Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks.
Install Embeddings
$ npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill embeddings --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/embeddings .claude/skills/embeddings && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "embeddings" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddings into .claude/skills/embeddings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "embeddings", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddingsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill embeddings --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/embeddings .agents/skills/embeddings && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "embeddings" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddings into .agents/skills/embeddings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "embeddings", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill embeddings --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/embeddings .cursor/skills/embeddings && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "embeddings" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddings into .cursor/skills/embeddings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "embeddings", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/unstructured/sub-skills/embeddings--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill embeddings --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/embeddings .gemini/skills/embeddings && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "embeddings" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddings into .gemini/skills/embeddings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "embeddings", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill embeddingsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/embeddings .github/skills/embeddings && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "embeddings" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddings into .github/skills/embeddings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "embeddings", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill embeddings --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/embeddings .opencode/skills/embeddings && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "embeddings" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/embeddings into .opencode/skills/embeddings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "embeddings", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
embeddings- GitHub stars
- 330
- Token cost
- ~1.4k tokens
- SKILL.md length
- 544 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks.
- Works in 5 steps: Route upstream work first → Select the provider module from… → Read credentials from environment… → …
- An agent needs BaseEmbeddingEncoder
- SKILL.md covers Start Here, Core Model, Safe Pattern and Metadata and Provenance, plus 3 more sections
- Runs Python scripts from its folder; calls python; needs OPENAI_API_KEY
What it does
Embeddings is an agent skill from VectorSpaceLab/AREX-Skill. Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks. Use when an agent needs BaseEmbeddingEncoder, EmbeddingConfig, OpenAI, OctoAI, Mixedbread, VoyageAI, VertexAI, Bedrock, or HuggingFace embedding guidance after partitioning or chunking.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/provider-reference.md`, `references/troubleshooting.md` and `scripts/embedding_config_check.py`).
It sits in AI & LLM Engineering, covering Embeddings. It works with Hugging Face, OpenAI and Vertex AI. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- An agent needs BaseEmbeddingEncoder
- EmbeddingConfig
- HuggingFace embedding guidance after partitioning
Example prompts
- “/embeddings”
Requirements
- Python 3
- A credential in OPENAI_API_KEY
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Route upstream work first
- Select the provider module from references/provider-reference.md and install only the provider SDKs needed for that route.
- Read credentials from environment variables or a secret manager at runtime; never hard-code, log, serialize, or commit API keys.
- Instantiate the provider-specific EmbeddingConfig and EmbeddingEncoder, then call
- Validate vector count and dimensions before persistence, especially when mixing providers or overriding model dimensions.
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENAI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Embeddings loads about 1.4k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 544 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 544 words, ~1,375 tokens.
Download SKILL.mdSave it as
.claude/skills/embeddings/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- embeddings
- description
- Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks. Use when an agent needs BaseEmbeddingEncoder, EmbeddingConfig, OpenAI, OctoAI, Mixedbread, VoyageAI, VertexAI, Bedrock, or HuggingFace embedding guidance after partitioning or chunking.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- Apache 2.0
Embeddings
Use this sub-skill after documents have already been partitioned or chunked into Unstructured Element objects and the task is to attach vector embeddings to those elements or embed a search query with the same provider.
Start Here
- Route upstream work first:
- Use
partitioningto create elements from files, URLs, HTML, text, or streams. - Use
chunkingbefore embedding when the vector store should index RAG-sized chunks rather than raw document elements. - Use
elements-and-metadatawhen inspecting serialized element JSON or preserving coordinate/table/source metadata.
- Use
- Select the provider module from
references/provider-reference.mdand install only the provider SDKs needed for that route. - Read credentials from environment variables or a secret manager at runtime; never hard-code, log, serialize, or commit API keys.
- Instantiate the provider-specific
EmbeddingConfigandEmbeddingEncoder, then call:embed_documents(elements)to mutate and return the same element objects withelement.embeddingspopulated.embed_query(query)to produce a single query vector for retrieval.
- Validate vector count and dimensions before persistence, especially when mixing providers or overriding model dimensions.
Core Model
unstructured.embed.interfaces.EmbeddingConfigis a Pydantic base class; concrete providers add credential, model, region, batching, or client options.unstructured.embed.interfaces.BaseEmbeddingEncoderdefinesembed_documents(elements),embed_query(query),num_of_dimensions,is_unit_vector, andinitialize().- Provider implementations convert each element to text with
str(element)before embedding, so empty text-like elements can create low-value vectors or provider errors. embed_documents()writes vectors toelement.embeddings; it is not a separate enrichment record and generally mutates the input elements in place.- Serialized text elements may include an
embeddingsfield, but ordinary metadata fields should remain intact if the element objects are preserved.
Safe Pattern
import os
from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder
config = OpenAIEmbeddingConfig(
api_key=os.environ["OPENAI_API_KEY"],
model_name="text-embedding-3-small",
)
encoder = OpenAIEmbeddingEncoder(config=config)
embedded_elements = encoder.embed_documents(chunks)
query_vector = encoder.embed_query("invoice due date")For provider-specific names, credentials, dependency extras, batching behavior, and model caveats, use references/provider-reference.md.
Metadata and Provenance
- Preserve source metadata by embedding existing
Elementobjects rather than converting them to plain strings and rebuilding them. - If downstream systems require enrichment provenance, add non-secret metadata outside the embedding vector itself, for example provider name, model name, and embedding timestamp managed by your application.
- Keep credentials and raw provider responses out of
ElementMetadata, logs, vector-store payloads, and serialized JSON fixtures. - If embedding chunks, preserve
metadata.orig_elementsonly when retrieval or citation workflows need source traceability; otherwise omit it upstream with thechunkingsub-skill to keep payloads smaller.
Show full SKILL.md (184 more words)Show less
Bundled Helpers
Use the bundled checker to verify importability and environment-variable presence without contacting providers or printing secret values:
python sub-skills/embeddings/scripts/embedding_config_check.py --provider openai
python sub-skills/embeddings/scripts/embedding_config_check.py --all --jsonThe checker intentionally does not call get_client(), embed_query(), or embed_documents(), because those may create SDK clients, read credential material, write provider-specific credential files, or make network calls.
Routing Boundaries
- Raw document partitioning, OCR, table extraction, and
partition()kwargs belong topartitioning. - Chunk sizing, overlap, table chunking, and
orig_elementsdecisions belong tochunking. - Element JSON conversion, schema inspection, coordinates, and staging conversions belong to
elements-and-metadata. - Broad ingest connectors and destination vector-store writes are excluded; the in-repo embed package README notes this area moved toward Unstructured Ingest.
Review Checklist
- Confirm the provider SDK and optional dependencies are installed before suggesting runtime embedding.
- Confirm credentials are sourced securely and never shown in code examples, logs, or serialized elements.
- Confirm
len(elements)equals the number of returned vectors; providers use assertions for this in several implementations. - Confirm element text is non-empty and appropriate for the provider token/model limits.
- Confirm metadata,
element_id, table metadata, and source provenance survive after embedding. - Confirm query vectors use the same provider/model/dimension as indexed document vectors.
© VectorSpaceLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts, references) in skills/repositories/repo-skills/unstructured/sub-skills/embeddings of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/provider-reference.md
- references/troubleshooting.md
- scripts/embedding_config_check.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Embeddings next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Embeddings this skillVectorSpaceLab/AREX-Skill | 330 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Neo4j Genai Plugin Skillneo4j-contrib/neo4j-skills | 114 | — | ~3k | Automated safety check: Notes | MIT | |
| AI SDKvercel-labs/ai-facts | 168 | 20 repos | ~1.2k | Automated safety check: Pass | None | |
| SageMaker Serving Image Selectionhuggingface/skills | 11k | 1 repos | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Codebase Managementgiancarloerra/SocratiCode | 3.3k | 1 repos | ~1.8k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Neo4j Genai Plugin Skill
neo4j-contrib/neo4j-skills
Use Neo4j GenAI Plugin ai.text. An agent skill from neo4j-contrib/neo4j-skills.
- Official
AI SDK
vercel-labs/ai-facts
Answer questions about the AI SDK and help build AI-powered features.
- Official
SageMaker Serving Image Selection
huggingface/skills
Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.
Codebase Management
giancarloerra/SocratiCode
Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.
Embeddings via 9Router
decolua/9router
Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Works with
Categories
Questions about Embeddings
What does Embeddings do?
Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks. Embeddings is an agent skill from VectorSpaceLab/AREX-Skill. Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks.
When should I use Embeddings?
Embeddings fits situations like: an agent needs BaseEmbeddingEncoder; embeddingConfig; huggingFace embedding guidance after partitioning.
How do I install Embeddings in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/unstructured/sub-skills/embeddings in VectorSpaceLab/AREX-Skill) into .claude/skills/embeddings in your project. Claude Code loads it when a task matches its description.
How do I install Embeddings in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a codex`. Or copy the skill folder (skills/repositories/repo-skills/unstructured/sub-skills/embeddings in VectorSpaceLab/AREX-Skill) into .agents/skills/embeddings in your project. Codex loads it when a task matches its description.
Can I use Embeddings in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill embeddings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/embeddings, .gemini/skills/embeddings, .github/skills/embeddings and .opencode/skills/embeddings in your project.
What does Embeddings need to run?
Going by SKILL.md and its folder, Embeddings needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY.
Does Embeddings access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Embeddings safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Embeddings use?
Embeddings is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Embeddings use?
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.6k tokens, read only when the agent opens those files.
What are the alternatives to Embeddings?
Skills that share tags, products or a category with Embeddings: Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars), Neo4j Genai Plugin Skill (neo4j-contrib/neo4j-skills, 114 stars), AI SDK (vercel-labs/ai-facts, 168 stars) and SageMaker Serving Image Selection (huggingface/skills, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Embeddings?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.