before indexing them) or shorten the \`namespace\`, which is prefixed onto every chunk id`)},Ze=/^[\w.-]{1,40}$/,ye=e=>e===void 0?"":`${encodeURIComponent(e)}#`,O=(e,c,u)=>`${ye(e)}${c}#${String(u)}`,he=(e,c)=>{const u=ye(c),m=u!==""&&e.startsWith(u)?e.slice(u.length):e,h=m.lastIndexOf("#"),E=h===-1?Number.NaN:Number(m.slice(h+1));return h===-1||!Number.isInteger(E)||E<0?{chunkIndex:0,sourceId:m}:{chunkIndex:E,sourceId:m.slice(0,h)}},Xe=async e=>Ue(new TextEncoder().encode(e)),Je=e=>{try{return Be([e.text,e.metadata,e.importance])}catch{return}},Ge=(e,c)=>{const u=[],m=[];for(const h of e)h.score>=c?u.push(h):m.push(h.id);return{kept:u,rejectedIds:m}},et=e=>e!==void 0&&Object.keys(e).length>0,H=e=>{if(!e)return;const c=Object.entries(e).filter(([u])=>!He.has(u));return c.length>0?Object.fromEntries(c):void 0},pe=new Set,tt=e=>{pe.has(e)||(pe.add(e),console.warn(`[@lunora/ai/rag] index "${e}" is used without a namespace — in a multi-tenant/sharded
 app this shares one tenant's chunks (text included) with every other tenant, since
 Vectorize indexes are account-global. Pass \`namespace\` (the shard/tenant key) on both
 index() and retrieve(). Single-tenant apps suppress this via { allowSharedNamespace: true }.`))},nt=e=>e.map(c=>`[source:${c.sourceId}#${String(c.chunkIndex)}]

package/dist/packem_shared/ragSyncTriggers-D933fCwt.mjs

@@ -0,0 +1 @@
+import{stableStringify as l}from"@lunora/wire";const v=c=>{const m=c.delayMs??0,y=(d,a)=>c.id===void 0?a:c.id(d),e=d=>d===void 0?void 0:c.text(d),u=d=>c.metadata?.(d),p=d=>c.namespace?.(d),o=(d,a)=>{const t=p(d);return{id:y(d,a),...t===void 0?{}:{namespace:t}}},f=(d,a,t)=>{const i=u(d);return{...o(d,a),...i===void 0?{}:{metadata:i},text:t}},g=(d,a)=>{try{return l(u(d))===l(u(a))}catch{return!1}},r=async(d,a)=>{await d.scheduler.runAfter(m,c.action,a)};return{afterDelete:async(d,a)=>{const t=a.previous??a.doc;await r(d,{deleted:!0,...t===void 0?{id:a.id}:o(t,a.id)})},afterInsert:async(d,a)=>{const t=e(a.doc);t===void 0||a.doc===void 0||await r(d,f(a.doc,a.id,t))},afterUpdate:async(d,a)=>{if(a.doc===void 0)return;const t=e(a.doc),i=e(a.previous),s=o(a.doc,a.id),n=a.previous===void 0?s:o(a.previous,a.id),w=n.id!==s.id||n.namespace!==s.namespace,h=c.metadata!==void 0&&a.previous!==void 0&&!g(a.doc,a.previous);if(w)await r(d,{deleted:!0,...n});else if(t===i&&!h)return;await(t===void 0?r(d,{deleted:!0,...s}):r(d,f(a.doc,a.id,t)))}}};export{v as ragSyncTriggers};

package/dist/packem_shared/sqliteVectorStore-f24ySqtJ.mjs

@@ -0,0 +1 @@
+import M from"./matchesMetadataFilter-BbIOyA5g.mjs";import{p as I,a as D,r as R,c as V,i as x}from"./sql-D5aqEMCY.mjs";import{LunoraError as B}from"@lunora/errors";const q=500,_=4096,A=(T,i)=>JSON.stringify([T,i]),U=T=>{const{dimensions:i,exec:c,table:w}=T,E=`${w}_ann`,f=`${w}_ann_ready`,u=(r,t)=>{if(r!==i)throw new B("RAG_DIMENSION_MISMATCH",`@lunora/ai/rag: ${t} is ${String(r)}-dimension but the \`ann\` index is ${String(i)}-dimension — set \`ann.dimensions\` to the embedding model's width, or reindex into a new \`table\` after changing models`)},g=async(r,t,o)=>{await c(`INSERT INTO ${E} (ref, namespace, embedding, id) VALUES (?, ?, ?, ?)`,[A(r,t),r,o,t])},S=async()=>{let r=0;for(;;){const t=await c(`SELECT rowid, id, namespace, vector FROM ${w} WHERE rowid > ? ORDER BY rowid LIMIT ?`,[r,q]);for(const o of t)u(JSON.parse(String(o.vector)).length,`stored vector "${String(o.id)}"`),await g(String(o.namespace),String(o.id),String(o.vector));if(t.length<q)return;r=Number(t.at(-1)?.rowid)}};return{ensure:async()=>{if((await c("SELECT name FROM sqlite_master WHERE name = ?",[f])).length>0){const[t]=await c(`SELECT dimensions FROM ${f}`,[]);u(Number(t?.dimensions),"the existing index");return}await c(`DROP TABLE IF EXISTS ${E}`,[]);try{await c(`CREATE VIRTUAL TABLE ${E} USING vec0(ref TEXT PRIMARY KEY, namespace TEXT PARTITION KEY, embedding FLOAT[${String(i)}] distance_metric=cosine, +id TEXT)`,[])}catch(t){throw t instanceof Error&&t.message.includes("no such module: vec0")?new Error("@lunora/ai/rag: sqliteVectorStore `ann` needs the sqlite-vec extension in this SQLite (`no such module: vec0`) — on celld set the `sqlite_vec` compatibility flag, on node:sqlite load the extension",{cause:t}):t}await S(),await c(`CREATE TABLE ${f} (dimensions INTEGER NOT NULL)`,[]),await c(`INSERT INTO ${f} (dimensions) VALUES (?)`,[i])},nearest:async(r,t,o)=>(u(t.length,"the query embedding"),(await c(`SELECT id, distance FROM ${E} WHERE embedding MATCH ? AND k = ? AND namespace = ?`,[JSON.stringify([...t]),Math.min(o,_),r])).map(v=>({distance:Number(v.distance),id:String(v.id)}))),put:async(r,t,o)=>{u(o.length,`the embedding for "${t}"`),await c(`DELETE FROM ${E} WHERE ref = ?`,[A(r,t)]),await g(r,t,JSON.stringify([...o]))},remove:async(r,t)=>{await c(`DELETE FROM ${E} WHERE ref IN (${I(t.length)})`,t.map(o=>A(r,o)))}}},X="lunora_rag_vectors",K=5e4,F=100,H=[4,16],W=null,h=T=>T??"",k=T=>{if(typeof T.exec!="function")throw new TypeError("@lunora/ai/rag: sqliteVectorStore requires an `exec` function");const i=D(T.table??X,"sqliteVectorStore `table`"),c=T.maxScan??K,{ann:w,exec:E}=T;if(w!==void 0&&(!Number.isInteger(w.dimensions)||w.dimensions<=0))throw new TypeError("@lunora/ai/rag: sqliteVectorStore `ann.dimensions` must be a positive integer");const f=w===void 0?void 0:U({dimensions:w.dimensions,exec:E,table:i}),u={deferredDelete:!0,maxDimensions:T.maxDimensions??w?.dimensions??!1,maxIdBytes:!1,maxMetadataBytes:!1,maxTopK:F,maxTopKWithMetadata:F};let g;const S=async()=>{g??=(async()=>{await E(`CREATE TABLE IF NOT EXISTS ${i} (id TEXT NOT NULL, namespace TEXT NOT NULL DEFAULT '', vector TEXT NOT NULL, metadata TEXT, PRIMARY KEY (namespace, id))`,[]),await E(`CREATE INDEX IF NOT EXISTS ${i}_namespace ON ${i} (namespace)`,[]),await f?.ensure()})().catch(e=>{throw g=void 0,e}),await g},O=async e=>{if(await S(),!e.embed)throw new TypeError("@lunora/ai/rag: sqliteVectorStore requires an `embed` function on upsert");const s=await e.embed(e.input),a=h(e.namespace);await f?.put(a,e.id,s),await E(`INSERT INTO ${i} (id, namespace, vector, metadata) VALUES (${I(4)}) ON CONFLICT(namespace, id) DO UPDATE SET vector = excluded.vector, metadata = excluded.metadata`,[e.id,a,JSON.stringify([...s]),e.metadata===void 0?W:JSON.stringify(e.metadata)])},r=async(e,s)=>{if(await S(),e.length===0)return[];const a=[];for(const d of x(e)){const m=await E(`SELECT id, metadata FROM ${i} WHERE namespace = ? AND id IN (${I(d.length)})`,[h(s),...d]);for(const n of m){const l=R(n.metadata);a.push({id:String(n.id),...l===void 0?{}:{metadata:l}})}}return a},t=async(e,s,a,d)=>{const m=h(a.namespace),n=await e.nearest(m,s,d),l=await r(n.map(L=>L.id),m),N=new Map(l.map(L=>[L.id,L])),b=[];for(const{distance:L,id:$}of n){const y=N.get($);y===void 0||!M(y.metadata,a.filter)||b.push({id:$,score:1-L,...a.returnMetadata==="none"||y.metadata===void 0?{}:{metadata:y.metadata}})}const p=b.slice(0,a.topK??10);return{count:p.length,exhausted:n.length<Math.min(d,_),matches:p}},o=async(e,s,a)=>{const d=a.topK??10;if(a.filter===void 0){const{count:m,matches:n}=await t(e,s,a,d);return{count:m,matches:n}}for(const m of H){const{count:n,exhausted:l,matches:N}=await t(e,s,a,d*m);if(n>=d||l)return{count:n,matches:N}}};return{capabilities:u,deleteByIds:async(e,s,a,d)=>{if(await S(),e.length===0){await d?.();return}for(const m of x(e))await E(`DELETE FROM ${i} WHERE namespace = ? AND id IN (${I(m.length)})`,[h(s),...m]),await f?.remove(h(s),m);await d?.()},getByIds:r,query:async e=>{await S();let s;if(e.embed&&e.input!==void 0)s=await e.embed(e.input);else throw new TypeError("@lunora/ai/rag: sqliteVectorStore query requires both `input` and `embed`");if(f!==void 0){const n=await o(f,s,e);if(n!==void 0)return n}const a=await E(`SELECT id, vector, metadata FROM ${i} WHERE namespace = ? LIMIT ?`,[h(e.namespace),c+1]);if(a.length>c)throw new RangeError(`@lunora/ai/rag: sqliteVectorStore scanned ${String(a.length)} vectors in namespace "${h(e.namespace)}", over the ${String(c)} limit — search here is brute force and linear, so this namespace has outgrown it. Shard it further, or move this index to Vectorize or a pgvector backend`);const d=[];for(const n of a){const l=R(n.metadata);if(!M(l,e.filter))continue;const N=R(n.vector);N!==void 0&&d.push({id:String(n.id),score:V(s,N),...e.returnMetadata==="none"||l===void 0?{}:{metadata:l}})}const m=d.toSorted((n,l)=>l.score-n.score).slice(0,e.topK??10);return{count:m.length,matches:m}},upsert:O}};export{k as sqliteVectorStore};

package/dist/rag/index.mjs

@@ -1 +1 @@
-import{default as o}from"../packem_shared/fixedWindowChunks-C461ahRE.mjs";import{markdownChunker as a,sentenceChunker as f,tokenChunker as n}from"../packem_shared/markdownChunker-iW8V4klY.mjs";import{default as x}from"../packem_shared/defineRag-BzrVmcfR.mjs";import{contentHash as p,guessMimeTypeFromExtension as i}from"../packem_shared/contentHash-BIn6ECP8.mjs";import{hybridRank as d}from"../packem_shared/hybridRank-B4skyCLx.mjs";import{default as k}from"../packem_shared/bm25LexicalStore-DMUzAL0O.mjs";import{default as h}from"../packem_shared/matchesMetadataFilter-BbIOyA5g.mjs";import{batchReranker as g,scoreReranker as C}from"../packem_shared/batchReranker-Bc38FBLH.mjs";import{defineRagSource as E}from"../packem_shared/defineRagSource-Q3f3niU8.mjs";import{sqlLexicalStore as T}from"../packem_shared/sqlLexicalStore-4C_cIwef.mjs";import{sqliteVectorStore as y}from"../packem_shared/sqliteVectorStore-Dyv1x3eC.mjs";import{ragSyncTriggers as q}from"../packem_shared/ragSyncTriggers-hgMcA4f2.mjs";import{VECTORIZE_CAPABILITIES as A,vectorizeStore as F}from"../packem_shared/VECTORIZE_CAPABILITIES-l9ceRO5j.mjs";export{A as VECTORIZE_CAPABILITIES,g as batchReranker,k as bm25LexicalStore,p as contentHash,x as defineRag,E as defineRagSource,o as fixedWindowChunks,i as guessMimeTypeFromExtension,d as hybridRank,a as markdownChunker,h as matchesMetadataFilter,q as ragSyncTriggers,C as scoreReranker,f as sentenceChunker,T as sqlLexicalStore,y as sqliteVectorStore,n as tokenChunker,F as vectorizeStore};
+import{default as o}from"../packem_shared/fixedWindowChunks-C461ahRE.mjs";import{markdownChunker as a,sentenceChunker as f,tokenChunker as n}from"../packem_shared/markdownChunker-iW8V4klY.mjs";import{default as x}from"../packem_shared/defineRag-CJudmmcj.mjs";import{contentHash as p,guessMimeTypeFromExtension as i}from"../packem_shared/contentHash-BIn6ECP8.mjs";import{hybridRank as d}from"../packem_shared/hybridRank-B4skyCLx.mjs";import{default as k}from"../packem_shared/bm25LexicalStore-DMUzAL0O.mjs";import{default as h}from"../packem_shared/matchesMetadataFilter-BbIOyA5g.mjs";import{batchReranker as g,scoreReranker as C}from"../packem_shared/batchReranker-Bc38FBLH.mjs";import{defineRagSource as E}from"../packem_shared/defineRagSource-Q3f3niU8.mjs";import{sqlLexicalStore as T}from"../packem_shared/sqlLexicalStore-4C_cIwef.mjs";import{sqliteVectorStore as y}from"../packem_shared/sqliteVectorStore-f24ySqtJ.mjs";import{ragSyncTriggers as q}from"../packem_shared/ragSyncTriggers-D933fCwt.mjs";import{VECTORIZE_CAPABILITIES as A,vectorizeStore as F}from"../packem_shared/VECTORIZE_CAPABILITIES-l9ceRO5j.mjs";export{A as VECTORIZE_CAPABILITIES,g as batchReranker,k as bm25LexicalStore,p as contentHash,x as defineRag,E as defineRagSource,o as fixedWindowChunks,i as guessMimeTypeFromExtension,d as hybridRank,a as markdownChunker,h as matchesMetadataFilter,q as ragSyncTriggers,C as scoreReranker,f as sentenceChunker,T as sqlLexicalStore,y as sqliteVectorStore,n as tokenChunker,F as vectorizeStore};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lunora/ai",
-  "version": "1.0.0-alpha.127",
+  "version": "1.0.0-alpha.129",
   "description": "Workers AI helper for Lunora: provider-agnostic AI SDK access from functions, Workers AI by default",
   "keywords": [
     "ai",
@@ -61,6 +61,7 @@
     "@ai-sdk/openai": "4.0.83",
     "@ai-sdk/provider-utils": "5.0.53",
     "@lunora/errors": ">=1.0.0-alpha.51 <2.0.0-0",
+    "@lunora/wire": "1.0.0-alpha.1",
     "ai": "7.0.127",
     "workers-ai-provider": "4.0.0"
   },

package/dist/packem_shared/ragSyncTriggers-hgMcA4f2.mjs

@@ -1 +0,0 @@
-import{s as l}from"./stable-key-B_BlboiY.mjs";const v=c=>{const m=c.delayMs??0,y=(d,a)=>c.id===void 0?a:c.id(d),e=d=>d===void 0?void 0:c.text(d),u=d=>c.metadata?.(d),p=d=>c.namespace?.(d),o=(d,a)=>{const t=p(d);return{id:y(d,a),...t===void 0?{}:{namespace:t}}},f=(d,a,t)=>{const s=u(d);return{...o(d,a),...s===void 0?{}:{metadata:s},text:t}},g=(d,a)=>{try{return l(u(d))===l(u(a))}catch{return!1}},r=async(d,a)=>{await d.scheduler.runAfter(m,c.action,a)};return{afterDelete:async(d,a)=>{const t=a.previous??a.doc;await r(d,{deleted:!0,...t===void 0?{id:a.id}:o(t,a.id)})},afterInsert:async(d,a)=>{const t=e(a.doc);t===void 0||a.doc===void 0||await r(d,f(a.doc,a.id,t))},afterUpdate:async(d,a)=>{if(a.doc===void 0)return;const t=e(a.doc),s=e(a.previous),i=o(a.doc,a.id),n=a.previous===void 0?i:o(a.previous,a.id),w=n.id!==i.id||n.namespace!==i.namespace,h=c.metadata!==void 0&&a.previous!==void 0&&!g(a.doc,a.previous);if(w)await r(d,{deleted:!0,...n});else if(t===s&&!h)return;await(t===void 0?r(d,{deleted:!0,...i}):r(d,f(a.doc,a.id,t)))}}};export{v as ragSyncTriggers};

package/dist/packem_shared/sqliteVectorStore-Dyv1x3eC.mjs

@@ -1 +0,0 @@
-import x from"./matchesMetadataFilter-BbIOyA5g.mjs";import{p as I,a as q,r as y,c as F,i as A}from"./sql-D5aqEMCY.mjs";import{LunoraError as _}from"@lunora/errors";const O=500,C=4096,R=(d,n)=>JSON.stringify([d,n]),D=d=>{const{dimensions:n,exec:r,table:l}=d,i=`${l}_ann`,T=`${l}_ann_ready`,u=(a,t)=>{if(a!==n)throw new _("RAG_DIMENSION_MISMATCH",`@lunora/ai/rag: ${t} is ${String(a)}-dimension but the \`ann\` index is ${String(n)}-dimension — set \`ann.dimensions\` to the embedding model's width, or reindex into a new \`table\` after changing models`)},g=async(a,t,o)=>{await r(`INSERT INTO ${i} (ref, namespace, embedding, id) VALUES (?, ?, ?, ?)`,[R(a,t),a,o,t])},S=async()=>{let a=0;for(;;){const t=await r(`SELECT rowid, id, namespace, vector FROM ${l} WHERE rowid > ? ORDER BY rowid LIMIT ?`,[a,O]);for(const o of t)u(JSON.parse(String(o.vector)).length,`stored vector "${String(o.id)}"`),await g(String(o.namespace),String(o.id),String(o.vector));if(t.length<O)return;a=Number(t.at(-1)?.rowid)}};return{ensure:async()=>{if((await r("SELECT name FROM sqlite_master WHERE name = ?",[T])).length>0){const[t]=await r(`SELECT dimensions FROM ${T}`,[]);u(Number(t?.dimensions),"the existing index");return}await r(`DROP TABLE IF EXISTS ${i}`,[]);try{await r(`CREATE VIRTUAL TABLE ${i} USING vec0(ref TEXT PRIMARY KEY, namespace TEXT PARTITION KEY, embedding FLOAT[${String(n)}] distance_metric=cosine, +id TEXT)`,[])}catch(t){throw t instanceof Error&&t.message.includes("no such module: vec0")?new Error("@lunora/ai/rag: sqliteVectorStore `ann` needs the sqlite-vec extension in this SQLite (`no such module: vec0`) — on celld set the `sqlite_vec` compatibility flag, on node:sqlite load the extension",{cause:t}):t}await S(),await r(`CREATE TABLE ${T} (dimensions INTEGER NOT NULL)`,[]),await r(`INSERT INTO ${T} (dimensions) VALUES (?)`,[n])},nearest:async(a,t,o)=>(u(t.length,"the query embedding"),(await r(`SELECT id, distance FROM ${i} WHERE embedding MATCH ? AND k = ? AND namespace = ?`,[JSON.stringify([...t]),Math.min(o,C),a])).map(e=>({distance:Number(e.distance),id:String(e.id)}))),put:async(a,t,o)=>{u(o.length,`the embedding for "${t}"`),await r(`DELETE FROM ${i} WHERE ref = ?`,[R(a,t)]),await g(a,t,JSON.stringify([...o]))},remove:async(a,t)=>{await r(`DELETE FROM ${i} WHERE ref IN (${I(t.length)})`,t.map(o=>R(a,o)))}}},B="lunora_rag_vectors",U=5e4,$=100,V=null,h=d=>d??"",W=d=>{if(typeof d.exec!="function")throw new TypeError("@lunora/ai/rag: sqliteVectorStore requires an `exec` function");const n=q(d.table??B,"sqliteVectorStore `table`"),r=d.maxScan??U,{ann:l,exec:i}=d;if(l!==void 0&&(!Number.isInteger(l.dimensions)||l.dimensions<=0))throw new TypeError("@lunora/ai/rag: sqliteVectorStore `ann.dimensions` must be a positive integer");const T=l===void 0?void 0:D({dimensions:l.dimensions,exec:i,table:n}),u={deferredDelete:!0,maxDimensions:d.maxDimensions??l?.dimensions??!1,maxIdBytes:!1,maxMetadataBytes:!1,maxTopK:$,maxTopKWithMetadata:$};let g;const S=async()=>{g??=(async()=>{await i(`CREATE TABLE IF NOT EXISTS ${n} (id TEXT NOT NULL, namespace TEXT NOT NULL DEFAULT '', vector TEXT NOT NULL, metadata TEXT, PRIMARY KEY (namespace, id))`,[]),await i(`CREATE INDEX IF NOT EXISTS ${n}_namespace ON ${n} (namespace)`,[]),await T?.ensure()})().catch(e=>{throw g=void 0,e}),await g},b=async e=>{if(await S(),!e.embed)throw new TypeError("@lunora/ai/rag: sqliteVectorStore requires an `embed` function on upsert");const c=await e.embed(e.input),s=h(e.namespace);await T?.put(s,e.id,c),await i(`INSERT INTO ${n} (id, namespace, vector, metadata) VALUES (${I(4)}) ON CONFLICT(namespace, id) DO UPDATE SET vector = excluded.vector, metadata = excluded.metadata`,[e.id,s,JSON.stringify([...c]),e.metadata===void 0?V:JSON.stringify(e.metadata)])},a=async(e,c)=>{if(await S(),e.length===0)return[];const s=[];for(const m of A(e)){const E=await i(`SELECT id, metadata FROM ${n} WHERE namespace = ? AND id IN (${I(m.length)})`,[h(c),...m]);for(const w of E){const f=y(w.metadata);s.push({id:String(w.id),...f===void 0?{}:{metadata:f}})}}return s},t=async(e,c,s)=>{const m=h(s.namespace),E=await e.nearest(m,c,s.topK??10),w=await a(E.map(L=>L.id),m),f=new Map(w.map(L=>[L.id,L])),N=[];for(const{distance:L,id:p}of E){const v=f.get(p);v!==void 0&&N.push({id:p,score:1-L,...s.returnMetadata==="none"||v.metadata===void 0?{}:{metadata:v.metadata}})}return{count:N.length,matches:N}};return{capabilities:u,deleteByIds:async(e,c,s,m)=>{if(await S(),e.length===0){await m?.();return}for(const E of A(e))await i(`DELETE FROM ${n} WHERE namespace = ? AND id IN (${I(E.length)})`,[h(c),...E]),await T?.remove(h(c),E);await m?.()},getByIds:a,query:async e=>{await S();let c;if(e.embed&&e.input!==void 0)c=await e.embed(e.input);else throw new TypeError("@lunora/ai/rag: sqliteVectorStore query requires both `input` and `embed`");if(T!==void 0&&e.filter===void 0)return t(T,c,e);const s=await i(`SELECT id, vector, metadata FROM ${n} WHERE namespace = ? LIMIT ?`,[h(e.namespace),r+1]);if(s.length>r)throw new RangeError(`@lunora/ai/rag: sqliteVectorStore scanned ${String(s.length)} vectors in namespace "${h(e.namespace)}", over the ${String(r)} limit — search here is brute force and linear, so this namespace has outgrown it. Shard it further, or move this index to Vectorize or a pgvector backend`);const m=[];for(const w of s){const f=y(w.metadata);if(!x(f,e.filter))continue;const N=y(w.vector);N!==void 0&&m.push({id:String(w.id),score:F(c,N),...e.returnMetadata==="none"||f===void 0?{}:{metadata:f}})}const E=m.toSorted((w,f)=>f.score-w.score).slice(0,e.topK??10);return{count:E.length,matches:E}},upsert:b}};export{W as sqliteVectorStore};

package/dist/packem_shared/stable-key-B_BlboiY.mjs

@@ -1 +0,0 @@
-const a=/["\\\u0000-\u001F\uD800-\uDFFF]/,f=t=>a.test(t)?JSON.stringify(t):`"${t}"`,y=t=>{if(t===void 0)return"null";if(typeof t=="bigint")throw new TypeError("stableStringify: cannot use a bigint in a stable JSON cache key — pass it as a string, or use stableWireKey");if(typeof t=="number"){if(Number.isNaN(t))return"nan";if(t===1/0)return"inf";if(t===-1/0)return"-inf";if(Object.is(t,-0))return"-0"}if(typeof t=="string")return f(t);if(t===null||typeof t!="object")return JSON.stringify(t);if(Array.isArray(t)){let r="[";for(let n=0;n<t.length;n++)n>0&&(r+=","),r+=y(t[n]);return r+"]"}const i=Object.getPrototypeOf(t);if(i!==null&&i!==Object.prototype){const r=t.constructor?.name??"value";throw new TypeError(`stableStringify: cannot use a ${r} in a stable JSON cache key — only plain objects, arrays, and JSON primitives are supported (wire-typed values key via stableWireKey)`)}const o=t,c=Object.keys(o).sort();let e="{",s=!0;for(const r of c){const n=o[r];n!==void 0&&(s?s=!1:e+=",",e+=f(r),e+=":",e+=y(n))}return e+"}"};export{y as s};