RAG / LLM apps

# 1. Chunk the source text into ~512-token windows with 50-token overlap.
# 2. Embed each chunk with whatever embedding model you use.
# 3. Write the chunk row + the embedding + the FTS index entry.

from originchain import OriginChain
from openai import OpenAI
import time, os

db = OriginChain(
    base_url=f"https://{os.environ['OC_HOST']}",
    bearer=os.environ["OC_TOKEN"],
    tenant=os.environ["OC_TENANT"],
)
ai = OpenAI()

def ingest(doc_id, source, full_text):
    chunks = chunk_text(full_text, tokens=512, overlap=50)
    emb = ai.embeddings.create(
        model="text-embedding-3-small",
        input=[c.text for c in chunks],
    )

    for i, c in enumerate(chunks):
        cid = f"{doc_id}:{i}"

        # 1. The row.
        db.rows.put("rag.chunks", {
            "id":         cid,
            "doc_id":     doc_id,
            "source":     source,
            "page":       c.page,
            "text":       c.text,
            "created_ms": int(time.time() * 1000),
        })

        # 2. The vector embedding.
        db.vector.put("rag.chunks", cid, emb.data[i].embedding,
                      metadata={"source": source, "page": c.page})

        # 3. The BM25 index.
        db.fts.index("rag.chunks", "text", doc_id=cid, text=c.text)

// TS SDK doesn't wrap row writes yet - using fetch for the row write,
// SDK for vector + FTS. Same logic as Python above.
import { OriginChainClient } from "@originchain/sdk";
import OpenAI from "openai";

const db = new OriginChainClient({
  baseUrl: `https://${process.env.OC_HOST}`,
  bearer:  process.env.OC_TOKEN!,
});
const ai = new OpenAI();

async function ingest(docId: string, source: string, fullText: string) {
  const chunks = chunkText(fullText, { tokens: 512, overlap: 50 });
  const emb = await ai.embeddings.create({
    model: "text-embedding-3-small",
    input: chunks.map(c => c.text),
  });

  for (let i = 0; i < chunks.length; i++) {
    const cid = `${docId}:${i}`;

    // 1. Row write via fetch.
    await fetch(`https://${process.env.OC_HOST}/v1/tenants/${process.env.OC_TENANT}/rows/rag.chunks`, {
      method: "POST",
      headers: {
        "Authorization": `Bearer ${process.env.OC_TOKEN}`,
        "Content-Type":  "application/json",
      },
      body: JSON.stringify({
        id: cid, doc_id: docId, source, page: chunks[i].page,
        text: chunks[i].text, created_ms: Date.now(),
      }),
    });

    // 2. Vector embedding.
    await db.vectorPut("rag.chunks", {
      id: cid, embedding: emb.data[i].embedding, dim: 1536, metric: "cosine",
      metadata: { source, page: chunks[i].page },
    });

    // 3. BM25 index.
    await db.ftsIndex("rag.chunks", "text", { doc_id: cid, text: chunks[i].text });
  }
}

# 1. Embed the question.
# 2. Run vector topk + BM25 search in parallel.
# 3. Fuse with Reciprocal Rank Fusion.
# 4. Pull the chunk rows for the top-k IDs.
# 5. Send them to the LLM as context.

def answer(question, source_filter=None):
    # 1.
    q_vec = ai.embeddings.create(
        model="text-embedding-3-small",
        input=question,
    ).data[0].embedding

    # 2. Parallel retrieval (one round-trip each, can run concurrently).
    vec_hits = db.vector_topk(
        "rag.chunks",
        query=q_vec, k=20, dim=1536, metric="cosine",
        filter={"source": source_filter} if source_filter else None,
    )
    fts_hits = db.fts.search("rag.chunks", "text", q=question, mode="bm25", k=20)

    # 3. Reciprocal Rank Fusion. Pick the top 5 fused IDs.
    fused_ids = rrf([h.id for h in vec_hits], [h.doc_id for h in fts_hits])[:5]

    # 4. Pull full chunk text + metadata.
    rows = []
    for cid in fused_ids:
        rows.append(db.rows.get("rag.chunks", cid))

    # 5. Send to the LLM as bounded, cited context.
    context = "\n\n".join(
        f"[Source {i+1}] ({r['source']} p.{r['page']}) {r['text']}"
        for i, r in enumerate(rows)
    )
    completion = ai.chat.completions.create(
        model="gpt-4o",
        temperature=0.0,
        messages=[
            { "role": "system", "content":
              "Answer using ONLY the context below. Cite every claim with [Source N]. "
              "If the context is insufficient, say so." },
            { "role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}" },
        ],
    )
    return completion.choices[0].message.content

async function answer(question: string, sourceFilter?: string) {
  // 1. Embed the question.
  const qVec = (await ai.embeddings.create({
    model: "text-embedding-3-small", input: question,
  })).data[0].embedding;

  // 2. Parallel retrieval.
  const [vecHits, ftsHits] = await Promise.all([
    db.vectorTopk("rag.chunks", {
      query: qVec, k: 20, dim: 1536, metric: "cosine",
      filter: sourceFilter ? { source: sourceFilter } : undefined,
    }),
    db.ftsSearch("rag.chunks", "text", { q: question, mode: "bm25", k: 20 }),
  ]);

  // 3. Reciprocal Rank Fusion. Pick top 5.
  const fusedIds = rrf(
    vecHits.map(h => h.id),
    (ftsHits as { doc_id: string }[]).map(h => h.doc_id),
  ).slice(0, 5);

  // 4. Fetch chunks via raw fetch (row helpers ship soon).
  const rows = await Promise.all(fusedIds.map(async (cid) => {
    const r = await fetch(
      `https://${process.env.OC_HOST}/v1/tenants/${process.env.OC_TENANT}/rows/rag.chunks/${cid}`,
      { headers: { "Authorization": `Bearer ${process.env.OC_TOKEN}` } },
    );
    return r.json();
  }));

  // 5. Send to LLM.
  const context = rows.map((r, i) =>
    `[Source ${i+1}] (${r.source} p.${r.page}) ${r.text}`,
  ).join("\n\n");

  const completion = await ai.chat.completions.create({
    model: "gpt-4o", temperature: 0.0,
    messages: [
      { role: "system", content:
        "Answer using ONLY the context below. Cite every claim with [Source N]. " +
        "If the context is insufficient, say so." },
      { role: "user", content: `Context:\n${context}\n\nQuestion: ${question}` },
    ],
  });
  return completion.choices[0].message.content;
}