{
  "id": "jina-embeddings-v2-base-code",
  "identity": {
    "family": "jina-embeddings-v2",
    "display_name": "Jina Embeddings v2 Base Code",
    "hub_id": "jinaai/jina-embeddings-v2-base-code",
    "api_name": null,
    "revision": null,
    "variants": [],
    "license": "Apache-2.0",
    "commercial_use": true,
    "commercial_use_note": "Apache-2.0 weights; the modeling code is loaded from the hub (remote code).",
    "release_date": "2023-11",
    "paper_url": "https://arxiv.org/abs/2310.19923",
    "repo_url": "https://huggingface.co/jinaai/jina-embeddings-v2-base-code"
  },
  "task": {
    "category": "embedding",
    "modalities_in": [
      "text"
    ],
    "modalities_out": [
      "vector"
    ],
    "best_at": "Code snippets and natural-language-to-code search across about 30 programming languages, with up to 8192-token inputs (ALiBi).",
    "worst_at": "General prose (E5 is the text default); the loader must run hub code, so a hub change can change behavior without a version bump here."
  },
  "io": {
    "input": {
      "text": {
        "max_tokens": 8192,
        "truncation": true
      },
      "prompts": "none"
    },
    "output": {
      "vector": {
        "dims": 768,
        "distance": "cosine",
        "type": "dense"
      }
    }
  },
  "mixpeek_wiring": {
    "extractors": [
      {
        "extractor": "web_scraper@v1",
        "selected_by": "generate_code_embeddings=true (default true); code blocks"
      }
    ],
    "feature_uris": [
      "mixpeek://web_scraper@v1/jinaai__jina_embeddings_v2_base_code"
    ],
    "vector_indexes": [
      "jinaai__jina_embeddings_v2_base_code"
    ],
    "retriever_stages": [
      "feature_search"
    ],
    "composes_with": [
      "web_scraper: code-block vectors beside E5 page text vectors"
    ]
  },
  "run": {
    "status": "served",
    "status_reason": "Ray Serve app in the inference registry (query embeds); web_scraper loads the same repo in-process (DocTypeCodeEmbedder).",
    "serve_apps": [
      "jinaai__jina_embeddings_v2_base_code"
    ],
    "runtime": "transformers AutoModel + AutoTokenizer with trust_remote_code=True (JinaBert hub code), mean pooling",
    "weights_format": "safetensors",
    "trust_remote_code": true,
    "size_on_disk_mb": 322,
    "params_millions": 161,
    "preprocessing": "Tokenize with truncation at max_length (default 8192); fp16 on GPU.",
    "postprocessing": "Mean pool over the attention mask, L2-normalize (768 dims).",
    "serving_shape": "both",
    "batch_size": null,
    "serve_batch": null,
    "scale_to_zero": {
      "min_replicas": 0,
      "max_replicas": 8,
      "idle_timeout_s": 300,
      "memory_gb": 1,
      "num_cpus": 0.25,
      "num_gpus": 0,
      "cold_start_s": {
        "warm_node_s": null,
        "new_node_s": null,
        "source": null
      },
      "cpu_fallback": true
    }
  },
  "cost": {
    "unmeasured": true,
    "measured": null,
    "note": "No committed throughput or cost measurement for this model."
  },
  "evidence": {
    "unmeasured": true,
    "items": []
  },
  "refs": [
    "hf://jinaai/jina-embeddings-v2-base-code@516f4baf13dec4ddddda8631e019b5737c8bc250"
  ],
  "formats": [
    {
      "ref": "hf://jinaai/jina-embeddings-v2-base-code@516f4baf13dec4ddddda8631e019b5737c8bc250",
      "format": "safetensors",
      "file": "model.safetensors",
      "loader": "transformers / open_clip from_pretrained; Mixpeek Hub import (api/models/huggingface.py)",
      "supported_today": true
    },
    {
      "ref": "hf://jinaai/jina-embeddings-v2-base-code@516f4baf13dec4ddddda8631e019b5737c8bc250",
      "format": "onnx",
      "file": "3 files, e.g. onnx/model.onnx",
      "loader": "onnxruntime; Mixpeek model upload (api/models/loadability.py, ONNX IR <= 11)",
      "supported_today": true
    },
    {
      "ref": "hf://jinaai/jina-embeddings-v2-base-code@516f4baf13dec4ddddda8631e019b5737c8bc250",
      "format": "pytorch_bin",
      "file": "pytorch_model.bin",
      "loader": "torch.load (pickle); Mixpeek refuses pickle weights (shared/security/torch_pickle.py)",
      "supported_today": false
    }
  ],
  "use_cases": [
    "code-search",
    "web-pages"
  ],
  "recommended": {
    "value": false,
    "for": [],
    "reason": null
  },
  "demos": [],
  "seo": {
    "title": "Jina Embeddings v2 Base Code: embedding model",
    "description": "Jina Embeddings v2 Base Code is a text embedding model (Apache-2.0). Served on Mixpeek, scaling to zero when idle.",
    "keywords": [
      "Jina Embeddings v2 Base Code",
      "jina-embeddings-v2",
      "embedding",
      "jinaai/jina-embeddings-v2-base-code",
      "code-search",
      "web-pages"
    ],
    "faqs": [
      {
        "q": "What is Jina Embeddings v2 Base Code best at?",
        "a": "Code snippets and natural-language-to-code search across about 30 programming languages, with up to 8192-token inputs (ALiBi)."
      },
      {
        "q": "What are the limits of Jina Embeddings v2 Base Code?",
        "a": "General prose (E5 is the text default); the loader must run hub code, so a hub change can change behavior without a version bump here."
      },
      {
        "q": "Can Jina Embeddings v2 Base Code be used commercially?",
        "a": "Yes. Apache-2.0 weights; the modeling code is loaded from the hub (remote code)."
      },
      {
        "q": "How does Jina Embeddings v2 Base Code run on Mixpeek?",
        "a": "Ray Serve app in the inference registry (query embeds); web_scraper loads the same repo in-process (DocTypeCodeEmbedder)."
      }
    ]
  },
  "last_verified": "2026-11-05",
  "sources": [
    "https://huggingface.co/jinaai/jina-embeddings-v2-base-code",
    "https://huggingface.co/api/models/jinaai/jina-embeddings-v2-base-code",
    "https://arxiv.org/abs/2310.19923",
    "server/engine/inference/jinaai/jina_embeddings_v2_base_code/services.py",
    "server/engine/extractors/web_scraper/v1/processors/doctype_embedders.py",
    "server/engine/extractors/web_scraper/v1/definition.py"
  ],
  "registry": {
    "jinaai__jina_embeddings_v2_base_code": {
      "deployment": "jinaai__jina_embeddings_v2_base_code",
      "service_id": "jinaai/jina-embeddings-v2-base-code",
      "routes": "engine/inference/jinaai/jina_embeddings_v2_base_code/routes.py",
      "route_prefix": "/jina_embeddings_v2_base_code/v1",
      "enabled": true,
      "description": "Jina Embeddings V2 Base Code embedding model. Generates 768-dimensional dense embeddings for code. Supports 8192 token context with code-optimized representations.",
      "capabilities": {
        "category": "embedding",
        "modality_input": [
          "text"
        ],
        "modality_output": "vector",
        "supports_batch": true,
        "reranking_mode": null
      },
      "vector_config": {
        "dimensions": 768,
        "distance": "cosine",
        "vector_type": "dense"
      },
      "serve": {
        "min_replicas": 0,
        "max_replicas": 8,
        "idle_timeout_s": 300,
        "target_ongoing_requests": 3,
        "num_cpus": 0.25,
        "num_gpus": 0,
        "memory_gb": 1,
        "pinnable": false,
        "placement": "worker",
        "enabled": true
      },
      "interactive_twin": false,
      "interactive_serve": null,
      "schemas": {
        "input": "shared.inference.jinaai.jina_embeddings_v2_base_code.models.InferenceRequest",
        "output": "shared.inference.jinaai.jina_embeddings_v2_base_code.models.InferenceResponse",
        "config": "shared.inference.jinaai.jina_embeddings_v2_base_code.models.InferenceConfigs"
      }
    }
  },
  "templates": [],
  "usage": {
    "namespaces": null,
    "collections": null,
    "uncounted": true,
    "templates": 0,
    "counted_at": null,
    "source": null
  },
  "facets": {
    "status": "served",
    "category": "embedding",
    "family": "jina-embeddings-v2",
    "license": "Apache-2.0",
    "commercial_use": true,
    "modalities_in": [
      "text"
    ],
    "modalities_out": [
      "vector"
    ],
    "use_cases": [
      "code-search",
      "web-pages"
    ],
    "recommended": false,
    "release_date": "2023-11",
    "params_millions": 161,
    "size_on_disk_mb": 322,
    "vector_dims": 768,
    "vector_distance": "cosine",
    "weights_format": "safetensors",
    "formats": [
      "onnx",
      "pytorch_bin",
      "safetensors"
    ],
    "loadable_today": true,
    "trust_remote_code": true,
    "cpu_fallback": true,
    "num_gpus": 0,
    "memory_gb": 1,
    "min_replicas": 0,
    "serving_shape": "both",
    "served": true,
    "ref_schemes": [
      "hf"
    ],
    "has_evidence": false,
    "cost_measured": false,
    "template_count": 0,
    "usage_namespaces": null,
    "usage_collections": null,
    "usage_uncounted": true,
    "has_demo": false,
    "rank_score": 3
  },
  "rank_score": 3
}