Listed together in guide “Local and private document Q&A”
Open-source vector database for semantic search, retrieval-augmented generation, and hybrid search.
Open (open weights/source) BSD-3-Clause
Use cases
- Retrieval-augmented generation pipelines for LLM apps
- Semantic search over documents and product catalogs
- Recommendation and similarity-matching systems
Pricing: Weaviate is free to self-host (BSD-3-Clause); Weaviate Cloud is a paid managed service priced by usage and tier.
Pricing ↗ · Sources
This record was last reviewed on 2026-09-10.
Listed together in guide “Local and private document Q&A”
Open-source platform for building LLM applications with visual agent workflows, RAG pipelines, and model management.
Open (open weights/source) Dify Open Source License (modified Apache-2.0)
Use cases
- Building internal AI assistants over company knowledge
- Prototyping and shipping agentic workflows without heavy coding
- Standardizing LLM app development across a team
Pricing: Self-hosting Dify is free under its open-source license; Dify Cloud offers a free sandbox and paid plans, with enterprise licensing for advanced needs.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-10-10.
Listed together in guide “Local and private document Q&A”
Open-source framework for building LLM applications and agents, with LangSmith and LangGraph for observability and orchestration.
Open (open weights/source) MIT
Use cases
- Building RAG pipelines and chatbots
- Orchestrating multi-step agents
- Debugging and evaluating LLM applications
Pricing: The framework is free and open source; LangSmith offers a free tier plus paid plans for teams.
Pricing ↗ · Sources
This record was last reviewed on 2026-09-10.
Listed together in guide “Local and private document Q&A”
Open-source data framework for connecting LLMs to private data, powering retrieval-augmented generation and document agents.
Open (open weights/source) MIT
Use cases
- Building RAG over enterprise documents
- Question answering on PDFs and knowledge bases
- Document-processing agents
Pricing: The framework is free and open source; LlamaCloud and LlamaParse are usage-priced hosted services.
Pricing ↗ · Sources
This record was last reviewed on 2026-09-10.
Related: shares the task Running models yourself
Managed AWS service for building applications with foundation models from multiple providers via one API.
Paid
Use cases
- Enterprise apps that need a choice of models under one API
- RAG systems grounded in private company data
- Regulated workloads requiring AWS data controls
Pricing: Pricing is usage-based per input/output token, with on-demand and provisioned-throughput options.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-10-09.
Related: shares the task Running models yourself
Platform for deploying and serving machine-learning models as scalable APIs.
Paid
Use cases
- Serving custom and open models in production
- Low-latency inference APIs
- Scaling ML services reliably
Pricing: Dedicated GPU compute is billed per minute with no charge for idle time, model APIs are billed per million tokens, and new accounts come with credits.
Documentation ↗ · Sources
This record was last reviewed on 2026-10-09.
Related: shares the task Running models yourself
AI compute company whose inference cloud serves open language models on wafer-scale hardware.
Freemium
Use cases
- Latency-sensitive applications needing fast tokens
- Serving open models at high speed
- Large-model training on specialized hardware
Pricing: Inference is usage-priced per token and starts with a free trial; training systems and on-premises deployments are sold separately.
Sources
This record was last reviewed on 2026-10-09.
Related: shares the task Running models yourself
Generative media inference platform for running diffusion and other models with a fast API.
Paid
Use cases
- Adding image and video generation to apps
- Serving open diffusion models at scale
- Prototyping generative media pipelines
Pricing: Pricing is usage-based per inference or compute second; new developers receive free credits.
Documentation ↗ · Sources
This record was last reviewed on 2026-10-09.