Bedrock Knowledge Bases Chunking Strategies That Fit Code RAG

# ❌ Fixed-size on source — splits mid-function
def fixed_chunks(text: str, size: int = 800, overlap: int = 100):
    out = []
    i = 0
    while i < len(text):
        out.append(text[i : i + size])
        i += size - overlap
    return out

# ✅ Fixed-size only for runbooks / plain ADRs
def fixed_for_prose(path: str, text: str):
    if path.endswith((".md", ".txt")) and "/src/" not in path:
        return fixed_chunks(text, size=1200, overlap=150)
    raise ValueError("use_ast_chunker_for_code")

import numpy as np

def semantic_breaks(sentence_embeddings: list[np.ndarray], threshold: float = 0.55):
    breaks = [0]
    for i in range(1, len(sentence_embeddings)):
        sim = float(np.dot(sentence_embeddings[i - 1], sentence_embeddings[i]))
        if sim < threshold:
            breaks.append(i)
    breaks.append(len(sentence_embeddings))
    return breaks  # slice sentences[breaks[j]:breaks[j+1]]

// chunk-ts.ts — illustrative ts-morph chunker
import { Project } from "ts-morph";

export function chunkTypeScript(filePath: string, source: string) {
  const project = new Project({ useInMemoryFileSystem: true });
  const sf = project.createSourceFile(filePath, source);
  const chunks: { id: string; text: string; metadata: Record<string, string> }[] = [];

  for (const fn of sf.getFunctions()) {
    if (!fn.isExported()) continue;
    const name = fn.getName() ?? "anonymous";
    const start = fn.getStartLineNumber();
    const text = `// file: ${filePath}\n// symbol: ${name}\n${fn.getText()}`;
    // ✅ Symbol-bounded chunk with path breadcrumb
    chunks.push({
      id: `${filePath}::${name}`,
      text,
      metadata: { path: filePath, symbol: name, language: "typescript", start: String(start) },
    });
  }

  // ❌ Don’t embed import-only noise as its own retrieval unit
  return chunks.filter((c) => c.text.split("\n").length > 3);
}

{
  "chunkingStrategy": "NONE",
  "comment": "Pre-chunked AST units already in S3; do not re-window"
}

# ✅ Upload one JSON/text object per symbol with metadata sidecar
aws s3 cp chunks/auth/getSession.json s3://kb-code/auth/getSession.json \
  --metadata language=typescript,repo=platform,symbol=getSession

def hit_at_k(retrieved_ids: list[str], gold_ids: set[str], k: int = 5) -> float:
    return 1.0 if gold_ids.intersection(retrieved_ids[:k]) else 0.0