embedding-strategies — Skillopedia

Embedding Strategies Guide to selecting and optimizing embedding models for vector search applications. When to Use This Skill - Choosing embedding models for RAG - Optimizing chunking strategies - Fine-tuning embeddings for domains - Comparing embedding model performance - Reducing embedding dimensions - Handling multilingual content Core Concepts 1. Embedding Model Comparison (2026) | Model | Dimensions | Max Tokens | Best For | | -------------------------- | ---------- | ---------- | ----------------------------------- | | voyage-3-large | 1024 | 32000 | Claude apps (Anthropic recommended)…

\n) -> List[Tuple[str, str]]:\n \"\"\"Chunk markdown by headers, preserving hierarchy.\"\"\"\n lines = text.split('\\n')\n chunks = []\n current_header = \"\"\n current_content = []\n\n for line in lines:\n if re.match(headers_pattern, line, re.MULTILINE):\n if current_content:\n chunks.append((current_header, '\\n'.join(current_content)))\n current_header = line\n current_content = []\n else:\n current_content.append(line)\n\n if current_content:\n chunks.append((current_header, '\\n'.join(current_content)))\n\n return chunks\n\n\ndef recursive_character_splitter(\n text: str,\n chunk_size: int = 1000,\n chunk_overlap: int = 200,\n separators: List[str] = None\n) -> List[str]:\n \"\"\"LangChain-style recursive splitter.\"\"\"\n separators = separators or [\"\\n\\n\", \"\\n\", \". \", \" \", \"\"]\n\n def split_text(text: str, separators: List[str]) -> List[str]:\n if not text:\n return []\n\n separator = separators[0]\n remaining_separators = separators[1:]\n\n if separator == \"\":\n # Character-level split\n return [text[i:i+chunk_size] for i in range(0, len(text), chunk_size - chunk_overlap)]\n\n splits = text.split(separator)\n chunks = []\n current_chunk = []\n current_length = 0\n\n for split in splits:\n split_length = len(split) + len(separator)\n\n if current_length + split_length > chunk_size and current_chunk:\n chunk_text = separator.join(current_chunk)\n\n # Recursively split if still too large\n if len(chunk_text) > chunk_size and remaining_separators:\n chunks.extend(split_text(chunk_text, remaining_separators))\n else:\n chunks.append(chunk_text)\n\n # Start new chunk with overlap\n overlap_splits = []\n overlap_length = 0\n for s in reversed(current_chunk):\n if overlap_length + len(s) \u003c= chunk_overlap:\n overlap_splits.insert(0, s)\n overlap_length += len(s)\n else:\n break\n current_chunk = overlap_splits\n current_length = overlap_length\n\n current_chunk.append(split)\n current_length += split_length\n\n if current_chunk:\n chunks.append(separator.join(current_chunk))\n\n return chunks\n\n return split_text(text, separators)\n```\n\n### Template 5: Domain-Specific Embedding Pipeline\n\n```python\nimport re\nfrom typing import List, Optional\nfrom dataclasses import dataclass\n\n@dataclass\nclass EmbeddedDocument:\n id: str\n document_id: str\n chunk_index: int\n text: str\n embedding: List[float]\n metadata: dict\n\nclass DomainEmbeddingPipeline:\n \"\"\"Pipeline for domain-specific embeddings.\"\"\"\n\n def __init__(\n self,\n embedding_model: str = \"voyage-3-large\",\n chunk_size: int = 512,\n chunk_overlap: int = 50,\n preprocessing_fn=None\n ):\n self.embeddings = VoyageAIEmbeddings(model=embedding_model)\n self.chunk_size = chunk_size\n self.chunk_overlap = chunk_overlap\n self.preprocess = preprocessing_fn or self._default_preprocess\n\n def _default_preprocess(self, text: str) -> str:\n \"\"\"Default preprocessing.\"\"\"\n # Remove excessive whitespace\n text = re.sub(r'\\s+', ' ', text)\n # Remove special characters (customize for your domain)\n text = re.sub(r'[^\\w\\s.,!?-]', '', text)\n return text.strip()\n\n async def process_documents(\n self,\n documents: List[dict],\n id_field: str = \"id\",\n content_field: str = \"content\",\n metadata_fields: Optional[List[str]] = None\n ) -> List[EmbeddedDocument]:\n \"\"\"Process documents for vector storage.\"\"\"\n processed = []\n\n for doc in documents:\n content = doc[content_field]\n doc_id = doc[id_field]\n\n # Preprocess\n cleaned = self.preprocess(content)\n\n # Chunk\n chunks = chunk_by_tokens(\n cleaned,\n self.chunk_size,\n self.chunk_overlap\n )\n\n # Create embeddings\n embeddings = await self.embeddings.aembed_documents(chunks)\n\n # Create records\n for i, (chunk, embedding) in enumerate(zip(chunks, embeddings)):\n metadata = {\"document_id\": doc_id, \"chunk_index\": i}\n\n # Add specified metadata fields\n if metadata_fields:\n for field in metadata_fields:\n if field in doc:\n metadata[field] = doc[field]\n\n processed.append(EmbeddedDocument(\n id=f\"{doc_id}_chunk_{i}\",\n document_id=doc_id,\n chunk_index=i,\n text=chunk,\n embedding=embedding,\n metadata=metadata\n ))\n\n return processed\n\n\n# Code-specific pipeline\nclass CodeEmbeddingPipeline:\n \"\"\"Specialized pipeline for code embeddings.\"\"\"\n\n def __init__(self):\n # Use Voyage's code-specific model\n self.embeddings = VoyageAIEmbeddings(model=\"voyage-code-3\")\n\n def chunk_code(self, code: str, language: str) -> List[dict]:\n \"\"\"Chunk code by functions/classes using tree-sitter.\"\"\"\n try:\n import tree_sitter_languages\n parser = tree_sitter_languages.get_parser(language)\n tree = parser.parse(bytes(code, \"utf8\"))\n\n chunks = []\n # Extract function and class definitions\n self._extract_nodes(tree.root_node, code, chunks)\n return chunks\n except ImportError:\n # Fallback to simple chunking\n return [{\"text\": code, \"type\": \"module\"}]\n\n def _extract_nodes(self, node, source_code: str, chunks: list):\n \"\"\"Recursively extract function/class definitions.\"\"\"\n if node.type in ['function_definition', 'class_definition', 'method_definition']:\n text = source_code[node.start_byte:node.end_byte]\n chunks.append({\n \"text\": text,\n \"type\": node.type,\n \"name\": self._get_name(node),\n \"start_line\": node.start_point[0],\n \"end_line\": node.end_point[0]\n })\n for child in node.children:\n self._extract_nodes(child, source_code, chunks)\n\n def _get_name(self, node) -> str:\n \"\"\"Extract name from function/class node.\"\"\"\n for child in node.children:\n if child.type == 'identifier' or child.type == 'name':\n return child.text.decode('utf8')\n return \"unknown\"\n\n async def embed_with_context(\n self,\n chunk: str,\n context: str = \"\"\n ) -> List[float]:\n \"\"\"Embed code with surrounding context.\"\"\"\n if context:\n combined = f\"Context: {context}\\n\\nCode:\\n{chunk}\"\n else:\n combined = chunk\n return await self.embeddings.aembed_query(combined)\n```\n\n### Template 6: Embedding Quality Evaluation\n\n```python\nimport numpy as np\nfrom typing import List, Dict\n\ndef evaluate_retrieval_quality(\n queries: List[str],\n relevant_docs: List[List[str]], # List of relevant doc IDs per query\n retrieved_docs: List[List[str]], # List of retrieved doc IDs per query\n k: int = 10\n) -> Dict[str, float]:\n \"\"\"Evaluate embedding quality for retrieval.\"\"\"\n\n def precision_at_k(relevant: set, retrieved: List[str], k: int) -> float:\n retrieved_k = retrieved[:k]\n relevant_retrieved = len(set(retrieved_k) & relevant)\n return relevant_retrieved / k if k > 0 else 0\n\n def recall_at_k(relevant: set, retrieved: List[str], k: int) -> float:\n retrieved_k = retrieved[:k]\n relevant_retrieved = len(set(retrieved_k) & relevant)\n return relevant_retrieved / len(relevant) if relevant else 0\n\n def mrr(relevant: set, retrieved: List[str]) -> float:\n for i, doc in enumerate(retrieved):\n if doc in relevant:\n return 1 / (i + 1)\n return 0\n\n def ndcg_at_k(relevant: set, retrieved: List[str], k: int) -> float:\n dcg = sum(\n 1 / np.log2(i + 2) if doc in relevant else 0\n for i, doc in enumerate(retrieved[:k])\n )\n ideal_dcg = sum(1 / np.log2(i + 2) for i in range(min(len(relevant), k)))\n return dcg / ideal_dcg if ideal_dcg > 0 else 0\n\n metrics = {\n f\"precision@{k}\": [],\n f\"recall@{k}\": [],\n \"mrr\": [],\n f\"ndcg@{k}\": []\n }\n\n for relevant, retrieved in zip(relevant_docs, retrieved_docs):\n relevant_set = set(relevant)\n metrics[f\"precision@{k}\"].append(precision_at_k(relevant_set, retrieved, k))\n metrics[f\"recall@{k}\"].append(recall_at_k(relevant_set, retrieved, k))\n metrics[\"mrr\"].append(mrr(relevant_set, retrieved))\n metrics[f\"ndcg@{k}\"].append(ndcg_at_k(relevant_set, retrieved, k))\n\n return {name: np.mean(values) for name, values in metrics.items()}\n\n\ndef compute_embedding_similarity(\n embeddings1: np.ndarray,\n embeddings2: np.ndarray,\n metric: str = \"cosine\"\n) -> np.ndarray:\n \"\"\"Compute similarity matrix between embedding sets.\"\"\"\n if metric == \"cosine\":\n # Normalize and compute dot product\n norm1 = embeddings1 / np.linalg.norm(embeddings1, axis=1, keepdims=True)\n norm2 = embeddings2 / np.linalg.norm(embeddings2, axis=1, keepdims=True)\n return norm1 @ norm2.T\n elif metric == \"euclidean\":\n from scipy.spatial.distance import cdist\n return -cdist(embeddings1, embeddings2, metric='euclidean')\n elif metric == \"dot\":\n return embeddings1 @ embeddings2.T\n else:\n raise ValueError(f\"Unknown metric: {metric}\")\n\n\ndef compare_embedding_models(\n texts: List[str],\n models: Dict[str, callable],\n queries: List[str],\n relevant_indices: List[List[int]],\n k: int = 5\n) -> Dict[str, Dict[str, float]]:\n \"\"\"Compare multiple embedding models on retrieval quality.\"\"\"\n results = {}\n\n for model_name, embed_fn in models.items():\n # Embed all texts\n doc_embeddings = np.array(embed_fn(texts))\n\n retrieved_per_query = []\n for query in queries:\n query_embedding = np.array(embed_fn([query])[0])\n # Compute similarities\n similarities = compute_embedding_similarity(\n query_embedding.reshape(1, -1),\n doc_embeddings,\n metric=\"cosine\"\n )[0]\n # Get top-k indices\n top_k_indices = np.argsort(similarities)[::-1][:k]\n retrieved_per_query.append([str(i) for i in top_k_indices])\n\n # Convert relevant indices to string IDs\n relevant_docs = [[str(i) for i in indices] for indices in relevant_indices]\n\n results[model_name] = evaluate_retrieval_quality(\n queries, relevant_docs, retrieved_per_query, k\n )\n\n return results\n```\n","content_type":"text/markdown; charset=utf-8","language":"markdown","size":16834,"content_sha256":"03f020b1bed3b6e8724a6700ae5860ae38b0621694035d83bd9ede133a77120c"}],"content_json":{"type":"doc","content":[{"type":"heading","attrs":{"level":1},"content":[{"text":"Embedding Strategies","type":"text"}]},{"type":"paragraph","content":[{"text":"Guide to selecting and optimizing embedding models for vector search applications.","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"When to Use This Skill","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Choosing embedding models for RAG","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Optimizing chunking strategies","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Fine-tuning embeddings for domains","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Comparing embedding model performance","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Reducing embedding dimensions","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Handling multilingual content","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Core Concepts","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"1. Embedding Model Comparison (2026)","type":"text"}]},{"type":"table","attrs":{"layout":null},"content":[{"type":"tr","content":[{"type":"th","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Model","type":"text"}]}]},{"type":"th","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Dimensions","type":"text"}]}]},{"type":"th","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Max Tokens","type":"text"}]}]},{"type":"th","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Best For","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"voyage-3-large","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"32000","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Claude apps (Anthropic recommended)","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"voyage-3","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"32000","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Claude apps, cost-effective","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"voyage-code-3","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"32000","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Code search","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"voyage-finance-2","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"32000","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Financial documents","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"voyage-law-2","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"32000","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Legal documents","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"text-embedding-3-large","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"3072","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"8191","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"OpenAI apps, high accuracy","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"text-embedding-3-small","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1536","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"8191","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"OpenAI apps, cost-effective","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"bge-large-en-v1.5","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"512","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Open source, local deployment","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"all-MiniLM-L6-v2","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"384","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"256","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Fast, lightweight","type":"text"}]}]}]},{"type":"tr","content":[{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"multilingual-e5-large","type":"text","marks":[{"type":"strong"}]}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"1024","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"512","type":"text"}]}]},{"type":"td","attrs":{"colspan":1,"rowspan":1,"colwidth":null,"alignment":""},"content":[{"type":"paragraph","content":[{"text":"Multi-language","type":"text"}]}]}]}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"2. Embedding Pipeline","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"Document → Chunking → Preprocessing → Embedding Model → Vector\n ↓\n [Overlap, Size] [Clean, Normalize] [API/Local]","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Templates and detailed worked examples","type":"text"}]},{"type":"paragraph","content":[{"text":"Full template library and detailed worked examples live in ","type":"text"},{"text":"references/details.md","type":"text","marks":[{"type":"code_inline"}]},{"text":". Read that file when you need the concrete templates.","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Best Practices","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"Do's","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Match model to use case","type":"text","marks":[{"type":"strong"}]},{"text":": Code vs prose vs multilingual","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Chunk thoughtfully","type":"text","marks":[{"type":"strong"}]},{"text":": Preserve semantic boundaries","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Normalize embeddings","type":"text","marks":[{"type":"strong"}]},{"text":": For cosine similarity search","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Batch requests","type":"text","marks":[{"type":"strong"}]},{"text":": More efficient than one-by-one","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Cache embeddings","type":"text","marks":[{"type":"strong"}]},{"text":": Avoid recomputing for static content","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Use Voyage AI for Claude apps","type":"text","marks":[{"type":"strong"}]},{"text":": Recommended by Anthropic","type":"text"}]}]}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"Don'ts","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Don't ignore token limits","type":"text","marks":[{"type":"strong"}]},{"text":": Truncation loses information","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Don't mix embedding models","type":"text","marks":[{"type":"strong"}]},{"text":": Incompatible vector spaces","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Don't skip preprocessing","type":"text","marks":[{"type":"strong"}]},{"text":": Garbage in, garbage out","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Don't over-chunk","type":"text","marks":[{"type":"strong"}]},{"text":": Lose important context","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Don't forget metadata","type":"text","marks":[{"type":"strong"}]},{"text":": Essential for filtering and debugging","type":"text"}]}]}]}]},"metadata":{"date":"2026-11-02","name":"embedding-strategies","author":"@skillopedia","source":{"stars":42106,"repo_name":"agents","origin_url":"https://github.com/wshobson/agents/blob/HEAD/plugins/llm-application-dev/skills/embedding-strategies/SKILL.md","repo_owner":"wshobson","body_sha256":"d87e8c3e519cdc1d4d4578412aeb681e931ada45de143159610d8fe3cda20648","cluster_key":"465fcc335535c490838bf392dac920ed2c57eb98a1e8a229e64c92a4f65f7b80","clean_bundle":{"format":"clean-skill-bundle-v1","source":"wshobson/agents/plugins/llm-application-dev/skills/embedding-strategies/SKILL.md","text_bytes":16834,"source_commit":"7e2fb559cf4b824b27f1fec49fe88f7511066d26","skills_sh_rank":2137,"attachment_count":1,"text_attachments":1,"attachment_storage":"skill_attachments","binary_attachments":0},"cluster_size":1,"skill_md_path":"plugins/llm-application-dev/skills/embedding-strategies/SKILL.md","import_metadata":{"date":"2026-11-02","author":"@skillopedia","version":"v1","category":"ai-agent-development","category_label":"AI"},"exact_dupes_collapsed_into_this":0},"version":"v1","category":"ai-agent-development","import_tag":"skills-sh-top20k-2026-11","description":"Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains."}},"renderedAt":1793686521516}

Important: agents should read /llm.txt, /llms.txt, or /.well-known/skills.json to discover the public Skillopedia API.