SDK and framework migrations
The named version jumps that break a build — openai-python v0 to v1, LangChain to LCEL, LlamaIndex Settings, the Vercel AI SDK majors.
A model API is a wire format and it changes slowly. The libraries wrapped around it are software, and they change at the speed of software. Almost nothing in this cluster is about a model behaving differently; it is about a client library that renamed a class, split itself into four packages, or replaced a constructor with a factory function, and about the specific hour you spend afterwards reading tracebacks that point at your own code.
These pages take one named jump each and walk the call sites. They quote the error the upgraded library actually raises, because that string is usually the only evidence you have, and they are explicit about the part of a migration nobody writes down: what has no equivalent on the other side, and what you do instead. Where a page names a version, treat the version as part of the claim — run the command that prints what you have installed before trusting a mapping table, including this one.
Migrating openai-python From v0 to v1
The call-site rewrite from module-level openai.ChatCompletion.create to an instantiated client, including the response-access and exception changes the automated tool leaves behind.
11 min read
Fixing "module 'openai' has no attribute 'ChatCompletion'"
Why the v1 SDK raises on the old module-level API, how to tell the shim's error apart from a real AttributeError, and the minimal diff for each call pattern.
9 min read
Migrating LangChain 0.0.x Imports to 0.1 and Later
How the flat langchain namespace split into langchain-core, partner packages and langchain-community, and which import each old path becomes.
10 min read
Migrating a LangChain Chain to LCEL
Rewriting an LLMChain as a pipe-composed runnable, including the return-type change and the old chain classes that have no direct equivalent.
11 min read
Migrating LlamaIndex ServiceContext to Settings
Rewriting a ServiceContext-based index build onto the global Settings object, and handling the per-instance configuration that a global cannot express.
10 min read
Migrating the Vercel AI SDK From v2 to v3
Replacing the v2 provider-stream-plus-StreamingTextResponse route handler with AI SDK Core's streamText, and what the provider abstraction does not carry across.
10 min read
Migrating the Vercel AI SDK From v3 to v4
The 3.4 to 4.0 removals and renames — provider facades, the AI-stream helpers, roundtrips, usage types — against a working v3 route handler.
11 min read
Fixing "streamText is not a function" After an AI SDK Upgrade
Why the import resolves but the export is missing, and the package.json and npm ls checks that tell a version problem from a wrong import path.
9 min read
Other topics
- LLM fundamentals & architecture
- Tokens, tokenization & context windows
- Prompt engineering
- Reasoning models & test-time compute
- Multimodal AI: vision, audio, video
- RAG & retrieval
- Embeddings & vector search
- AI agents & tool use
- Structured output & function calling
- Fine-tuning & post-training
- Local inference errors, string by string
- Running local models day to day
- Testing code that calls an LLM
- Snapshot and property testing for model output
- Regression suites for prompts
- Eval gates in CI
- Flaky tests against a model
- Determinism and the cost of testing
- Contract and streaming tests
- Testing tool calls and retrieval
- Inference, serving & latency
- Rolling out a prompt change
- Testing AI systems in practice
- Forecasting a time series
- Machine learning on tabular data
- Geospatial data and models
- Understanding audio that is not speech
- Understanding video
- Core computer vision tasks
- Machine learning on graphs
- Point clouds and 3D
- Evaluation, benchmarks & LLM-as-judge
- Sensor and IoT data
- Logs and event streams
- Models over biological sequences
- Machine learning on molecules
- Embedding and searching code
- Extracting invoices and purchase orders
- Receipts, statements and tax forms
- Insurance policies and contracts
- Deeds, court filings and patents
- Extracting from medical records
- Observability & LLMOps
- CVs, certificates and identity documents
- Shipping, customs and technical documents
- Meetings, email, chat and filled-in forms
- Building an extraction pipeline
- Business, property and inspection documents
- Contract clauses and insurance claims
- Regulated and compliance documents
- Consumer, travel and closing documents
- Mapping one chat API onto another
- Hallucination & failure modes
- Re-embedding and model deprecation
- Cutting over between providers
- Parity gaps, shims and legacy endpoints
- Moving between model versions
- Migrating vector stores and caches
- Mapping capabilities and parameters
- Migrating pipelines and agents
- Contracts, runbooks and rollback
- Auditing a codebase before a cutover
- Compliance and fine-tune migration
- LLM cost engineering
- Routing, cost tracking and multi-tenancy
- What a migration does to your prompts
- AI security & prompt injection
- Privacy, compliance & data residency
- AI governance, policy & society
- Building reliable AI applications
- AI hardware, GPUs & compute
- Open-weight models & local inference
- AI for developers & coding agents
- AI in industry: vertical playbooks
- AGI, superintelligence, alignment & the long future
- Machine learning foundations
- NLP fundamentals & classical tasks
- Data engineering for AI
- Synthetic data & dataset curation
- AI product design & UX
- Search, ranking & recommendation
- Enterprise adoption & change management
- AI careers, skills & teams
- Reading AI research
- AI in science & discovery
- Robotics & embodied AI
- AI economics, markets & business models
- AI myths, hype & media literacy
- Context engineering
- Shipping AI features: patterns & anti-patterns
- Build it: end-to-end AI tutorials
- Python for AI: hands-on recipes
- TypeScript, React and the web
- Frameworks and SDKs
- Errors and troubleshooting
- AI facts, numbers and statistics
- The history of AI
- The maths behind AI
- Architectures beyond the transformer
- Reinforcement learning
- Diffusion and generative media
- Speech, audio and voice engineering
- Benchmarks, one at a time
- AI search visibility
- Infrastructure and operations
- Databases and storage for AI
- Knowledge graphs and structured knowledge
- Classical ML in production
- Regulation, jurisdiction by jurisdiction
- Prompt recipes and pattern library
- AI for people who do not write code
- Writing, media and creative work
- Edge and on-device AI
- Interpretability and model internals
- Field notes
- OpenAI model behaviour
- Claude model behaviour
- Gemini model behaviour
- Llama model behaviour
- Mistral model behaviour
- Qwen model behaviour
- DeepSeek model behaviour
- Cohere model behaviour
- Grok model behaviour
- Small model behaviour
- Hybrid model architectures
- Token cost by language and script
- Transliteration, romanization and script handling
- Locale-correct output
- Multilingual generation quality
- Multilingual pipelines
- The EU AI Act, article by article
- AI under the GDPR and EU data law
- US AI regulation, state and sector
- International AI governance and standards
- AI litigation and enforcement
- Running AI workloads on AWS
- Running AI workloads on Google Cloud
- Running AI workloads on Azure
- AI at the edge: Workers, Vercel and Netlify
- Serving models on Kubernetes
- Operating AI infrastructure
- Quantization formats and what they cost
- llama.cpp, flag by flag
- Ollama and the desktop local-model runtimes
- Local models on Apple Silicon
- Hardware for local inference
- Running speech and embedding models locally
- Model files, adapters and conversion
- VRAM arithmetic for local models