Function Calling
Listed inFunction CallingAPIs & SDKson
The model returns a request your code chooses to run. Arguments are model-generated, and providers document the model inventing ones nobody supplied.
Intermediate4 min
#api
#security
Page 3 of 11
Listed inFunction CallingAPIs & SDKson
The model returns a request your code chooses to run. Arguments are model-generated, and providers document the model inventing ones nobody supplied.
Listed inGoogle ADKAI Agentson
Google's ADK: agent definitions, tools, sessions, and the built-in evaluation harness.
Listed inLLM EvaluationsEvaluationon
The open-source eval framework and registry — a good template for structuring your own graded test set.
Listed inMultimodal AIMultimodal AIon
Images are billed as input tokens and share the context budget. Plus the provider’s own list of what vision reads badly.
Listed inTokensHow LLMs Workon
The BPE paper — why tokenizers merge frequent byte pairs, and why your rare identifiers cost so much.
Listed inConducting Adversarial TestingSafety & Ethicson
Derive your attack surface from the OWASP taxonomy rather than a jailbreak list, then fix findings in the layer that can enforce them.
Listed inStructured OutputPrompt Engineeringon
Asking for JSON in the prompt, JSON mode, and schema-constrained output give different guarantees. JSON mode promises syntactically valid JSON and not conformance to your schema, which is the gap most applications trip on.
Listed inOpenAI Embeddings APIEmbeddingson
Shortening a vector is supported and cheap, and slicing it yourself without normalizing degrades search with nothing failing.
Listed inClaude Agent SDKAI Agentson
Writing the agent loop is straightforward; the harness supplies what surrounds it. Context management, sessions, permissions, and the file and shell tools an agent needs are what adopting the SDK gives you.
Listed inText to SpeechMultimodal AIon
Uncompressed formats start playing sooner, streams fail after playback begins, and disclosing that the voice is synthetic is a policy requirement.
Listed inCodexDevelopment Toolson
The name meant a completion model once and a coding agent now. Sandboxing and approvals are the operating decision, not the surface you run it on.
Listed inOpenAI GPT & o-seriesModels & Providerson
Reasoning tokens are billed as output, invisible in the API, and share your context window. That explains both the bill and the truncation.
Listed inPurpose and FunctionalityVector Databaseson
A B-tree cannot find nearest neighbors, exact search stops scaling, and approximate search trades a guarantee for speed. Sometimes you need none of it.
Listed inMCP ServerModel Context Protocolon
Tools are model-controlled, resources are application-controlled. That column decides which primitive a capability belongs to.
Listed inLLM EvaluationsEvaluationon
Stop asserting one output and start measuring across many. Three layers, and the cheap one people skip on the way to a judge model.
Listed inCommon TerminologyIntroductionon
The working vocabulary in one place, ordered so each term builds on the last, plus four confusions that cause real mistakes.
Listed inQwenModels & Providerson
Apache 2.0, over 100 languages, dense and mixture-of-experts across a wide size range. Why tokenizer coverage shows up in your bill.
Listed inLanceDBVector Databaseson
An embedded retrieval library rather than a server, with multimodal assets beside the vectors. Plus what the project does not actually claim.
Listed inContext EngineeringContext Engineeringon
Five things make up the payload, and each is a decision with its own failure. Tool definitions are billed on every call whether used or not.