DeepEval
Listed inDeepEvalEvaluationon
Evaluations in pytest. Almost every built-in metric calls a judge model, which decides what belongs in a blocking gate and what does not.
Intermediate3 min
#evaluation
#ci
Page 4 of 11
Listed inDeepEvalEvaluationon
Evaluations in pytest. Almost every built-in metric calls a judge model, which decides what belongs in a blocking gate and what does not.
Listed inTokensHow LLMs Workon
The unit models actually read and bill for, and why character counts mislead you.
Listed inModels on Hugging FaceModels & Providerson
A model card is a data structure. Read the license first, then what it was derived from, then whether that benchmark number has a source.
Listed inLong Context ProcessingContext Engineeringon
The curve is U-shaped and the middle is the weak spot, even for models trained for long context. Where to put what matters.
Listed inArize AIObservabilityon
Tracing and evaluation in one OpenTelemetry-native tool that can run locally. The drift and embedding analysis often attributed to it does not appear in the documentation.
Listed inFine-tuningHow LLMs Workon
The documented benefits are about behavior and format rather than knowledge. Fine-tuning shapes how a model responds; retrieval is what gives it facts it did not train on.
Listed inGoogle Gemini APIAPIs & SDKson
Four safety categories, five thresholds, and a default of OFF. Blocking arrives in a field rather than an exception.
Listed inLlamaIndexRAGon
Documents and Nodes, and a query stage that separates retrieval, postprocessing and response synthesis. Postprocessing is the step hand-written pipelines usually skip, and it is where reranking and filtering belong.
Listed inAtlanContext Engineeringon
The context an assistant needs for warehouse data is metadata, not rows. Certification is what makes it trustworthy enough to act on.
Listed inContent Moderation APIsSafety & Ethicson
Scores are signals for your policy, not a blocking decision. Block on flagged alone and you suppress your own model declining to help.
Listed inProviding ContextPrompt Engineeringon
Long documents go above the question, not below it, and the boundary between your instruction and their text is a security control.
Listed inAnomaly DetectionEmbeddingson
An anomaly score is a distance read backwards. Plus the unnormalized-vector bug that makes a detector flag your longest documents.
Listed inManual ImplementationAI Agentson
The agent loop in forty lines, why a failing tool returns its error as a result, and what a framework is doing on top.
Listed inAudio ProcessingMultimodal AIon
Transcribing first meters you by file size and sending the audio meters you by tokens. An hour of audio is about 115,000 of them.
Listed inWindsurfDevelopment Toolson
Windsurf became Devin Desktop in June 2026 and Cascade was replaced. What the editor is now, and how it retrieves code from your repository.
Listed inChoosing the Right ModelModels & Providerson
Compare models on capability, latency, cost per request, context window, maximum output, and where they can run. Price per million tokens is not cost per request, and twenty saved examples from your own application settle the choice faster than a leaderboard.
Listed inEmbedding Models on Hugging FaceEmbeddingson
Changing embedding models means re-embedding the whole corpus, so the choice is harder to reverse than a generation model. What to check on a model card: vector dimensions, maximum sequence length, licensing, and whether the model expects a prompt prefix that fails silently when omitted.
Listed inMCP HostModel Context Protocolon
The six responsibilities the specification gives the host, why one client per server is the isolation boundary, and what happens when a server asks you for a completion.
Listed inLangChain for Multimodal AppsMultimodal AIon
Message content becomes a list of typed blocks. The shapes for images, audio and files, and when the abstraction is worth its dependency.