[{"data":1,"prerenderedAt":515},["ShallowReactive",2],{"blog-tag-en-evaluation":3},[4,86,197,269,341,411,464],{"slug":5,"published":6,"minutes":7,"category":8,"tags":9,"tagPages":15,"keywords":17,"about":30,"sources":39,"cover":76,"og":77,"expertise":78,"locales":79,"lang":80,"title":83,"description":84,"coverAlt":85},"synthetic-test-data-rag-evals","2026-10-17",10,"rag",[10,11,12,13,14],"RAG","Evaluation","Synthetic data","Retrieval","Testing",[8,16],"evaluation",[18,19,20,21,22,23,24,25,26,27,28,29],"synthetic test data RAG","RAG evaluation dataset","question generation from chunks","hard negatives retrieval evaluation","answerability filter","RAG test set generation","synthetic QA pairs","RAG eval data contamination","multilingual RAG evaluation German Hungarian","retrieval metrics recall ndcg","LLM judge human spot check","unanswerable questions RAG",[31,34,36],{"name":32,"url":33},"Retrieval-augmented generation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval_augmented_generation",{"name":12,"url":35},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSynthetic_data",{"name":37,"url":38},"Information retrieval","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FInformation_retrieval",[40,43,46,49,52,55,58,61,64,67,70,73],{"title":41,"url":42},"Red Hat Developers: Synthetic data for RAG evaluation (Feb 23, 2026)","https:\u002F\u002Fdevelopers.redhat.com\u002Farticles\u002F2026\u002F02\u002F23\u002Fsynthetic-data-rag-evaluation-why-your-rag-system-needs-better-testing",{"title":44,"url":45},"Ragas docs: Testset Generation for RAG","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fgetstarted\u002Frag_testset_generation\u002F",{"title":47,"url":48},"Ragas docs: Testset generation concepts (query types, scenarios)","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Ftest_data_generation\u002Frag\u002F",{"title":50,"url":51},"NVIDIA Technical Blog: Evaluating and Enhancing RAG Pipeline Performance Using Synthetic Data","https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fevaluating-and-enhancing-rag-pipeline-performance-using-synthetic-data\u002F",{"title":53,"url":54},"DeepEval docs: Datasets and the Synthesizer","https:\u002F\u002Fdeepeval.com\u002Fdocs\u002Fevaluation-datasets",{"title":56,"url":57},"Rajpurkar, Jia, Liang: Know What You Don't Know: Unanswerable Questions for SQuAD (ACL 2018)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.03822",{"title":59,"url":60},"Rahmani et al.: Towards Understanding Bias in Synthetic Data for Evaluation (CIKM 2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.10301",{"title":62,"url":63},"Cheng et al.: A Survey on Data Contamination for Large Language Models","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14425",{"title":65,"url":66},"Xu et al.: Infini-gram mini: Exact n-gram Search at the Internet Scale (EMNLP 2025)","https:\u002F\u002Faclanthology.org\u002F2025.emnlp-main.1268\u002F",{"title":68,"url":69},"Panickssery, Bowman, Feng: LLM Evaluators Recognize and Favor Their Own Generations","https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.13076",{"title":71,"url":72},"Enevoldsen et al.: MMTEB, Massive Multilingual Text Embedding Benchmark (ICLR 2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.13595",{"title":74,"url":75},"Evidently AI: How to align an LLM judge with human labels (Nov 2025)","https:\u002F\u002Fwww.evidentlyai.com\u002Fblog\u002Fhow-to-align-llm-judge-with-human-labels","\u002Fimages\u002Fblog\u002Fsynthetic-test-data-rag-evals\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fsynthetic-test-data-rag-evals\u002Fog.jpg","ai-engineer",[80,81,82],"en","de","hu","Generating synthetic test data for RAG evaluations","Question generation from chunks, hard negatives, answerability labels, German and Hungarian coverage, contamination and human spot checks.","Synthetic test data for RAG evals: a robot runs a machine that turns a book into a stack of question cards.",{"slug":87,"published":88,"minutes":89,"category":90,"tags":91,"tagPages":96,"keywords":101,"about":109,"sources":121,"cover":191,"og":192,"expertise":78,"locales":193,"lang":80,"title":194,"description":195,"coverAlt":196},"opik","2026-10-05",7,"llmops",[92,93,11,94,95],"LLM observability","Tracing","OpenTelemetry","Self-hosting",[97,98,16,99,100],"llm-observability","tracing","opentelemetry","self-hosting",[87,102,103,104,105,106,107,108],"opik review","opik vs langfuse","opik pricing","self-hosted llm tracing","opik opentelemetry","llm as a judge metrics","opik guardrails",[110,113,115,118],{"name":111,"url":112},"Comet ML","https:\u002F\u002Fwww.comet.com",{"name":94,"url":114},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenTelemetry",{"name":116,"url":117},"Observability (software)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FObservability_(software)",{"name":119,"url":120},"Apache License","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_License",[122,125,128,131,134,137,140,143,146,149,152,155,158,161,164,167,170,173,176,179,182,185,188],{"title":123,"url":124},"Opik repository README on GitHub","https:\u002F\u002Fgithub.com\u002Fcomet-ml\u002Fopik",{"title":126,"url":127},"Opik LICENSE file: Apache License 2.0","https:\u002F\u002Fgithub.com\u002Fcomet-ml\u002Fopik\u002Fblob\u002Fmain\u002FLICENSE",{"title":129,"url":130},"Opik on PyPI: package metadata","https:\u002F\u002Fpypi.org\u002Fpypi\u002Fopik\u002Fjson",{"title":132,"url":133},"Opik product page","https:\u002F\u002Fwww.comet.com\u002Fsite\u002Fproducts\u002Fopik\u002F",{"title":135,"url":136},"Opik pricing","https:\u002F\u002Fwww.comet.com\u002Fsite\u002Fpricing\u002F",{"title":138,"url":139},"Opik docs: run locally with Docker Compose","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fself-host\u002Flocal_deployment",{"title":141,"url":142},"Opik docs: Kubernetes deployment with Helm","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fself-host\u002Fkubernetes",{"title":144,"url":145},"Opik docs: platform architecture","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fself-host\u002Farchitecture",{"title":147,"url":148},"Opik docs: tracing getting started","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Ftracing\u002Fgetting-started",{"title":150,"url":151},"Opik docs: OpenTelemetry integration","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fintegrations\u002Fopentelemetry",{"title":153,"url":154},"Opik docs: evaluation metrics overview","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fevaluation\u002Fmetrics\u002Foverview",{"title":156,"url":157},"Opik docs: online evaluation rules","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fproduction\u002Fonline-evaluation\u002Frules",{"title":159,"url":160},"Opik docs: Prompt Library overview","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fdevelopment\u002Fprompt-library\u002Foverview",{"title":162,"url":163},"Opik docs: optimisation algorithms","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fdevelopment\u002Foptimization-runs\u002Falgorithms\u002Foverview",{"title":165,"url":166},"Opik docs: guardrails overview","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fguardrails\u002Foverview",{"title":168,"url":169},"Opik docs: guardrails server","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fguardrails\u002Fserver",{"title":171,"url":172},"Opik docs: SDK anonymizers","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fproduction\u002Fgateway-guardrails\u002Fanonymizers",{"title":174,"url":175},"Opik docs: data anonymization","https:\u002F\u002Fwww.comet.com\u002Fdocs\u002Fopik\u002Fadministration\u002Fdata_anonymization",{"title":177,"url":178},"Comet ML privacy policy","https:\u002F\u002Fwww.comet.com\u002Fsite\u002Fprivacy-policy\u002F",{"title":180,"url":181},"Comet Trust Center","https:\u002F\u002Ftrust.comet.com\u002F",{"title":183,"url":184},"Langfuse repository README (licence)","https:\u002F\u002Fgithub.com\u002Flangfuse\u002Flangfuse",{"title":186,"url":187},"Arize Phoenix repository README (licence)","https:\u002F\u002Fgithub.com\u002FArize-ai\u002Fphoenix",{"title":189,"url":190},"LangChain pricing (LangSmith plans)","https:\u002F\u002Fwww.langchain.com\u002Fpricing","\u002Fimages\u002Fblog\u002Fopik\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fopik\u002Fog.jpg",[80,81,82],"Opik review: open-source tracing and evals, with a US-hosted cloud","Opik: traces, LLM-as-a-judge metrics, prompt versions and an optimiser on one Apache 2.0 platform. Free to self-host, Pro cloud $19\u002Fmonth, US-hosted.","Opik review: binoculars on a stack of notebooks, a cloud above a flag in the background.",{"slug":198,"published":199,"updated":200,"minutes":201,"category":8,"tags":202,"tagPages":206,"keywords":207,"about":218,"sources":226,"cover":263,"og":264,"expertise":78,"locales":265,"lang":80,"title":266,"description":267,"coverAlt":268},"reranking-models-compared","2026-09-30","2026-10-01",8,[203,10,204,205,11],"Reranking","Search","Cross-encoders",[8,16],[208,209,210,211,212,213,214,215,216,217],"cross-encoder reranker comparison","Cohere Rerank 4 pricing","bge-reranker-v2-m3","Voyage rerank-3","Jina reranker v3.5","ColBERT late interaction vs reranker","LLM as reranker","reciprocal rank fusion vs reranker","reranking top-k evaluation","self-hosted reranker ONNX CPU",[219,222,225],{"name":220,"url":221},"Learning to rank","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLearning_to_rank",{"name":223,"url":224},"BERT (language model)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBERT_%28language_model%29",{"name":37,"url":38},[227,230,233,236,239,242,245,248,251,254,257,260],{"title":228,"url":229},"Sentence-BERT (arXiv 1908.10084)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10084",{"title":231,"url":232},"Sentence Transformers: retrieve and re-rank","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Fapplications\u002Fretrieve_rerank\u002FREADME.html",{"title":234,"url":235},"BAAI\u002Fbge-reranker-v2-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-reranker-v2-m3",{"title":237,"url":238},"Cohere docs: reranking best practices","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Freranking-best-practices",{"title":240,"url":241},"Cohere pricing","https:\u002F\u002Fcohere.com\u002Fpricing",{"title":243,"url":244},"Voyage AI blog: rerank-3 (30 Sep 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F09\u002F30\u002Frerank-3\u002F",{"title":246,"url":247},"Voyage AI docs: pricing","https:\u002F\u002Fdocs.voyageai.com\u002Fdocs\u002Fpricing",{"title":249,"url":250},"Jina AI: Reranker v3.5 (3 Aug 2026)","https:\u002F\u002Fjina.ai\u002Fnews\u002Fjina-reranker-v3-5-faster-listwise-reranking-hybrid-attention-self-distillation\u002F",{"title":252,"url":253},"ColBERTv2 (arXiv 2112.01488)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.01488",{"title":255,"url":256},"Elasticsearch docs: reciprocal rank fusion","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Frest-apis\u002Freciprocal-rank-fusion",{"title":258,"url":259},"Azure AI Search: semantic ranking overview","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsemantic-search-overview",{"title":261,"url":262},"RankGPT (arXiv 2304.09542)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.09542","\u002Fimages\u002Fblog\u002Freranking-models-compared\u002Fcover.webp","\u002Fimages\u002Fblog\u002Freranking-models-compared\u002Fog.jpg",[80,81,82],"Cross-encoder rerankers compared: Cohere, bge, Voyage, Jina and late interaction (2026)","Rerankers in October 2026: pointwise, listwise and late interaction, Cohere, Voyage, bge, Qwen3, Jina and mxbai, prices, self-hosting and choosing k.","Cross-encoder rerankers compared: a funnel narrows many cards to five, and one card is lifted to the front.",{"slug":270,"published":271,"updated":272,"minutes":201,"category":8,"tags":273,"tagPages":277,"keywords":278,"about":289,"sources":298,"cover":335,"og":336,"expertise":78,"locales":337,"lang":80,"title":338,"description":339,"coverAlt":340},"table-extraction-rag","2026-09-29","2026-10-16",[10,274,275,11,276],"Tables","Document parsing","Text-to-SQL",[8,16],[279,280,281,282,283,284,285,286,287,288],"table extraction for RAG","tables in RAG pipelines","pdfplumber vs Camelot","Table Transformer PubTables-1M","Docling table mode TableFormer","Azure Document Intelligence tables","TEDS metric limitations","markdown vs HTML table for LLM","text-to-SQL for table questions","LlamaParse table extraction",[290,292,295],{"name":32,"url":291},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval-augmented_generation",{"name":293,"url":294},"Table (information)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTable_%28information%29",{"name":296,"url":297},"PDF","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPDF",[299,302,305,308,311,314,317,320,323,326,329,332],{"title":300,"url":301},"Factorial study of parsers, chunkers and retrievers (arXiv 2609.31660)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.31660",{"title":303,"url":304},"pdfplumber on GitHub","https:\u002F\u002Fgithub.com\u002Fjsvine\u002Fpdfplumber",{"title":306,"url":307},"Camelot documentation","https:\u002F\u002Fcamelot-py.readthedocs.io\u002Fen\u002Flatest\u002F",{"title":309,"url":310},"Microsoft Table Transformer (archived)","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftable-transformer",{"title":312,"url":313},"PubTabNet and TEDS (arXiv 1911.10683)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.10683",{"title":315,"url":316},"Semantic evaluation of table extraction (arXiv 2603.18652)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.18652",{"title":318,"url":319},"TableFormer (arXiv 2203.01017)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.01017",{"title":321,"url":322},"Docling docs: advanced options","https:\u002F\u002Fdocling-project.github.io\u002Fdocling\u002Fusage\u002Fadvanced_options\u002F",{"title":324,"url":325},"Azure Document Intelligence: layout model","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fai-services\u002Fdocument-intelligence\u002Fprebuilt\u002Flayout",{"title":327,"url":328},"Table Meets LLM (WSDM 2024)","https:\u002F\u002Fzmy.io\u002Ffiles\u002Fwsdm24-SUC.pdf",{"title":330,"url":331},"TableRAG (arXiv 2410.04739)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.04739",{"title":333,"url":334},"Chain-of-Table (arXiv 2401.04398)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.04398","\u002Fimages\u002Fblog\u002Ftable-extraction-rag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Ftable-extraction-rag\u002Fog.jpg",[80,81,82],"Table extraction for RAG: extraction layers, serialization and queries that hold","Tables in RAG: why chunking breaks them, pdfplumber, Camelot, Docling and cloud extractors, what TEDS misses, serialization, and routing questions to SQL.","Table extraction for RAG: a table on a page becomes separate row strips that each keep a header tab.",{"slug":342,"published":343,"updated":6,"minutes":201,"category":8,"tags":344,"tagPages":348,"keywords":350,"about":361,"sources":369,"cover":405,"og":406,"expertise":78,"locales":407,"lang":80,"title":408,"description":409,"coverAlt":410},"embedding-fine-tuning-domain","2026-09-28",[345,346,10,11,347],"Embeddings","Fine-tuning","Sentence Transformers",[349,8,16],"embeddings",[351,352,353,354,355,356,357,358,359,360],"fine-tuning embedding models","domain adaptation embeddings","hard negative mining retrieval","MultipleNegativesRankingLoss","GISTEmbed vs MNRL","Matryoshka embedding dimensions","Qwen3-Embedding fine-tune","BGE-M3 vs EmbeddingGemma","embedding evaluation recall@k","catastrophic forgetting dense retrieval",[362,365,368],{"name":363,"url":364},"Word embedding","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FWord_embedding",{"name":366,"url":367},"Fine-tuning (deep learning)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FFine-tuning_%28deep_learning%29",{"name":37,"url":38},[370,373,376,379,382,385,388,391,394,397,400,402],{"title":371,"url":372},"Sentence Transformers: training overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Ftraining_overview.html",{"title":374,"url":375},"Sentence Transformers: loss overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Floss_overview.html",{"title":377,"url":378},"Sentence Transformers: hard negative mining","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fpackage_reference\u002Futil\u002Fhard_negatives.html",{"title":380,"url":381},"RocketQA (arXiv 2010.08191)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08191",{"title":383,"url":384},"InPars (arXiv 2202.05144)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.05144",{"title":386,"url":387},"Promptagator (arXiv 2209.11755)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.11755",{"title":389,"url":390},"Qwen blog: Qwen3-Embedding (Jun 2025)","https:\u002F\u002Fqwenlm.github.io\u002Fblog\u002Fqwen3-embedding\u002F",{"title":392,"url":393},"BAAI\u002Fbge-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-m3",{"title":395,"url":396},"Google: EmbeddingGemma docs (Oct 2026)","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fembeddinggemma",{"title":398,"url":399},"Sentence Transformers: Matryoshka embeddings","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Ftraining\u002Fmatryoshka\u002FREADME.html",{"title":401,"url":72},"MMTEB (arXiv 2502.13595)",{"title":403,"url":404},"ANCE-Tele (arXiv 2210.17167)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.17167","\u002Fimages\u002Fblog\u002Fembedding-fine-tuning-domain\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fembedding-fine-tuning-domain\u002Fog.jpg",[80,81,82],"Fine-tuning embedding models for your domain: hard negatives, losses and evals","Fine-tuning embedding models for your domain: when it beats a reranker, hard negatives, sentence-transformers v6 losses, Matryoshka, evals and cost.","Fine-tuning embedding models: loose dots on the left become tight clusters on the right after training.",{"slug":412,"published":413,"updated":414,"minutes":7,"category":90,"tags":415,"tagPages":416,"keywords":417,"about":425,"sources":434,"cover":458,"og":459,"expertise":78,"locales":460,"lang":80,"title":461,"description":462,"coverAlt":463},"langfuse","2026-08-13","2026-10-07",[92,93,94,95,11],[97,98,99,100,16],[412,418,419,420,421,422,423,424],"langfuse vs langsmith","llm tracing tool","self-hosted llm observability","langfuse pricing","opentelemetry llm traces","llm cost tracking","prompt versioning",[426,429,430,433],{"name":427,"url":428},"Langfuse","https:\u002F\u002Flangfuse.com",{"name":94,"url":114},{"name":431,"url":432},"ClickHouse","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FClickHouse",{"name":116,"url":117},[435,438,441,444,447,450,453,456],{"title":436,"url":437},"Langfuse documentation: observability and application tracing","https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fobservability\u002Foverview",{"title":439,"url":440},"Langfuse documentation: get started with tracing","https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fobservability\u002Fget-started",{"title":442,"url":443},"Langfuse pricing: cloud plans, billable units and worked examples","https:\u002F\u002Flangfuse.com\u002Fpricing",{"title":445,"url":446},"Langfuse pricing: self-hosted plans and the feature comparison","https:\u002F\u002Flangfuse.com\u002Fpricing-self-host",{"title":448,"url":449},"Self-host Langfuse: deployment options, containers and storage services","https:\u002F\u002Flangfuse.com\u002Fself-hosting",{"title":451,"url":452},"Langfuse changelog: v4 is live (17 August 2026)","https:\u002F\u002Flangfuse.com\u002Fchangelog\u002F2026-08-17-langfuse-v4",{"title":454,"url":455},"Langfuse blog: Langfuse joins ClickHouse (16 January 2026)","https:\u002F\u002Flangfuse.com\u002Fblog\u002Fjoining-clickhouse",{"title":457,"url":184},"GitHub: langfuse\u002Flangfuse, the platform repository","\u002Fimages\u002Fblog\u002Flangfuse\u002Fcover.webp","\u002Fimages\u002Fblog\u002Flangfuse\u002Fog.jpg",[80,81,82],"Langfuse review: tracing, prompts and evals you can host yourself","Langfuse: LLM traces, prompt versions and experiments on one MIT-licensed platform. What self-hosting costs, how unit pricing adds up, and where it loses.","Langfuse review: a footprint trail in a house garden leads to a notebook with a magnifying glass.",{"slug":465,"published":466,"updated":200,"minutes":7,"category":90,"tags":467,"tagPages":469,"keywords":470,"about":478,"sources":483,"cover":509,"og":510,"expertise":78,"locales":511,"lang":80,"title":512,"description":513,"coverAlt":514},"arize-phoenix","2026-07-03",[92,93,94,468,11],"Self-hosted",[97,98,99,16],[471,472,473,474,475,476,477],"arize phoenix","phoenix arize self-hosted","arize phoenix docker","llm tracing opentelemetry","phoenix vs langfuse","openinference instrumentation","llm observability tools",[479,481,482],{"name":480,"url":187},"Arize Phoenix",{"name":94,"url":114},{"name":116,"url":117},[484,487,490,493,496,499,502,505,507],{"title":485,"url":486},"Arize Phoenix: open-source AI observability and evaluation","https:\u002F\u002Fphoenix.arize.com",{"title":488,"url":489},"Phoenix documentation: self-hosting","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix\u002Fself-hosting",{"title":491,"url":492},"Phoenix documentation: licence, Elastic License 2.0","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix\u002Fself-hosting\u002Flicense",{"title":494,"url":495},"Phoenix documentation: architecture, storage and scaling","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix\u002Fself-hosting\u002Farchitecture",{"title":497,"url":498},"Phoenix documentation: setup tracing","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix\u002Ftracing\u002Fhow-to-tracing\u002Fsetup-tracing",{"title":500,"url":501},"Phoenix documentation: OpenTelemetry SDK setup","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix\u002Ftracing\u002Fhow-to-tracing\u002Fsetup-tracing\u002Fsetup-using-phoenix-otel",{"title":503,"url":504},"Arize pricing: AX Free, AX Pro and AX Enterprise","https:\u002F\u002Farize.com\u002Fpricing\u002F",{"title":506,"url":443},"Langfuse pricing: cloud plans and billable units",{"title":508,"url":190},"LangChain pricing: LangSmith plans","\u002Fimages\u002Fblog\u002Farize-phoenix\u002Fcover.webp","\u002Fimages\u002Fblog\u002Farize-phoenix\u002Fog.jpg",[80,81,82],"Arize Phoenix review: LLM tracing and evals you host yourself","Arize Phoenix: an ELv2-licensed tracing and eval server on your own database. Strengths, operating cost, and where Langfuse, Braintrust or LangSmith win.","Arize Phoenix review: a phoenix rises above a small house with a magnifying glass on its roof.",1793451238220]