About
What is skald?
Skald is an open-source platform designed to provide a production-ready Retrieval-Augmented Generation (RAG) system for your infrastructure. It offers a plug-and-play API that allows for quick deployment and extensive configuration of your RAG engine. Skald handles the entire ingestion process, including document parsing, chunking, summarization, tagging, embedding generation, and vector storage. For retrieval, it manages query rewriting, vector search, LLM chat, chat history, and source references. While it comes with solid defaults suitable for most use cases, users can fine-tune various aspects such as vector search parameters, reranking, models, and chunking strategies. Skald also includes built-in evaluation tools to assess the performance of custom RAG engines and supports powerful filtering for improved response accuracy and speed.
Best used for
Ideal for developers and startup founders who need to implement advanced RAG capabilities, customize their AI search, and evaluate system performance. Especially valuable for those requiring a fully-featured, open-source solution that can be self-hosted or deployed with a free cloud tier.
Common actions
workflowsautomated workflowopen-sourcelow-code/no-codegithub copilotdeepfake"AI Agents"face swappingcollaboration
Capabilities
Key features
- Production-ready RAG
- Configurable RAG engine
- Document parsing and chunking
- Embedding generation
- Vector storage
- Query rewriting
- LLM chat
Target Audience
developerstartup founderdata scientistproduct manager
Integrations
Not yet documentedPricing & Plans
Open Source · Freemium · Enterprise
FAQs
What is the difference between Skald's open-source and Enterprise Edition?
The open-source version of Skald is fully-featured and can run without third-party dependencies. The Enterprise Edition (EE) is primarily designed for on-premise deployments and has a separate license. For 100% FOSS code, the skald-foss repository is available, which is what powers their Cloud offering.
Can Skald be deployed without third-party services like OpenAI?
Yes, Skald can be deployed without any third-party dependencies, including OpenAI. This advanced usage requires hosting your own LLM inference server and using a local embeddings service, which is provided in the local docker compose profile.
What kind of configuration options does Skald offer for RAG engines?
Skald allows extensive configuration of its RAG engine. Users can tune vector search parameters, reranking strategies, models, and chunking methods. It also supports powerful filtering to refine the accessible knowledge for each query, ensuring precise and relevant responses.
Shypd.aiThe largest open index of AI tools
