Served on MixpeekEmbeddingVerified 2026-11-05
Jina Embeddings v2 Base Code
jinaai/jina-embeddings-v2-base-code
Jina Embeddings v2 Base Code is a text embedding model (Apache-2.0). Served on Mixpeek, scaling to zero when idle.
A Ray Serve app in Mixpeek's inference registry hosts it. It starts at zero replicas and wakes on first use.
New opens the Designer in Studio. For an existing namespace, open it in Studio and use its Designer tab.
No demo for Jina Embeddings v2 Base Code yet
A video, image, slideshow or playground goes here once we record one on our own data.
What it is good and bad at
- 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.
- Task
- Embedding
- Input
- Text
- Output
- Vector
- Use cases
- Code search, Web pages
Templates that use it
No template uses this model yet. Browse templates.
Input and output
Input
- text
- max_tokens
- 8192
- truncation
- true
- prompts
- none
Output
- vector
- dims
- 768
- distance
- cosine
- type
- dense
How Mixpeek wires it
- Extractors
web_scraper@v1generate_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
- Combines with
- web_scraper: code-block vectors beside E5 page text vectors
How it runs
- Status
- Served on Mixpeek 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
- safetensors, needs remote code
- Parameters
- 161 M
- Size on disk
- 322 MB
- Preprocessing
- Tokenize with truncation at max_length (default 8192); fp16 on GPU.
- Postprocessing
- Mean pool over the attention mask, L2-normalize (768 dims).
- Serving
- both
- Hardware
- Runs on CPU (slower without a GPU)
Scale to zero
- Minimum replicas
- 0
- Maximum replicas
- 8
- Idle timeout
- 300 s
- Memory
- 1 GB
- CPUs
- 0.25
- GPUs
- 0
- Cold start, node warm
- Not recorded
- Cold start, new node
- Not recorded
Measured cost
Unmeasured
No committed throughput or cost measurement for this model.
Our evaluations
Unmeasured
We have not evaluated this model on our own data yet. Publisher results are in the sources below.
Questions
- What is Jina Embeddings v2 Base Code best at?
- Code snippets and natural-language-to-code search across about 30 programming languages, with up to 8192-token inputs (ALiBi).
- What are the limits of Jina Embeddings v2 Base Code?
- 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.
- Can Jina Embeddings v2 Base Code be used commercially?
- Yes. Apache-2.0 weights; the modeling code is loaded from the hub (remote code).
- How does Jina Embeddings v2 Base Code run on Mixpeek?
- Ray Serve app in the inference registry (query embeds); web_scraper loads the same repo in-process (DocTypeCodeEmbedder).