Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Language & NLP / txtai
⬡PipelineLanguage & NLPFree

txtai

All-in-one semantic search, RAG, and LLM workflow engine — embeddings, vector DB, and pipelines in one library.

@ai-supply
Installs53k
⟳ upstream v9.11.0 · updated 26d ago
↗ Source repository
← More Language & NLPLanguage & NLP leaderboard →How we grade security →Source ↗
✓ Grade A · 100/100 · SafeSecurity assessment
✓No compromise signals37capabilities surfaced9of 20 OWASP controls clear
Suspicious code patternsExternal endpoints declaredExternal endpoints declaredExternal endpoints declared
scanned 17d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

txtai

txtai is an all-in-one open-source embedding database that powers semantic search, LLM orchestration, and language model workflows. It combines a vector store, sparse retrieval, RAG pipelines, and workflow automation into a single lightweight library with minimal dependencies.

Key Features

  • Embeddings database: vector + keyword hybrid search in a single index
  • RAG pipelines: retrieval-augmented generation with any LLM (OpenAI, Hugging Face, Ollama)
  • LLM workflows: chain extractors, summaries, translations, classifiers, and custom steps
  • Graph networks: build knowledge graphs from document collections
  • Multimodal: text, image, audio, video embeddings
  • API server: YAML-config-driven REST API, no code needed

Quick Start

from txtai import Embeddings

embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2")
embeddings.index(["US tops all nations in gold medals",
                   "Weightlifting athlete sets new record"])

result = embeddings.search("athletic performance")
print(result)  # [(0, 0.75), (1, 0.63)]

Install via ai-supply

npx ai-supply add txtai-semantic-search-pipeline

Curated mirror of the open-source txtai (Apache-2.0). Get it from the source.

Rating rank
#1
of 30 in Language & NLP
Install rank
#15
of 30 in Language & NLP
Security score
100/100 · A
safe
Security rank
#1
of 30 in Language & NLP
Installs
53k
cat avg 145k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Language & NLP leaderboard →
✓ Security: Safe · 100100/100 · grade Ascanned 17d ago
✓ no compromise signals37 risk-surface · 6/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → img.shields.io, join.slack.com, coveralls.io, neuml.com, cal.com, txtai.cloud, neuml.github.io, www.youtube.com +32
18 steps⚑ uses secretsactions/checkout@v6actions/setup-python@v6actions/setup-java@v5pre-commit/action@v3.0.1github.com

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: Slack token · neuml-txtai-aa0a8cf/examples/28_Push_notifications_with_workflows.ipynb (CWE-798)expected
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — destructive rm -rf / · neuml-txtai-aa0a8cf/.github/workflows/build.yml (CWE-78)risk surface
•Suspicious code patterns — pickle deserialization · neuml-txtai-aa0a8cf/examples/29_Anatomy_of_a_txtai_index.ipynb (CWE-502)risk surface
•Suspicious code patterns — OS command execution · neuml-txtai-aa0a8cf/examples/47_Building_an_efficient_sparse_keyword_index_in_Python.ipynb (CWE-78)risk surface
•Suspicious code patterns — pipe-to-shell install · neuml-txtai-aa0a8cf/examples/81_OpenCode_as_a_txtai_LLM.ipynb (CWE-494)risk surface
•Suspicious code patterns — dynamic code execution · neuml-txtai-aa0a8cf/src/python/txtai/pipeline/train/hfonnx.py (CWE-95)risk surface
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · neuml-txtai-aa0a8cf/.pre-commit-config.yamlrisk surface
•External endpoints declared — 19 distinct host(s) · neuml-txtai-aa0a8cf/README.mdrisk surface
•External endpoints declared — 4 distinct host(s) · neuml-txtai-aa0a8cf/docs/agent/configuration.mdrisk surface
•Egress to a private/loopback host — 127.0.0.1 · neuml-txtai-aa0a8cf/docs/api/cluster.md (CWE-918)risk surface
•External endpoints declared — 3 distinct host(s) · neuml-txtai-aa0a8cf/docs/api/cluster.mdrisk surface
•External endpoints declared — 2 distinct host(s) · neuml-txtai-aa0a8cf/docs/api/customization.mdrisk surface
•External endpoints declared — 5 distinct host(s) · neuml-txtai-aa0a8cf/docs/api/mcp.mdrisk surface
•External endpoints declared — 13 distinct host(s) · neuml-txtai-aa0a8cf/docs/cloud.mdrisk surface
•External endpoints declared — 8 distinct host(s) · neuml-txtai-aa0a8cf/docs/index.mdrisk surface
•External endpoints declared — 7 distinct host(s) · neuml-txtai-aa0a8cf/docs/install.mdrisk surface
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · neuml-txtai-aa0a8cf/examples/04_Add_semantic_search_to_Elasticsearch.ipynb (CWE-272)risk surface
•External endpoints declared — 18 distinct host(s) · neuml-txtai-aa0a8cf/examples/22_Transform_tabular_data_with_composable_workflows.ipynbrisk surface
•External endpoints declared — 6 distinct host(s) · neuml-txtai-aa0a8cf/examples/24_Whats_new_in_txtai_4_0.ipynbrisk surface
•External endpoints declared — 11 distinct host(s) · neuml-txtai-aa0a8cf/examples/28_Push_notifications_with_workflows.ipynbrisk surface
•External endpoints declared — 10 distinct host(s) · neuml-txtai-aa0a8cf/examples/47_Building_an_efficient_sparse_keyword_index_in_Python.ipynbrisk surface
•External endpoints declared — 14 distinct host(s) · neuml-txtai-aa0a8cf/examples/69_Granting_autonomy_to_agents.ipynbrisk surface
•External endpoints declared — 15 distinct host(s) · neuml-txtai-aa0a8cf/examples/73_Chunking_your_data_for_RAG.ipynbrisk surface
•External endpoints declared — 25 distinct host(s) · neuml-txtai-aa0a8cf/examples/84_Agent_Tools.ipynbrisk surface
•Egress to a private/loopback host — 192.168.1.1, 127.0.0.1 · neuml-txtai-aa0a8cf/test/python/testapi/testapipipeline.py (CWE-918)risk surface
•Egress to a private/loopback host — 127.0.0.1, [::1] · neuml-txtai-aa0a8cf/test/python/testpipeline/testdata/testurlretrieve.py (CWE-918)risk surface
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: Slack token · neuml-txtai-aa0a8cf/examples/28_Push_notifications_with_workflows.ipynb (CWE-798)expected
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · neuml-txtai-aa0a8cf/test/python/testapi/testapipipeline.py (CWE-200)risk surface
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · neuml-txtai-aa0a8cf/examples/65_Speech_to_Speech_RAG.ipynb (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓LLM03Supply ChainPassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — destructive rm -rf / · neuml-txtai-aa0a8cf/.github/workflows/build.yml (CWE-78)risk surface
•Suspicious code patterns — pickle deserialization · neuml-txtai-aa0a8cf/examples/29_Anatomy_of_a_txtai_index.ipynb (CWE-502)risk surface
•Suspicious code patterns — OS command execution · neuml-txtai-aa0a8cf/examples/47_Building_an_efficient_sparse_keyword_index_in_Python.ipynb (CWE-78)risk surface
•Suspicious code patterns — pipe-to-shell install · neuml-txtai-aa0a8cf/examples/81_OpenCode_as_a_txtai_LLM.ipynb (CWE-494)risk surface
•Suspicious code patterns — dynamic code execution · neuml-txtai-aa0a8cf/src/python/txtai/pipeline/train/hfonnx.py (CWE-95)risk surface
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML06AI Supply ChainPassed
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (15) · hygiene / uncategorized
•Unrecognized file type — '.coveragerc' is not on the allowlist · neuml-txtai-aa0a8cf/.coveragercrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · neuml-txtai-aa0a8cf/.gitignorerisk surface
•Unrecognized file type — '.pylintrc' is not on the allowlist · neuml-txtai-aa0a8cf/.pylintrcrisk surface
•Unrecognized file type — '.cff' is not on the allowlist · neuml-txtai-aa0a8cf/CITATION.cffrisk surface
•Unrecognized file type — '.?' is not on the allowlist · neuml-txtai-aa0a8cf/LICENSErisk surface
•Suspicious network references — raw IP URL (5 URLs) · neuml-txtai-aa0a8cf/docs/api/cluster.mdrisk surface
•Suspicious network references — suspicious TLD (17 URLs) · neuml-txtai-aa0a8cf/docs/embeddings/configuration/ann.mdrisk surface
•Suspicious network references — suspicious TLD (5 URLs) · neuml-txtai-aa0a8cf/docs/faq.mdrisk surface
•Unrecognized file type — '.excalidraw' is not on the allowlist · neuml-txtai-aa0a8cf/docs/images/agent.excalidrawrisk surface
•Suspicious network references — raw IP URL (22 URLs) · neuml-txtai-aa0a8cf/examples/15_Distributed_embeddings_cluster.ipynbrisk surface
•Suspicious network references — raw IP URL (112 URLs) · neuml-txtai-aa0a8cf/examples/22_Transform_tabular_data_with_composable_workflows.ipynbrisk surface
•Suspicious network references — raw IP URL (3 URLs) · neuml-txtai-aa0a8cf/test/python/testapi/testapipipeline.pyrisk surface
•Suspicious network references — raw IP URL (2 URLs) · neuml-txtai-aa0a8cf/test/python/testapi/testcluster.pyrisk surface
•Suspicious network references — raw IP URL (8 URLs) · neuml-txtai-aa0a8cf/test/python/testpipeline/testdata/testurlretrieve.pyrisk surface
•Suspicious network references — raw IP URL (1 URLs) · neuml-txtai-aa0a8cf/test/python/testpipeline/testllm/testlitellm.pyrisk surface
✔ verified source · pinned neuml-txtai-aa0a8cf
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/txtai-semantic-search-pipeline/check). Click a policy:

Consume txtai programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/txtai-semantic-search-pipeline

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/txtai-semantic-search-pipeline/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add txtai-semantic-search-pipeline

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/txtai-semantic-search-pipeline/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "txtai-semantic-search-pipeline" })
OpenAPI spec →
vlatest
✓ Security: Safe · 1001mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy