[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-openrag-extensible-stack-for-agentic-rag-summary":3,"summaries-facets-categories":111,"summary-related-openrag-extensible-stack-for-agentic-rag-summary":4517},{"id":4,"title":5,"ai":6,"body":13,"categories":86,"created_at":87,"date_modified":87,"description":88,"extension":89,"faq":87,"featured":90,"kicker_label":87,"meta":91,"navigation":92,"path":93,"published_at":94,"question":87,"scraped_at":95,"seo":96,"sitemap":97,"source_id":98,"source_name":99,"source_type":100,"source_url":101,"stem":102,"tags":103,"thumbnail_url":87,"tldr":108,"tweet":87,"unknown_tags":109,"__hash__":110},"summaries\u002Fsummaries\u002Fopenrag-extensible-stack-for-agentic-rag-summary.md","OpenRAG: Extensible Stack for Agentic RAG",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",6666,1622,14192,0.0021217,{"type":14,"value":15,"toc":78},"minimark",[16,21,25,29,32,61,64,68,71,75],[17,18,20],"h2",{"id":19},"why-start-with-openrags-opinionated-baseline","Why Start with OpenRAG's Opinionated Baseline",[22,23,24],"p",{},"RAG remains complex due to variables like PDF parsing pains, chunking strategies, evolving embeddings, and tweaks such as summaries, chunk expansion, cross-encoders, re-ranking, and query rewriting—tailored to unique documents, users, and queries. Claims that \"RAG is dead\" or \"solved\" ignore these realities; context windows don't eliminate costs for million-token datasets, and naive pipelines (extract text, chunk, embed, vector DB, top-k retrieval) fail in production. OpenRAG provides a high-quality, extensible baseline using three open-source projects: Docling (document processing), OpenSearch (search\u002Findexing), and Langflow (visual orchestration\u002Fagents). Run it fully offline with local models like IBM Granite 3B (LLM) or Qwen3 0.6B\u002F6B (embeddings), supporting air-gapped setups. This stack enables agentic retrieval where the LLM decides searches\u002Ftools, outperforming rigid top-k by handling multi-step queries dynamically.",[17,26,28],{"id":27},"superior-document-ingestion-with-docling","Superior Document Ingestion with Docling",[22,30,31],{},"Docling excels at parsing diverse formats (PDFs, HTML, Word, slides, spreadsheets, audio\u002Fvideo), outputting structured DocTags (XML-like hierarchy) convertible to Markdown, HTML, or JSON. Use hierarchical chunking based on document structure for better context preservation. Pipelines include:",[33,34,35,43,49,55],"ul",{},[36,37,38,42],"li",{},[39,40,41],"strong",{},"Simple",": Text extraction for Markdown\u002FHTML\u002FWord.",[36,44,45,48],{},[39,46,47],{},"ASR",": Speech-to-text for audio\u002Fvideo.",[36,50,51,54],{},[39,52,53],{},"PDF Standard",": Small models for layout analysis, table\u002Fimage extraction, OCR (for scanned docs).",[36,56,57,60],{},[39,58,59],{},"PDF VLM",": Granite Docling 25.8M vision model for end-to-end extraction.",[22,62,63],{},"Toggle options like table structure capture, OCR, and image descriptions (slower but richer). Embed chunks via flexible providers (OpenAI, local), then index in OpenSearch for hybrid vector\u002Fkeyword search with filtering\u002Faggregation.",[17,65,67],{"id":66},"hybrid-search-and-agentic-generation-in-opensearch-langflow","Hybrid Search and Agentic Generation in OpenSearch + Langflow",[22,69,70],{},"OpenSearch (Elasticsearch fork) supports multi-model vector search (useful for embedding migrations, despite slowdowns) and JVector KNN plugin for live indexing on disk (no full in-memory requirement, scales better than HNSW\u002FIVF). Agentic retrieval in Langflow gives the LLM tools (e.g., multi-model OpenSearch retriever, calculator to avoid math hallucinations, MCP server) and instructions to perform iterative searches, yielding precise answers with tool traces and next-query nudges. UI features: upload\u002Fsync folders, inspect chunks\u002Fobjects, create knowledge filters (e.g., by metadata), cloud connectors (Google Drive\u002FSharePoint\u002FOneDrive via OAuth for auto-sync).",[17,72,74],{"id":73},"tune-evaluate-and-extend-without-reinventing","Tune, Evaluate, and Extend Without Reinventing",[22,76,77],{},"Customize via settings (chunk size\u002Foverlap, Docling flags, system prompts, API keys for app integration) or Langflow's drag-and-drop editor: add guardrails (parse\u002Fvalidate inputs), Ollama models, or new flows. Expose as API\u002FMCP server for other agents. Version 0.4.0 is playable today (Next.js frontend, Python backend); star\u002Fcontribute on GitHub. Test outcomes iteratively—OpenRAG's modularity lets you baseline, measure (e.g., via Langflow enrichment), and adapt for your data\u002Fusers, avoiding per-project wheel-reinvention.",{"title":79,"searchDepth":80,"depth":80,"links":81},"",2,[82,83,84,85],{"id":19,"depth":80,"text":20},{"id":27,"depth":80,"text":28},{"id":66,"depth":80,"text":67},{"id":73,"depth":80,"text":74},[],null,"There are many variables in building RAG applications, from document parsing to the language model you pick for generation and everything in between. Combining Docling for document parsing, OpenSearch for retrieval, and Langflow for orchestration, plus local and remote models, OpenRAG is an opinionated, agentic, open-source stack for building the RAG application of your dreams.\n\nJust because it has opinions doesn't make it inflexible though. In this talk we'll look at how OpenRAG gives you a great baseline for RAG and how you can tune it and evaluate the outcomes to create RAG applications that work well with your data. You'll learn how to get the best out of your documents with Docling, how OpenSearch provides more than just vector search, and how Langflow makes it easy to customise your pipeline to interact with your data the way you want to. You’ll leave with a playbook of options to improve your RAG app and a stack you can extend without reinventing everything.\n\nPhil Nash - Developer relations engineer, IBM\n\nPhil is a developer relations engineer for DataStax and Google Developer Expert living in Melbourne, Australia. He's been working in developer relations for a decade, speaking at conferences since 2012, and writing JavaScript since before jQuery. Away from the keyboard, Phil enjoys travel, live music, and hanging out with his mini sausage dog, Ruby.\n\nSocials:\nhttps:\u002F\u002Fx.com\u002Fphilnash\nhttps:\u002F\u002Flinkedin.com\u002Fin\u002Fphilnash\nhttps:\u002F\u002Fphilna.sh\nhttps:\u002F\u002Fgithub.com\u002Fphilnash","md",false,{},true,"\u002Fsummaries\u002Fopenrag-extensible-stack-for-agentic-rag-summary","2026-04-08 11:00:16","2026-04-08 14:46:44",{"title":5,"description":88},{"loc":93},"885ec3c38f4cbdf4","AI Engineer","video","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4TxOBhDRRCM","summaries\u002Fopenrag-extensible-stack-for-agentic-rag-summary",[104,105,106,107],"llm","agents","ai-tools","open-source","OpenRAG combines Docling for document parsing, OpenSearch for hybrid search, and Langflow for orchestration into an open-source baseline that supports agentic retrieval, local models, and easy customization for production RAG apps.",[],"sfmkf57ahoGIsKng_IMBQxkY762_WuID4PA_D5qA9WI",[112,115,117,120,122,125,128,131,134,136,138,140,142,144,146,148,151,153,155,157,159,161,163,166,168,170,172,174,176,178,180,182,184,186,188,190,192,194,196,198,200,202,204,206,208,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,281,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691,3693,3695,3697,3699,3701,3703,3705,3707,3709,3711,3713,3715,3717,3719,3721,3723,3725,3727,3729,3731,3733,3735,3737,3739,3741,3743,3745,3747,3749,3751,3753,3755,3757,3759,3761,3763,3765,3767,3769,3771,3773,3775,3777,3779,3781,3783,3785,3787,3789,3791,3793,3795,3797,3799,3801,3803,3805,3807,3809,3811,3813,3815,3817,3819,3821,3823,3825,3827,3829,3831,3833,3835,3837,3839,3841,3843,3845,3847,3849,3851,3853,3855,3857,3859,3861,3863,3865,3867,3869,3871,3873,3875,3877,3879,3881,3883,3885,3887,3889,3891,3893,3895,3897,3899,3901,3903,3905,3907,3909,3911,3913,3915,3917,3919,3921,3923,3925,3927,3929,3931,3933,3935,3937,3939,3941,3943,3945,3947,3949,3951,3953,3955,3957,3959,3961,3963,3965,3967,3969,3971,3973,3975,3977,3979,3981,3983,3985,3987,3989,3991,3993,3995,3997,3999,4001,4003,4005,4007,4009,4011,4013,4015,4017,4019,4021,4023,4025,4027,4029,4031,4033,4035,4037,4039,4041,4043,4045,4047,4049,4051,4053,4055,4057,4059,4061,4063,4065,4067,4069,4071,4073,4075,4077,4079,4081,4083,4085,4087,4089,4091,4093,4095,4097,4099,4101,4103,4105,4107,4109,4111,4113,4115,4117,4119,4121,4123,4125,4127,4129,4131,4133,4135,4137,4139,4141,4143,4145,4147,4149,4151,4153,4155,4157,4159,4161,4163,4165,4167,4169,4171,4173,4175,4177,4179,4181,4183,4185,4187,4189,4191,4193,4195,4197,4199,4201,4203,4205,4207,4209,4211,4213,4215,4217,4219,4221,4223,4225,4227,4229,4231,4233,4235,4237,4239,4241,4243,4245,4247,4249,4251,4253,4255,4257,4259,4261,4263,4265,4267,4269,4271,4273,4275,4277,4279,4281,4283,4285,4287,4289,4291,4293,4295,4297,4299,4301,4303,4305,4307,4309,4311,4313,4315,4317,4319,4321,4323,4325,4327,4329,4331,4333,4335,4337,4339,4341,4343,4345,4347,4349,4351,4353,4355,4357,4359,4361,4363,4365,4367,4369,4371,4373,4375,4377,4379,4381,4383,4385,4387,4389,4391,4393,4395,4397,4399,4401,4403,4405,4407,4409,4411,4413,4415,4417,4419,4421,4423,4425,4427,4429,4431,4433,4435,4437,4439,4441,4443,4445,4447,4449,4451,4453,4455,4457,4459,4461,4463,4465,4467,4469,4471,4473,4475,4477,4479,4481,4483,4485,4487,4489,4491,4493,4495,4497,4499,4501,4503,4505,4507,4509,4511,4513,4515],{"categories":113},[114],"Business & SaaS",{"categories":116},[114],{"categories":118},[119],"AI News & Trends",{"categories":121},[],{"categories":123},[124],"AI Automation",{"categories":126},[127],"Marketing & Growth",{"categories":129},[130],"Design & Frontend",{"categories":132},[133],"Software Engineering",{"categories":135},[124],{"categories":137},[],{"categories":139},[130],{"categories":141},[130],{"categories":143},[124],{"categories":145},[130],{"categories":147},[130],{"categories":149},[150],"AI & LLMs",{"categories":152},[130],{"categories":154},[130],{"categories":156},[],{"categories":158},[130],{"categories":160},[130],{"categories":162},[150],{"categories":164},[165],"Developer Productivity",{"categories":167},[150],{"categories":169},[150],{"categories":171},[150],{"categories":173},[119],{"categories":175},[150],{"categories":177},[124],{"categories":179},[114],{"categories":181},[119],{"categories":183},[127],{"categories":185},[],{"categories":187},[],{"categories":189},[124],{"categories":191},[124],{"categories":193},[124],{"categories":195},[127],{"categories":197},[150],{"categories":199},[165],{"categories":201},[119],{"categories":203},[],{"categories":205},[],{"categories":207},[],{"categories":209},[210],"Data Science & Visualization",{"categories":212},[],{"categories":214},[124],{"categories":216},[133],{"categories":218},[124],{"categories":220},[124],{"categories":222},[150],{"categories":224},[127],{"categories":226},[124],{"categories":228},[],{"categories":230},[],{"categories":232},[],{"categories":234},[130],{"categories":236},[130],{"categories":238},[124],{"categories":240},[127],{"categories":242},[165],{"categories":244},[130],{"categories":246},[150],{"categories":248},[133],{"categories":250},[150],{"categories":252},[],{"categories":254},[124],{"categories":256},[150],{"categories":258},[165],{"categories":260},[165],{"categories":262},[],{"categories":264},[127],{"categories":266},[114],{"categories":268},[150],{"categories":270},[114],{"categories":272},[114],{"categories":274},[124],{"categories":276},[127],{"categories":278},[124],{"categories":280},[114],{"categories":282},[124],{"categories":284},[130],{"categories":286},[150],{"categories":288},[130],{"categories":290},[150],{"categories":292},[114],{"categories":294},[150],{"categories":296},[127],{"categories":298},[],{"categories":300},[150],{"categories":302},[114],{"categories":304},[],{"categories":306},[119],{"categories":308},[133],{"categories":310},[],{"categories":312},[150],{"categories":314},[130],{"categories":316},[150],{"categories":318},[130],{"categories":320},[],{"categories":322},[124],{"categories":324},[],{"categories":326},[],{"categories":328},[],{"categories":330},[150],{"categories":332},[],{"categories":334},[150],{"categories":336},[150],{"categories":338},[130],{"categories":340},[150],{"categories":342},[165],{"categories":344},[124],{"categories":346},[127],{"categories":348},[165],{"categories":350},[165],{"categories":352},[165],{"categories":354},[127],{"categories":356},[127],{"categories":358},[150],{"categories":360},[150],{"categories":362},[130],{"categories":364},[114],{"categories":366},[130],{"categories":368},[133],{"categories":370},[114],{"categories":372},[114],{"categories":374},[114],{"categories":376},[130],{"categories":378},[],{"categories":380},[],{"categories":382},[150],{"categories":384},[150],{"categories":386},[133],{"categories":388},[150],{"categories":390},[150],{"categories":392},[],{"categories":394},[150],{"categories":396},[150],{"categories":398},[],{"categories":400},[150],{"categories":402},[119],{"categories":404},[119],{"categories":406},[],{"categories":408},[],{"categories":410},[127],{"categories":412},[127],{"categories":414},[133],{"categories":416},[150],{"categories":418},[],{"categories":420},[],{"categories":422},[124],{"categories":424},[150],{"categories":426},[150],{"categories":428},[],{"categories":430},[150,114],{"categories":432},[150],{"categories":434},[],{"categories":436},[150],{"categories":438},[150],{"categories":440},[],{"categories":442},[],{"categories":444},[124],{"categories":446},[150],{"categories":448},[150],{"categories":450},[124],{"categories":452},[150],{"categories":454},[],{"categories":456},[],{"categories":458},[150],{"categories":460},[],{"categories":462},[150],{"categories":464},[150],{"categories":466},[],{"categories":468},[124],{"categories":470},[130],{"categories":472},[],{"categories":474},[124,475],"DevOps & Cloud",{"categories":477},[150],{"categories":479},[124],{"categories":481},[150],{"categories":483},[],{"categories":485},[],{"categories":487},[],{"categories":489},[],{"categories":491},[150],{"categories":493},[124],{"categories":495},[],{"categories":497},[124],{"categories":499},[],{"categories":501},[150],{"categories":503},[],{"categories":505},[],{"categories":507},[],{"categories":509},[],{"categories":511},[124],{"categories":513},[130],{"categories":515},[150],{"categories":517},[127],{"categories":519},[119],{"categories":521},[114],{"categories":523},[165],{"categories":525},[],{"categories":527},[124],{"categories":529},[124],{"categories":531},[150],{"categories":533},[],{"categories":535},[],{"categories":537},[],{"categories":539},[124],{"categories":541},[],{"categories":543},[124],{"categories":545},[124],{"categories":547},[119],{"categories":549},[124],{"categories":551},[150],{"categories":553},[],{"categories":555},[150],{"categories":557},[],{"categories":559},[119],{"categories":561},[124,562],"Product Strategy",{"categories":564},[133],{"categories":566},[475],{"categories":568},[562],{"categories":570},[150],{"categories":572},[124],{"categories":574},[],{"categories":576},[119],{"categories":578},[119],{"categories":580},[124],{"categories":582},[],{"categories":584},[124],{"categories":586},[150],{"categories":588},[150],{"categories":590},[165],{"categories":592},[150],{"categories":594},[],{"categories":596},[150,133],{"categories":598},[119],{"categories":600},[150],{"categories":602},[119],{"categories":604},[124],{"categories":606},[119],{"categories":608},[],{"categories":610},[133],{"categories":612},[114],{"categories":614},[],{"categories":616},[124],{"categories":618},[124],{"categories":620},[124],{"categories":622},[124],{"categories":624},[114],{"categories":626},[130],{"categories":628},[127],{"categories":630},[],{"categories":632},[124],{"categories":634},[],{"categories":636},[119],{"categories":638},[119],{"categories":640},[119],{"categories":642},[124],{"categories":644},[119],{"categories":646},[150],{"categories":648},[165],{"categories":650},[150],{"categories":652},[133],{"categories":654},[150,165],{"categories":656},[165],{"categories":658},[165],{"categories":660},[165],{"categories":662},[165],{"categories":664},[150],{"categories":666},[],{"categories":668},[],{"categories":670},[127],{"categories":672},[],{"categories":674},[150],{"categories":676},[165],{"categories":678},[150],{"categories":680},[130],{"categories":682},[133],{"categories":684},[],{"categories":686},[150],{"categories":688},[165],{"categories":690},[127],{"categories":692},[119],{"categories":694},[133],{"categories":696},[150],{"categories":698},[],{"categories":700},[133],{"categories":702},[130],{"categories":704},[114],{"categories":706},[114],{"categories":708},[],{"categories":710},[130],{"categories":712},[114],{"categories":714},[119],{"categories":716},[165],{"categories":718},[124],{"categories":720},[124],{"categories":722},[150],{"categories":724},[150],{"categories":726},[119],{"categories":728},[119],{"categories":730},[165],{"categories":732},[119],{"categories":734},[],{"categories":736},[562],{"categories":738},[124],{"categories":740},[119],{"categories":742},[119],{"categories":744},[119],{"categories":746},[150],{"categories":748},[124],{"categories":750},[124],{"categories":752},[114],{"categories":754},[114],{"categories":756},[150],{"categories":758},[119],{"categories":760},[],{"categories":762},[150],{"categories":764},[114],{"categories":766},[124],{"categories":768},[124],{"categories":770},[124],{"categories":772},[130],{"categories":774},[124],{"categories":776},[165],{"categories":778},[119],{"categories":780},[119],{"categories":782},[119],{"categories":784},[119],{"categories":786},[119],{"categories":788},[],{"categories":790},[],{"categories":792},[165],{"categories":794},[119],{"categories":796},[119],{"categories":798},[119],{"categories":800},[],{"categories":802},[150],{"categories":804},[],{"categories":806},[],{"categories":808},[130],{"categories":810},[114],{"categories":812},[],{"categories":814},[119],{"categories":816},[124],{"categories":818},[124],{"categories":820},[124],{"categories":822},[127],{"categories":824},[124],{"categories":826},[],{"categories":828},[119],{"categories":830},[119],{"categories":832},[150],{"categories":834},[],{"categories":836},[127],{"categories":838},[127],{"categories":840},[150],{"categories":842},[119],{"categories":844},[114],{"categories":846},[133],{"categories":848},[150],{"categories":850},[],{"categories":852},[150],{"categories":854},[150],{"categories":856},[133],{"categories":858},[150],{"categories":860},[150],{"categories":862},[150],{"categories":864},[127],{"categories":866},[119],{"categories":868},[150],{"categories":870},[150],{"categories":872},[119],{"categories":874},[124],{"categories":876},[165],{"categories":878},[114],{"categories":880},[150],{"categories":882},[165],{"categories":884},[165],{"categories":886},[],{"categories":888},[127],{"categories":890},[119],{"categories":892},[119],{"categories":894},[165],{"categories":896},[124],{"categories":898},[124],{"categories":900},[124],{"categories":902},[124],{"categories":904},[130],{"categories":906},[150],{"categories":908},[150],{"categories":910},[562],{"categories":912},[150],{"categories":914},[150],{"categories":916},[124],{"categories":918},[114],{"categories":920},[127],{"categories":922},[],{"categories":924},[114],{"categories":926},[114],{"categories":928},[],{"categories":930},[130],{"categories":932},[150],{"categories":934},[],{"categories":936},[],{"categories":938},[119],{"categories":940},[119],{"categories":942},[119],{"categories":944},[119],{"categories":946},[],{"categories":948},[119],{"categories":950},[150],{"categories":952},[150],{"categories":954},[],{"categories":956},[119],{"categories":958},[119],{"categories":960},[114],{"categories":962},[150],{"categories":964},[],{"categories":966},[],{"categories":968},[119],{"categories":970},[119],{"categories":972},[119],{"categories":974},[150],{"categories":976},[119],{"categories":978},[119],{"categories":980},[119],{"categories":982},[119],{"categories":984},[119],{"categories":986},[],{"categories":988},[124],{"categories":990},[150],{"categories":992},[127],{"categories":994},[114],{"categories":996},[124],{"categories":998},[150],{"categories":1000},[],{"categories":1002},[127],{"categories":1004},[119],{"categories":1006},[119],{"categories":1008},[119],{"categories":1010},[119],{"categories":1012},[165],{"categories":1014},[133],{"categories":1016},[],{"categories":1018},[150],{"categories":1020},[124],{"categories":1022},[124],{"categories":1024},[124],{"categories":1026},[475],{"categories":1028},[124],{"categories":1030},[150],{"categories":1032},[150],{"categories":1034},[133],{"categories":1036},[475],{"categories":1038},[210],{"categories":1040},[150],{"categories":1042},[210],{"categories":1044},[],{"categories":1046},[127],{"categories":1048},[127],{"categories":1050},[130],{"categories":1052},[475],{"categories":1054},[124],{"categories":1056},[150],{"categories":1058},[150],{"categories":1060},[124],{"categories":1062},[124],{"categories":1064},[124],{"categories":1066},[165],{"categories":1068},[165],{"categories":1070},[124],{"categories":1072},[124],{"categories":1074},[],{"categories":1076},[124],{"categories":1078},[124],{"categories":1080},[150],{"categories":1082},[210],{"categories":1084},[124],{"categories":1086},[124],{"categories":1088},[124],{"categories":1090},[124],{"categories":1092},[114],{"categories":1094},[130],{"categories":1096},[119],{"categories":1098},[133],{"categories":1100},[475],{"categories":1102},[133],{"categories":1104},[210],{"categories":1106},[],{"categories":1108},[133],{"categories":1110},[],{"categories":1112},[],{"categories":1114},[133],{"categories":1116},[150],{"categories":1118},[],{"categories":1120},[],{"categories":1122},[],{"categories":1124},[114],{"categories":1126},[],{"categories":1128},[],{"categories":1130},[210],{"categories":1132},[150],{"categories":1134},[475],{"categories":1136},[150],{"categories":1138},[],{"categories":1140},[124],{"categories":1142},[165],{"categories":1144},[165],{"categories":1146},[127],{"categories":1148},[127],{"categories":1150},[127],{"categories":1152},[475],{"categories":1154},[133],{"categories":1156},[124],{"categories":1158},[114],{"categories":1160},[114],{"categories":1162},[133],{"categories":1164},[130],{"categories":1166},[210],{"categories":1168},[130],{"categories":1170},[],{"categories":1172},[150],{"categories":1174},[124],{"categories":1176},[124],{"categories":1178},[165],{"categories":1180},[124],{"categories":1182},[124],{"categories":1184},[130],{"categories":1186},[130],{"categories":1188},[124],{"categories":1190},[475],{"categories":1192},[150],{"categories":1194},[],{"categories":1196},[127],{"categories":1198},[124],{"categories":1200},[114],{"categories":1202},[124],{"categories":1204},[124],{"categories":1206},[],{"categories":1208},[150],{"categories":1210},[124],{"categories":1212},[124],{"categories":1214},[165],{"categories":1216},[124],{"categories":1218},[150],{"categories":1220},[],{"categories":1222},[124],{"categories":1224},[],{"categories":1226},[130],{"categories":1228},[165],{"categories":1230},[150],{"categories":1232},[133],{"categories":1234},[130],{"categories":1236},[165],{"categories":1238},[210],{"categories":1240},[165],{"categories":1242},[],{"categories":1244},[150],{"categories":1246},[150],{"categories":1248},[562],{"categories":1250},[133],{"categories":1252},[150,124],{"categories":1254},[124],{"categories":1256},[150],{"categories":1258},[124],{"categories":1260},[124,133],{"categories":1262},[124],{"categories":1264},[150],{"categories":1266},[],{"categories":1268},[165],{"categories":1270},[150],{"categories":1272},[124],{"categories":1274},[150],{"categories":1276},[],{"categories":1278},[133],{"categories":1280},[114],{"categories":1282},[124],{"categories":1284},[],{"categories":1286},[210],{"categories":1288},[133],{"categories":1290},[124],{"categories":1292},[133],{"categories":1294},[],{"categories":1296},[124],{"categories":1298},[],{"categories":1300},[124],{"categories":1302},[],{"categories":1304},[],{"categories":1306},[130],{"categories":1308},[165],{"categories":1310},[150],{"categories":1312},[124],{"categories":1314},[],{"categories":1316},[124],{"categories":1318},[133],{"categories":1320},[150],{"categories":1322},[150],{"categories":1324},[133],{"categories":1326},[133],{"categories":1328},[165],{"categories":1330},[114],{"categories":1332},[],{"categories":1334},[150],{"categories":1336},[150],{"categories":1338},[150],{"categories":1340},[124],{"categories":1342},[150],{"categories":1344},[],{"categories":1346},[130],{"categories":1348},[150],{"categories":1350},[124],{"categories":1352},[],{"categories":1354},[150],{"categories":1356},[],{"categories":1358},[150],{"categories":1360},[],{"categories":1362},[],{"categories":1364},[],{"categories":1366},[150],{"categories":1368},[150],{"categories":1370},[150],{"categories":1372},[150],{"categories":1374},[],{"categories":1376},[150],{"categories":1378},[150],{"categories":1380},[150],{"categories":1382},[],{"categories":1384},[150],{"categories":1386},[],{"categories":1388},[127],{"categories":1390},[150],{"categories":1392},[],{"categories":1394},[],{"categories":1396},[],{"categories":1398},[150],{"categories":1400},[119],{"categories":1402},[119],{"categories":1404},[],{"categories":1406},[124],{"categories":1408},[150],{"categories":1410},[],{"categories":1412},[150],{"categories":1414},[150],{"categories":1416},[119],{"categories":1418},[],{"categories":1420},[150],{"categories":1422},[119],{"categories":1424},[124],{"categories":1426},[150],{"categories":1428},[],{"categories":1430},[],{"categories":1432},[],{"categories":1434},[124],{"categories":1436},[124],{"categories":1438},[124],{"categories":1440},[124],{"categories":1442},[150],{"categories":1444},[130],{"categories":1446},[130],{"categories":1448},[124],{"categories":1450},[124],{"categories":1452},[165],{"categories":1454},[562],{"categories":1456},[165],{"categories":1458},[165],{"categories":1460},[150],{"categories":1462},[124],{"categories":1464},[150],{"categories":1466},[165],{"categories":1468},[150],{"categories":1470},[124],{"categories":1472},[124],{"categories":1474},[124],{"categories":1476},[124],{"categories":1478},[124],{"categories":1480},[150],{"categories":1482},[165],{"categories":1484},[165],{"categories":1486},[127],{"categories":1488},[124],{"categories":1490},[],{"categories":1492},[124],{"categories":1494},[],{"categories":1496},[119],{"categories":1498},[150],{"categories":1500},[],{"categories":1502},[114],{"categories":1504},[130],{"categories":1506},[130],{"categories":1508},[124],{"categories":1510},[124],{"categories":1512},[150],{"categories":1514},[150],{"categories":1516},[119],{"categories":1518},[119],{"categories":1520},[475],{"categories":1522},[124],{"categories":1524},[119],{"categories":1526},[],{"categories":1528},[150],{"categories":1530},[124],{"categories":1532},[124],{"categories":1534},[124],{"categories":1536},[124],{"categories":1538},[150],{"categories":1540},[150],{"categories":1542},[150],{"categories":1544},[150],{"categories":1546},[124],{"categories":1548},[124],{"categories":1550},[124],{"categories":1552},[124],{"categories":1554},[],{"categories":1556},[130],{"categories":1558},[150],{"categories":1560},[150],{"categories":1562},[150],{"categories":1564},[],{"categories":1566},[127],{"categories":1568},[],{"categories":1570},[165],{"categories":1572},[],{"categories":1574},[124],{"categories":1576},[165],{"categories":1578},[130],{"categories":1580},[165],{"categories":1582},[],{"categories":1584},[165],{"categories":1586},[165],{"categories":1588},[],{"categories":1590},[130],{"categories":1592},[124],{"categories":1594},[124],{"categories":1596},[165],{"categories":1598},[150],{"categories":1600},[150],{"categories":1602},[],{"categories":1604},[119],{"categories":1606},[],{"categories":1608},[127],{"categories":1610},[],{"categories":1612},[130],{"categories":1614},[119],{"categories":1616},[130],{"categories":1618},[130],{"categories":1620},[130],{"categories":1622},[130],{"categories":1624},[130],{"categories":1626},[130],{"categories":1628},[130],{"categories":1630},[130],{"categories":1632},[130],{"categories":1634},[130],{"categories":1636},[],{"categories":1638},[124],{"categories":1640},[130],{"categories":1642},[150],{"categories":1644},[150],{"categories":1646},[130],{"categories":1648},[130],{"categories":1650},[130],{"categories":1652},[130],{"categories":1654},[130],{"categories":1656},[130],{"categories":1658},[130],{"categories":1660},[150,130],{"categories":1662},[130],{"categories":1664},[130],{"categories":1666},[130],{"categories":1668},[130],{"categories":1670},[],{"categories":1672},[130],{"categories":1674},[130],{"categories":1676},[130],{"categories":1678},[130],{"categories":1680},[130],{"categories":1682},[130],{"categories":1684},[130],{"categories":1686},[130],{"categories":1688},[130],{"categories":1690},[130,150],{"categories":1692},[130],{"categories":1694},[130],{"categories":1696},[],{"categories":1698},[119],{"categories":1700},[],{"categories":1702},[150],{"categories":1704},[],{"categories":1706},[124],{"categories":1708},[475],{"categories":1710},[562],{"categories":1712},[124],{"categories":1714},[124],{"categories":1716},[],{"categories":1718},[124],{"categories":1720},[],{"categories":1722},[124],{"categories":1724},[],{"categories":1726},[],{"categories":1728},[150],{"categories":1730},[150],{"categories":1732},[150],{"categories":1734},[119],{"categories":1736},[119],{"categories":1738},[119],{"categories":1740},[119],{"categories":1742},[],{"categories":1744},[119],{"categories":1746},[],{"categories":1748},[119],{"categories":1750},[150],{"categories":1752},[119],{"categories":1754},[119],{"categories":1756},[119],{"categories":1758},[119],{"categories":1760},[150],{"categories":1762},[119],{"categories":1764},[124],{"categories":1766},[],{"categories":1768},[124],{"categories":1770},[119],{"categories":1772},[150],{"categories":1774},[119],{"categories":1776},[119],{"categories":1778},[119],{"categories":1780},[150],{"categories":1782},[150],{"categories":1784},[150],{"categories":1786},[],{"categories":1788},[],{"categories":1790},[150],{"categories":1792},[119],{"categories":1794},[],{"categories":1796},[150],{"categories":1798},[124],{"categories":1800},[150],{"categories":1802},[124],{"categories":1804},[124],{"categories":1806},[150],{"categories":1808},[],{"categories":1810},[],{"categories":1812},[124],{"categories":1814},[124],{"categories":1816},[124],{"categories":1818},[124],{"categories":1820},[124],{"categories":1822},[124],{"categories":1824},[124],{"categories":1826},[124],{"categories":1828},[],{"categories":1830},[124],{"categories":1832},[124],{"categories":1834},[124],{"categories":1836},[150],{"categories":1838},[150],{"categories":1840},[150],{"categories":1842},[119],{"categories":1844},[150],{"categories":1846},[150],{"categories":1848},[150],{"categories":1850},[124],{"categories":1852},[127],{"categories":1854},[127],{"categories":1856},[127],{"categories":1858},[124],{"categories":1860},[],{"categories":1862},[150],{"categories":1864},[],{"categories":1866},[],{"categories":1868},[150],{"categories":1870},[],{"categories":1872},[124],{"categories":1874},[130],{"categories":1876},[165],{"categories":1878},[210],{"categories":1880},[150],{"categories":1882},[124],{"categories":1884},[130],{"categories":1886},[],{"categories":1888},[124],{"categories":1890},[127,114],{"categories":1892},[124],{"categories":1894},[124],{"categories":1896},[475],{"categories":1898},[133],{"categories":1900},[127],{"categories":1902},[165],{"categories":1904},[150],{"categories":1906},[],{"categories":1908},[150],{"categories":1910},[],{"categories":1912},[150],{"categories":1914},[150],{"categories":1916},[124],{"categories":1918},[],{"categories":1920},[150],{"categories":1922},[124],{"categories":1924},[150],{"categories":1926},[165],{"categories":1928},[124],{"categories":1930},[150],{"categories":1932},[150,165],{"categories":1934},[165],{"categories":1936},[],{"categories":1938},[150],{"categories":1940},[150],{"categories":1942},[150],{"categories":1944},[],{"categories":1946},[],{"categories":1948},[124],{"categories":1950},[127],{"categories":1952},[119],{"categories":1954},[124],{"categories":1956},[150],{"categories":1958},[119],{"categories":1960},[],{"categories":1962},[165],{"categories":1964},[119],{"categories":1966},[],{"categories":1968},[210],{"categories":1970},[127],{"categories":1972},[114],{"categories":1974},[119],{"categories":1976},[150],{"categories":1978},[124],{"categories":1980},[150],{"categories":1982},[124],{"categories":1984},[124],{"categories":1986},[119],{"categories":1988},[165],{"categories":1990},[130],{"categories":1992},[114],{"categories":1994},[150],{"categories":1996},[150],{"categories":1998},[],{"categories":2000},[],{"categories":2002},[150],{"categories":2004},[],{"categories":2006},[150],{"categories":2008},[119],{"categories":2010},[],{"categories":2012},[124],{"categories":2014},[165],{"categories":2016},[119],{"categories":2018},[165],{"categories":2020},[124],{"categories":2022},[150],{"categories":2024},[],{"categories":2026},[124],{"categories":2028},[124],{"categories":2030},[130],{"categories":2032},[124],{"categories":2034},[130],{"categories":2036},[124],{"categories":2038},[124],{"categories":2040},[130],{"categories":2042},[],{"categories":2044},[],{"categories":2046},[130],{"categories":2048},[130],{"categories":2050},[130],{"categories":2052},[133],{"categories":2054},[165],{"categories":2056},[165],{"categories":2058},[124],{"categories":2060},[119],{"categories":2062},[165],{"categories":2064},[165],{"categories":2066},[127],{"categories":2068},[130],{"categories":2070},[124],{"categories":2072},[124],{"categories":2074},[150],{"categories":2076},[165],{"categories":2078},[150],{"categories":2080},[],{"categories":2082},[475],{"categories":2084},[562],{"categories":2086},[],{"categories":2088},[],{"categories":2090},[124],{"categories":2092},[119],{"categories":2094},[127],{"categories":2096},[127],{"categories":2098},[210],{"categories":2100},[130],{"categories":2102},[210],{"categories":2104},[210],{"categories":2106},[124],{"categories":2108},[],{"categories":2110},[],{"categories":2112},[210],{"categories":2114},[133],{"categories":2116},[150],{"categories":2118},[133],{"categories":2120},[210],{"categories":2122},[133],{"categories":2124},[210],{"categories":2126},[114],{"categories":2128},[133],{"categories":2130},[165],{"categories":2132},[150],{"categories":2134},[],{"categories":2136},[210],{"categories":2138},[475],{"categories":2140},[],{"categories":2142},[150],{"categories":2144},[150],{"categories":2146},[],{"categories":2148},[],{"categories":2150},[150],{"categories":2152},[150],{"categories":2154},[119],{"categories":2156},[150],{"categories":2158},[],{"categories":2160},[119],{"categories":2162},[],{"categories":2164},[],{"categories":2166},[119],{"categories":2168},[119],{"categories":2170},[150],{"categories":2172},[150],{"categories":2174},[150],{"categories":2176},[150],{"categories":2178},[150],{"categories":2180},[150],{"categories":2182},[127],{"categories":2184},[],{"categories":2186},[150],{"categories":2188},[],{"categories":2190},[],{"categories":2192},[124],{"categories":2194},[165],{"categories":2196},[],{"categories":2198},[475],{"categories":2200},[150,475],{"categories":2202},[150],{"categories":2204},[],{"categories":2206},[130],{"categories":2208},[130],{"categories":2210},[130],{"categories":2212},[130],{"categories":2214},[130],{"categories":2216},[],{"categories":2218},[],{"categories":2220},[],{"categories":2222},[133],{"categories":2224},[124],{"categories":2226},[114],{"categories":2228},[133],{"categories":2230},[165],{"categories":2232},[130],{"categories":2234},[],{"categories":2236},[127],{"categories":2238},[562],{"categories":2240},[210],{"categories":2242},[210],{"categories":2244},[210],{"categories":2246},[165],{"categories":2248},[562],{"categories":2250},[165],{"categories":2252},[],{"categories":2254},[114],{"categories":2256},[133],{"categories":2258},[150],{"categories":2260},[130],{"categories":2262},[127],{"categories":2264},[133],{"categories":2266},[127],{"categories":2268},[150],{"categories":2270},[130],{"categories":2272},[133],{"categories":2274},[475],{"categories":2276},[150],{"categories":2278},[119],{"categories":2280},[133],{"categories":2282},[],{"categories":2284},[150],{"categories":2286},[133],{"categories":2288},[133],{"categories":2290},[124],{"categories":2292},[],{"categories":2294},[127],{"categories":2296},[127],{"categories":2298},[127],{"categories":2300},[124],{"categories":2302},[150],{"categories":2304},[],{"categories":2306},[114],{"categories":2308},[165],{"categories":2310},[165],{"categories":2312},[210],{"categories":2314},[114],{"categories":2316},[119],{"categories":2318},[210],{"categories":2320},[],{"categories":2322},[119],{"categories":2324},[119],{"categories":2326},[119],{"categories":2328},[150],{"categories":2330},[114],{"categories":2332},[150],{"categories":2334},[],{"categories":2336},[],{"categories":2338},[],{"categories":2340},[133],{"categories":2342},[124],{"categories":2344},[],{"categories":2346},[165],{"categories":2348},[130],{"categories":2350},[],{"categories":2352},[127],{"categories":2354},[],{"categories":2356},[130],{"categories":2358},[150],{"categories":2360},[165],{"categories":2362},[114],{"categories":2364},[],{"categories":2366},[130],{"categories":2368},[130],{"categories":2370},[150],{"categories":2372},[],{"categories":2374},[],{"categories":2376},[133],{"categories":2378},[150],{"categories":2380},[],{"categories":2382},[124],{"categories":2384},[150],{"categories":2386},[],{"categories":2388},[133],{"categories":2390},[124],{"categories":2392},[150],{"categories":2394},[210],{"categories":2396},[150],{"categories":2398},[],{"categories":2400},[210],{"categories":2402},[150],{"categories":2404},[133],{"categories":2406},[150],{"categories":2408},[210],{"categories":2410},[124],{"categories":2412},[150],{"categories":2414},[150],{"categories":2416},[150,124],{"categories":2418},[124],{"categories":2420},[124],{"categories":2422},[124],{"categories":2424},[130],{"categories":2426},[165],{"categories":2428},[150],{"categories":2430},[165],{"categories":2432},[130],{"categories":2434},[150],{"categories":2436},[],{"categories":2438},[],{"categories":2440},[150],{"categories":2442},[150],{"categories":2444},[150],{"categories":2446},[124],{"categories":2448},[150],{"categories":2450},[],{"categories":2452},[150],{"categories":2454},[150],{"categories":2456},[124],{"categories":2458},[124],{"categories":2460},[150],{"categories":2462},[150],{"categories":2464},[],{"categories":2466},[150],{"categories":2468},[],{"categories":2470},[150],{"categories":2472},[150],{"categories":2474},[150],{"categories":2476},[150],{"categories":2478},[150],{"categories":2480},[150],{"categories":2482},[150],{"categories":2484},[],{"categories":2486},[150],{"categories":2488},[119],{"categories":2490},[119],{"categories":2492},[],{"categories":2494},[],{"categories":2496},[150],{"categories":2498},[],{"categories":2500},[150],{"categories":2502},[150,475],{"categories":2504},[],{"categories":2506},[119],{"categories":2508},[],{"categories":2510},[150],{"categories":2512},[],{"categories":2514},[],{"categories":2516},[],{"categories":2518},[150],{"categories":2520},[],{"categories":2522},[150],{"categories":2524},[],{"categories":2526},[150],{"categories":2528},[150],{"categories":2530},[],{"categories":2532},[],{"categories":2534},[150,475],{"categories":2536},[475,150],{"categories":2538},[119],{"categories":2540},[],{"categories":2542},[150],{"categories":2544},[],{"categories":2546},[150],{"categories":2548},[150],{"categories":2550},[],{"categories":2552},[119],{"categories":2554},[150,114],{"categories":2556},[119],{"categories":2558},[133],{"categories":2560},[],{"categories":2562},[124],{"categories":2564},[150],{"categories":2566},[127],{"categories":2568},[150],{"categories":2570},[165],{"categories":2572},[165],{"categories":2574},[475],{"categories":2576},[119],{"categories":2578},[150],{"categories":2580},[475],{"categories":2582},[133],{"categories":2584},[150],{"categories":2586},[165],{"categories":2588},[],{"categories":2590},[150],{"categories":2592},[],{"categories":2594},[],{"categories":2596},[150],{"categories":2598},[],{"categories":2600},[150],{"categories":2602},[133],{"categories":2604},[114],{"categories":2606},[165],{"categories":2608},[127],{"categories":2610},[124],{"categories":2612},[165],{"categories":2614},[],{"categories":2616},[127],{"categories":2618},[],{"categories":2620},[],{"categories":2622},[150],{"categories":2624},[119],{"categories":2626},[127],{"categories":2628},[],{"categories":2630},[150],{"categories":2632},[119],{"categories":2634},[119],{"categories":2636},[127],{"categories":2638},[119],{"categories":2640},[150],{"categories":2642},[119],{"categories":2644},[150],{"categories":2646},[],{"categories":2648},[150],{"categories":2650},[150],{"categories":2652},[150],{"categories":2654},[119],{"categories":2656},[],{"categories":2658},[],{"categories":2660},[130],{"categories":2662},[119],{"categories":2664},[],{"categories":2666},[150],{"categories":2668},[150],{"categories":2670},[150],{"categories":2672},[150],{"categories":2674},[150],{"categories":2676},[150],{"categories":2678},[150],{"categories":2680},[150],{"categories":2682},[150],{"categories":2684},[127],{"categories":2686},[150,130],{"categories":2688},[119],{"categories":2690},[119],{"categories":2692},[150],{"categories":2694},[133],{"categories":2696},[210],{"categories":2698},[150],{"categories":2700},[150],{"categories":2702},[],{"categories":2704},[],{"categories":2706},[150],{"categories":2708},[150],{"categories":2710},[],{"categories":2712},[130],{"categories":2714},[130],{"categories":2716},[165],{"categories":2718},[150],{"categories":2720},[165],{"categories":2722},[150],{"categories":2724},[150],{"categories":2726},[],{"categories":2728},[150],{"categories":2730},[],{"categories":2732},[],{"categories":2734},[150],{"categories":2736},[],{"categories":2738},[],{"categories":2740},[119],{"categories":2742},[],{"categories":2744},[150],{"categories":2746},[150],{"categories":2748},[150],{"categories":2750},[],{"categories":2752},[150],{"categories":2754},[119],{"categories":2756},[562],{"categories":2758},[124],{"categories":2760},[150],{"categories":2762},[],{"categories":2764},[124],{"categories":2766},[150],{"categories":2768},[],{"categories":2770},[150],{"categories":2772},[],{"categories":2774},[124],{"categories":2776},[],{"categories":2778},[],{"categories":2780},[124],{"categories":2782},[124],{"categories":2784},[124],{"categories":2786},[150],{"categories":2788},[],{"categories":2790},[124],{"categories":2792},[124],{"categories":2794},[],{"categories":2796},[],{"categories":2798},[124],{"categories":2800},[150],{"categories":2802},[119],{"categories":2804},[562],{"categories":2806},[127],{"categories":2808},[],{"categories":2810},[130],{"categories":2812},[150],{"categories":2814},[150],{"categories":2816},[114],{"categories":2818},[119],{"categories":2820},[119],{"categories":2822},[119],{"categories":2824},[119],{"categories":2826},[],{"categories":2828},[124],{"categories":2830},[124],{"categories":2832},[124],{"categories":2834},[124],{"categories":2836},[165],{"categories":2838},[150],{"categories":2840},[114],{"categories":2842},[],{"categories":2844},[165],{"categories":2846},[124],{"categories":2848},[130],{"categories":2850},[130],{"categories":2852},[130],{"categories":2854},[130],{"categories":2856},[130],{"categories":2858},[130],{"categories":2860},[150,114],{"categories":2862},[124],{"categories":2864},[114],{"categories":2866},[119],{"categories":2868},[119],{"categories":2870},[165],{"categories":2872},[],{"categories":2874},[],{"categories":2876},[127],{"categories":2878},[],{"categories":2880},[150],{"categories":2882},[127],{"categories":2884},[150],{"categories":2886},[133],{"categories":2888},[124],{"categories":2890},[114],{"categories":2892},[124],{"categories":2894},[133],{"categories":2896},[165],{"categories":2898},[124],{"categories":2900},[],{"categories":2902},[165],{"categories":2904},[],{"categories":2906},[],{"categories":2908},[124],{"categories":2910},[124],{"categories":2912},[124],{"categories":2914},[150],{"categories":2916},[150],{"categories":2918},[150],{"categories":2920},[150],{"categories":2922},[150],{"categories":2924},[],{"categories":2926},[475],{"categories":2928},[150],{"categories":2930},[],{"categories":2932},[],{"categories":2934},[],{"categories":2936},[165],{"categories":2938},[],{"categories":2940},[150],{"categories":2942},[],{"categories":2944},[119],{"categories":2946},[150],{"categories":2948},[119],{"categories":2950},[150],{"categories":2952},[124],{"categories":2954},[],{"categories":2956},[150],{"categories":2958},[150],{"categories":2960},[],{"categories":2962},[210],{"categories":2964},[210],{"categories":2966},[133],{"categories":2968},[130],{"categories":2970},[],{"categories":2972},[150],{"categories":2974},[124],{"categories":2976},[],{"categories":2978},[],{"categories":2980},[150],{"categories":2982},[133],{"categories":2984},[124],{"categories":2986},[114],{"categories":2988},[165,133],{"categories":2990},[133],{"categories":2992},[150],{"categories":2994},[124],{"categories":2996},[],{"categories":2998},[],{"categories":3000},[],{"categories":3002},[],{"categories":3004},[],{"categories":3006},[],{"categories":3008},[150],{"categories":3010},[],{"categories":3012},[],{"categories":3014},[150],{"categories":3016},[],{"categories":3018},[],{"categories":3020},[],{"categories":3022},[150],{"categories":3024},[119],{"categories":3026},[],{"categories":3028},[],{"categories":3030},[],{"categories":3032},[150],{"categories":3034},[],{"categories":3036},[150],{"categories":3038},[150],{"categories":3040},[],{"categories":3042},[150],{"categories":3044},[133],{"categories":3046},[],{"categories":3048},[165],{"categories":3050},[165],{"categories":3052},[],{"categories":3054},[127],{"categories":3056},[],{"categories":3058},[],{"categories":3060},[],{"categories":3062},[130],{"categories":3064},[119],{"categories":3066},[124],{"categories":3068},[150],{"categories":3070},[114],{"categories":3072},[150],{"categories":3074},[],{"categories":3076},[],{"categories":3078},[114],{"categories":3080},[127],{"categories":3082},[124],{"categories":3084},[],{"categories":3086},[475],{"categories":3088},[],{"categories":3090},[127],{"categories":3092},[150],{"categories":3094},[150],{"categories":3096},[127],{"categories":3098},[150],{"categories":3100},[130],{"categories":3102},[124],{"categories":3104},[150],{"categories":3106},[124],{"categories":3108},[150],{"categories":3110},[124],{"categories":3112},[165],{"categories":3114},[165],{"categories":3116},[130],{"categories":3118},[],{"categories":3120},[150],{"categories":3122},[150],{"categories":3124},[127],{"categories":3126},[562],{"categories":3128},[165],{"categories":3130},[119],{"categories":3132},[150],{"categories":3134},[119],{"categories":3136},[150],{"categories":3138},[150],{"categories":3140},[],{"categories":3142},[150],{"categories":3144},[],{"categories":3146},[150],{"categories":3148},[127],{"categories":3150},[150],{"categories":3152},[150],{"categories":3154},[150],{"categories":3156},[],{"categories":3158},[150],{"categories":3160},[150],{"categories":3162},[562],{"categories":3164},[],{"categories":3166},[119],{"categories":3168},[475],{"categories":3170},[133],{"categories":3172},[],{"categories":3174},[210],{"categories":3176},[],{"categories":3178},[],{"categories":3180},[119],{"categories":3182},[150],{"categories":3184},[],{"categories":3186},[150],{"categories":3188},[150],{"categories":3190},[124],{"categories":3192},[150],{"categories":3194},[119],{"categories":3196},[119],{"categories":3198},[130],{"categories":3200},[130],{"categories":3202},[130],{"categories":3204},[150],{"categories":3206},[210],{"categories":3208},[119],{"categories":3210},[165],{"categories":3212},[],{"categories":3214},[130],{"categories":3216},[130],{"categories":3218},[475],{"categories":3220},[130],{"categories":3222},[130],{"categories":3224},[124],{"categories":3226},[119],{"categories":3228},[475],{"categories":3230},[150],{"categories":3232},[150],{"categories":3234},[150],{"categories":3236},[150],{"categories":3238},[],{"categories":3240},[124],{"categories":3242},[150],{"categories":3244},[130],{"categories":3246},[],{"categories":3248},[],{"categories":3250},[119],{"categories":3252},[],{"categories":3254},[124],{"categories":3256},[124],{"categories":3258},[124],{"categories":3260},[124],{"categories":3262},[124],{"categories":3264},[124],{"categories":3266},[124],{"categories":3268},[124],{"categories":3270},[],{"categories":3272},[],{"categories":3274},[150],{"categories":3276},[],{"categories":3278},[124],{"categories":3280},[165],{"categories":3282},[165],{"categories":3284},[210],{"categories":3286},[114],{"categories":3288},[],{"categories":3290},[],{"categories":3292},[],{"categories":3294},[130],{"categories":3296},[150],{"categories":3298},[],{"categories":3300},[114],{"categories":3302},[114],{"categories":3304},[130],{"categories":3306},[165],{"categories":3308},[210],{"categories":3310},[130],{"categories":3312},[130],{"categories":3314},[],{"categories":3316},[124],{"categories":3318},[114],{"categories":3320},[114],{"categories":3322},[150],{"categories":3324},[124],{"categories":3326},[133],{"categories":3328},[130],{"categories":3330},[],{"categories":3332},[127],{"categories":3334},[210],{"categories":3336},[119],{"categories":3338},[119],{"categories":3340},[119],{"categories":3342},[475],{"categories":3344},[],{"categories":3346},[124],{"categories":3348},[],{"categories":3350},[124],{"categories":3352},[124],{"categories":3354},[150],{"categories":3356},[150],{"categories":3358},[133],{"categories":3360},[124],{"categories":3362},[133],{"categories":3364},[],{"categories":3366},[124],{"categories":3368},[130],{"categories":3370},[130],{"categories":3372},[130],{"categories":3374},[150],{"categories":3376},[124],{"categories":3378},[150],{"categories":3380},[114],{"categories":3382},[119],{"categories":3384},[130],{"categories":3386},[119],{"categories":3388},[150],{"categories":3390},[],{"categories":3392},[119],{"categories":3394},[124],{"categories":3396},[119],{"categories":3398},[119],{"categories":3400},[119],{"categories":3402},[119],{"categories":3404},[],{"categories":3406},[],{"categories":3408},[119],{"categories":3410},[119],{"categories":3412},[],{"categories":3414},[119],{"categories":3416},[119],{"categories":3418},[150],{"categories":3420},[150],{"categories":3422},[119],{"categories":3424},[119],{"categories":3426},[150],{"categories":3428},[],{"categories":3430},[150],{"categories":3432},[124],{"categories":3434},[150],{"categories":3436},[150],{"categories":3438},[],{"categories":3440},[150],{"categories":3442},[150],{"categories":3444},[150],{"categories":3446},[119],{"categories":3448},[],{"categories":3450},[],{"categories":3452},[],{"categories":3454},[],{"categories":3456},[150],{"categories":3458},[150],{"categories":3460},[],{"categories":3462},[127],{"categories":3464},[119],{"categories":3466},[],{"categories":3468},[],{"categories":3470},[],{"categories":3472},[],{"categories":3474},[],{"categories":3476},[150],{"categories":3478},[],{"categories":3480},[],{"categories":3482},[150],{"categories":3484},[],{"categories":3486},[124],{"categories":3488},[124],{"categories":3490},[124],{"categories":3492},[114],{"categories":3494},[],{"categories":3496},[127],{"categories":3498},[133],{"categories":3500},[133],{"categories":3502},[475],{"categories":3504},[119],{"categories":3506},[],{"categories":3508},[150],{"categories":3510},[150],{"categories":3512},[114],{"categories":3514},[],{"categories":3516},[114],{"categories":3518},[],{"categories":3520},[],{"categories":3522},[],{"categories":3524},[133],{"categories":3526},[124],{"categories":3528},[124],{"categories":3530},[124],{"categories":3532},[124],{"categories":3534},[124],{"categories":3536},[],{"categories":3538},[119],{"categories":3540},[150],{"categories":3542},[150],{"categories":3544},[150],{"categories":3546},[],{"categories":3548},[114],{"categories":3550},[],{"categories":3552},[130],{"categories":3554},[210],{"categories":3556},[130],{"categories":3558},[],{"categories":3560},[],{"categories":3562},[150],{"categories":3564},[124],{"categories":3566},[],{"categories":3568},[150],{"categories":3570},[150],{"categories":3572},[150],{"categories":3574},[124],{"categories":3576},[124],{"categories":3578},[150],{"categories":3580},[210],{"categories":3582},[124],{"categories":3584},[],{"categories":3586},[150],{"categories":3588},[],{"categories":3590},[562],{"categories":3592},[133],{"categories":3594},[210],{"categories":3596},[133],{"categories":3598},[475],{"categories":3600},[150],{"categories":3602},[133],{"categories":3604},[119],{"categories":3606},[475],{"categories":3608},[133],{"categories":3610},[130],{"categories":3612},[130],{"categories":3614},[],{"categories":3616},[133],{"categories":3618},[],{"categories":3620},[165],{"categories":3622},[133],{"categories":3624},[],{"categories":3626},[210],{"categories":3628},[210],{"categories":3630},[562],{"categories":3632},[],{"categories":3634},[150],{"categories":3636},[133],{"categories":3638},[475],{"categories":3640},[124],{"categories":3642},[124],{"categories":3644},[210],{"categories":3646},[150],{"categories":3648},[165],{"categories":3650},[150],{"categories":3652},[],{"categories":3654},[],{"categories":3656},[],{"categories":3658},[127],{"categories":3660},[150],{"categories":3662},[130],{"categories":3664},[133],{"categories":3666},[133],{"categories":3668},[150],{"categories":3670},[127],{"categories":3672},[165],{"categories":3674},[150],{"categories":3676},[133],{"categories":3678},[150],{"categories":3680},[133],{"categories":3682},[165],{"categories":3684},[165],{"categories":3686},[124],{"categories":3688},[165],{"categories":3690},[133],{"categories":3692},[114],{"categories":3694},[133],{"categories":3696},[133],{"categories":3698},[133],{"categories":3700},[133],{"categories":3702},[],{"categories":3704},[119],{"categories":3706},[],{"categories":3708},[210],{"categories":3710},[150],{"categories":3712},[150],{"categories":3714},[],{"categories":3716},[],{"categories":3718},[],{"categories":3720},[150],{"categories":3722},[119],{"categories":3724},[150],{"categories":3726},[150],{"categories":3728},[],{"categories":3730},[150],{"categories":3732},[130],{"categories":3734},[150],{"categories":3736},[150],{"categories":3738},[150],{"categories":3740},[],{"categories":3742},[],{"categories":3744},[],{"categories":3746},[475],{"categories":3748},[475],{"categories":3750},[114],{"categories":3752},[124],{"categories":3754},[114,127],{"categories":3756},[150],{"categories":3758},[119],{"categories":3760},[],{"categories":3762},[130],{"categories":3764},[210],{"categories":3766},[150],{"categories":3768},[133],{"categories":3770},[150],{"categories":3772},[],{"categories":3774},[210],{"categories":3776},[475],{"categories":3778},[124],{"categories":3780},[114],{"categories":3782},[475],{"categories":3784},[124],{"categories":3786},[165],{"categories":3788},[124],{"categories":3790},[165],{"categories":3792},[150],{"categories":3794},[165],{"categories":3796},[165],{"categories":3798},[133],{"categories":3800},[210],{"categories":3802},[150],{"categories":3804},[127],{"categories":3806},[],{"categories":3808},[150],{"categories":3810},[130],{"categories":3812},[210],{"categories":3814},[114],{"categories":3816},[150],{"categories":3818},[210],{"categories":3820},[165],{"categories":3822},[150],{"categories":3824},[150],{"categories":3826},[210],{"categories":3828},[150],{"categories":3830},[165],{"categories":3832},[150],{"categories":3834},[],{"categories":3836},[150],{"categories":3838},[150],{"categories":3840},[150],{"categories":3842},[150],{"categories":3844},[],{"categories":3846},[124],{"categories":3848},[475],{"categories":3850},[],{"categories":3852},[],{"categories":3854},[150],{"categories":3856},[114],{"categories":3858},[127],{"categories":3860},[114],{"categories":3862},[114],{"categories":3864},[124],{"categories":3866},[],{"categories":3868},[150],{"categories":3870},[119],{"categories":3872},[150],{"categories":3874},[150],{"categories":3876},[],{"categories":3878},[124],{"categories":3880},[119],{"categories":3882},[150,475],{"categories":3884},[124,475],{"categories":3886},[475],{"categories":3888},[150],{"categories":3890},[124],{"categories":3892},[124],{"categories":3894},[133],{"categories":3896},[133],{"categories":3898},[133],{"categories":3900},[150],{"categories":3902},[130],{"categories":3904},[124],{"categories":3906},[],{"categories":3908},[475],{"categories":3910},[],{"categories":3912},[475],{"categories":3914},[475],{"categories":3916},[114],{"categories":3918},[124],{"categories":3920},[],{"categories":3922},[475],{"categories":3924},[150],{"categories":3926},[119],{"categories":3928},[150],{"categories":3930},[130],{"categories":3932},[133],{"categories":3934},[133],{"categories":3936},[133],{"categories":3938},[475],{"categories":3940},[],{"categories":3942},[],{"categories":3944},[],{"categories":3946},[150],{"categories":3948},[133],{"categories":3950},[150],{"categories":3952},[133],{"categories":3954},[475],{"categories":3956},[475],{"categories":3958},[150],{"categories":3960},[124],{"categories":3962},[],{"categories":3964},[150],{"categories":3966},[150],{"categories":3968},[150],{"categories":3970},[],{"categories":3972},[],{"categories":3974},[475],{"categories":3976},[475],{"categories":3978},[150,475],{"categories":3980},[124],{"categories":3982},[124],{"categories":3984},[124],{"categories":3986},[124],{"categories":3988},[124],{"categories":3990},[124],{"categories":3992},[],{"categories":3994},[133],{"categories":3996},[150],{"categories":3998},[133],{"categories":4000},[127],{"categories":4002},[150],{"categories":4004},[562],{"categories":4006},[562],{"categories":4008},[124],{"categories":4010},[133],{"categories":4012},[],{"categories":4014},[124],{"categories":4016},[150],{"categories":4018},[],{"categories":4020},[130],{"categories":4022},[],{"categories":4024},[150],{"categories":4026},[124],{"categories":4028},[119],{"categories":4030},[150],{"categories":4032},[],{"categories":4034},[],{"categories":4036},[130],{"categories":4038},[130],{"categories":4040},[165],{"categories":4042},[130],{"categories":4044},[124],{"categories":4046},[],{"categories":4048},[124],{"categories":4050},[119],{"categories":4052},[150],{"categories":4054},[150],{"categories":4056},[],{"categories":4058},[150],{"categories":4060},[165],{"categories":4062},[150],{"categories":4064},[],{"categories":4066},[210],{"categories":4068},[133],{"categories":4070},[133],{"categories":4072},[114],{"categories":4074},[114],{"categories":4076},[114],{"categories":4078},[124],{"categories":4080},[114],{"categories":4082},[124],{"categories":4084},[475],{"categories":4086},[562],{"categories":4088},[119],{"categories":4090},[119],{"categories":4092},[119],{"categories":4094},[475],{"categories":4096},[119,114],{"categories":4098},[210],{"categories":4100},[124],{"categories":4102},[],{"categories":4104},[150],{"categories":4106},[],{"categories":4108},[133],{"categories":4110},[210],{"categories":4112},[130],{"categories":4114},[133],{"categories":4116},[165],{"categories":4118},[],{"categories":4120},[124],{"categories":4122},[],{"categories":4124},[562],{"categories":4126},[],{"categories":4128},[130],{"categories":4130},[130],{"categories":4132},[210],{"categories":4134},[],{"categories":4136},[150],{"categories":4138},[210],{"categories":4140},[],{"categories":4142},[150],{"categories":4144},[150],{"categories":4146},[],{"categories":4148},[165],{"categories":4150},[150],{"categories":4152},[],{"categories":4154},[150],{"categories":4156},[],{"categories":4158},[],{"categories":4160},[124],{"categories":4162},[124],{"categories":4164},[],{"categories":4166},[133],{"categories":4168},[133],{"categories":4170},[133],{"categories":4172},[150,124],{"categories":4174},[124],{"categories":4176},[124],{"categories":4178},[124],{"categories":4180},[210],{"categories":4182},[210],{"categories":4184},[],{"categories":4186},[119],{"categories":4188},[150],{"categories":4190},[210],{"categories":4192},[210],{"categories":4194},[119],{"categories":4196},[114],{"categories":4198},[124],{"categories":4200},[133],{"categories":4202},[150],{"categories":4204},[150],{"categories":4206},[124],{"categories":4208},[133],{"categories":4210},[124],{"categories":4212},[150],{"categories":4214},[127],{"categories":4216},[],{"categories":4218},[150],{"categories":4220},[],{"categories":4222},[150],{"categories":4224},[150],{"categories":4226},[133],{"categories":4228},[],{"categories":4230},[210],{"categories":4232},[150],{"categories":4234},[124],{"categories":4236},[124],{"categories":4238},[133],{"categories":4240},[165],{"categories":4242},[165],{"categories":4244},[119],{"categories":4246},[150],{"categories":4248},[124],{"categories":4250},[],{"categories":4252},[124],{"categories":4254},[150],{"categories":4256},[119],{"categories":4258},[150],{"categories":4260},[150],{"categories":4262},[150],{"categories":4264},[124],{"categories":4266},[210],{"categories":4268},[150],{"categories":4270},[130],{"categories":4272},[150],{"categories":4274},[150],{"categories":4276},[150],{"categories":4278},[150],{"categories":4280},[],{"categories":4282},[150],{"categories":4284},[210],{"categories":4286},[130],{"categories":4288},[150],{"categories":4290},[130],{"categories":4292},[],{"categories":4294},[],{"categories":4296},[],{"categories":4298},[150],{"categories":4300},[],{"categories":4302},[],{"categories":4304},[],{"categories":4306},[],{"categories":4308},[124],{"categories":4310},[165],{"categories":4312},[124],{"categories":4314},[124],{"categories":4316},[133],{"categories":4318},[114],{"categories":4320},[150],{"categories":4322},[150],{"categories":4324},[150],{"categories":4326},[114],{"categories":4328},[165],{"categories":4330},[],{"categories":4332},[210],{"categories":4334},[127],{"categories":4336},[150],{"categories":4338},[130],{"categories":4340},[165],{"categories":4342},[165],{"categories":4344},[562],{"categories":4346},[124],{"categories":4348},[150],{"categories":4350},[150],{"categories":4352},[165],{"categories":4354},[150],{"categories":4356},[],{"categories":4358},[],{"categories":4360},[475],{"categories":4362},[130],{"categories":4364},[165],{"categories":4366},[150],{"categories":4368},[119],{"categories":4370},[165],{"categories":4372},[114],{"categories":4374},[124],{"categories":4376},[124],{"categories":4378},[119],{"categories":4380},[150],{"categories":4382},[],{"categories":4384},[],{"categories":4386},[],{"categories":4388},[150],{"categories":4390},[],{"categories":4392},[119],{"categories":4394},[],{"categories":4396},[150],{"categories":4398},[],{"categories":4400},[119],{"categories":4402},[124],{"categories":4404},[150],{"categories":4406},[475],{"categories":4408},[150],{"categories":4410},[165],{"categories":4412},[150],{"categories":4414},[165],{"categories":4416},[165],{"categories":4418},[],{"categories":4420},[],{"categories":4422},[165],{"categories":4424},[165],{"categories":4426},[165],{"categories":4428},[],{"categories":4430},[165],{"categories":4432},[124],{"categories":4434},[124],{"categories":4436},[],{"categories":4438},[150],{"categories":4440},[127],{"categories":4442},[210],{"categories":4444},[150],{"categories":4446},[],{"categories":4448},[165],{"categories":4450},[150],{"categories":4452},[562],{"categories":4454},[165],{"categories":4456},[165],{"categories":4458},[127],{"categories":4460},[133],{"categories":4462},[133],{"categories":4464},[],{"categories":4466},[133],{"categories":4468},[150],{"categories":4470},[],{"categories":4472},[],{"categories":4474},[124],{"categories":4476},[],{"categories":4478},[124],{"categories":4480},[124],{"categories":4482},[119],{"categories":4484},[150],{"categories":4486},[119],{"categories":4488},[165],{"categories":4490},[119],{"categories":4492},[133],{"categories":4494},[133],{"categories":4496},[133],{"categories":4498},[119],{"categories":4500},[150],{"categories":4502},[124],{"categories":4504},[475],{"categories":4506},[114],{"categories":4508},[475],{"categories":4510},[475],{"categories":4512},[133],{"categories":4514},[475],{"categories":4516},[475],[4518,4750,4838,4923],{"id":4519,"title":4520,"ai":4521,"body":4526,"categories":4713,"created_at":87,"date_modified":87,"description":79,"extension":89,"faq":87,"featured":90,"kicker_label":87,"meta":4714,"navigation":92,"path":4737,"published_at":4738,"question":87,"scraped_at":4739,"seo":4740,"sitemap":4741,"source_id":4742,"source_name":99,"source_type":4743,"source_url":4744,"stem":4745,"tags":4746,"thumbnail_url":87,"tldr":4747,"tweet":87,"unknown_tags":4748,"__hash__":4749},"summaries\u002Fsummaries\u002Ftiny-llms-and-on-device-agents-via-litert-lm-on-ed-summary.md","Tiny LLMs and On-Device Agents via LiteRT-LM on Edge Hardware",{"provider":7,"model":8,"input_tokens":4522,"output_tokens":4523,"processing_time_ms":4524,"cost_usd":4525},8771,2602,22997,0.0030327,{"type":14,"value":4527,"toc":4705},[4528,4532,4535,4538,4541,4545,4552,4558,4561,4569,4573,4576,4579,4646,4649,4652,4656,4659,4662,4665,4669,4672,4675,4679],[17,4529,4531],{"id":4530},"edge-ai-benefits-drive-on-device-llms","Edge AI Benefits Drive On-Device LLMs",[22,4533,4534],{},"Running LLMs on edge devices solves key constraints: ultra-low latency for in-loop UX like live voice translation (impossible via cloud), full privacy in messaging apps, offline capability, and cost savings on laptops. Cormac Brick, Google AI Edge tech lead, emphasizes these over cloud alternatives, drawing from 10 years optimizing hardware from Raspberry Pi to NPUs. Tradeoffs include RAM limits (e.g., 2-4GB for viable models) and hardware variability, pushing optimizations like memory-mapped per-layer embeddings to keep effective params low.",[22,4536,4537],{},"\"There's a lot of benefits to running on the edge. There's latency or UX improvements for some really sensitive in-the-loop things like live voice translation.\" — Cormac Brick, highlighting why Pixel's on-device translation beats cloud latency.",[22,4539,4540],{},"Google's stack—LiteRT (ex-TensorFlow Lite), MediaPipe, LiteRT-LM—ships in Photos, YouTube Shorts effects, and Android system services. One .tflite file deploys cross-platform (Android\u002FiOS\u002FMac\u002FLinux\u002FWindows\u002FWeb\u002FIoT) on CPU\u002FGPU; NPUs need separate compilation. This enables broad reach beyond premium devices.",[17,4542,4544],{"id":4543},"system-genai-vs-in-app-tiny-llms-deployment-patterns","System GenAI vs. In-App Tiny LLMs: Deployment Patterns",[22,4546,4547,4548,4551],{},"Two trends emerge: ",[39,4549,4550],{},"system-level GenAI"," integrates 2-5B param models into OS (Android AI Core, Apple Intelligence) for broad APIs like summarization\u002Fprompting, pre-loaded on premium devices. Customization via prompting or skills; no app downloads needed.",[22,4553,4554,4557],{},[39,4555,4556],{},"In-app GenAI"," uses tiny LLMs (TLMs, 100-500M params) bundled with apps\u002Fwebpages for wider device compatibility. Fine-tuning is essential below 500M params for production reliability on tasks like summarization, transcription, voice-to-function (e.g., Function Gemma at 270M params hits 85-90% on 10 Android functions). Prompting alone fails for tiny models; fine-tuning yields \"really reliable performance.\"",[22,4559,4560],{},"Decision chain: System for foundation tasks (leverage OS investment); in-app for custom, task-specific reliability. Tradeoff: System limits to premium hardware; tiny models sacrifice generality but gain deployability.",[22,4562,4563,4564,4568],{},"\"For the really really tiny models certainly less than 500 ",[4565,4566,4567],"span",{},"million parameters"," you need to fine-tune to get production level reliability.\" — Brick on why prompting isn't enough for edge-scale models.",[17,4570,4572],{"id":4571},"gemma-2b4b-edge-optimized-for-agents-and-multimodality","Gemma 2B\u002F4B: Edge-Optimized for Agents and Multimodality",[22,4574,4575],{},"Gemma 2 (E2B: 2B effective params; E4B: 4B) targets edge with RAM efficiency via partial embedding loads (hundreds of bytes per token). Multimodal (audio\u002Fimage\u002Ftext for small sizes); built-in function calling + thinking unlocks on-device agents. Apache 2.0 license broadens use.",[22,4577,4578],{},"Performance (snapshot, ongoing optimizations with Qualcomm\u002FIntel\u002FRaspberry Pi):",[4580,4581,4582,4598],"table",{},[4583,4584,4585],"thead",{},[4586,4587,4588,4592,4595],"tr",{},[4589,4590,4591],"th",{},"Device",[4589,4593,4594],{},"Gemma 2B Prefill\u002FDecode (tok\u002Fs)",[4589,4596,4597],{},"Gemma 4B Prefill\u002FDecode (tok\u002Fs)",[4599,4600,4601,4613,4624,4635],"tbody",{},[4586,4602,4603,4607,4610],{},[4604,4605,4606],"td",{},"High-end Android (GPU)",[4604,4608,4609],{},"2000+\u002F1000+",[4604,4611,4612],{},"~half",[4586,4614,4615,4618,4621],{},[4604,4616,4617],{},"MacBook",[4604,4619,4620],{},"1000s",[4604,4622,4623],{},"Proportional",[4586,4625,4626,4629,4632],{},[4604,4627,4628],{},"Raspberry Pi 5",[4604,4630,4631],{},"20\u002F133",[4604,4633,4634],{},"N\u002FA",[4586,4636,4637,4640,4643],{},[4604,4638,4639],{},"Qualcomm IoT NPU",[4604,4641,4642],{},"High (NPU boost)",[4604,4644,4645],{},"High",[22,4647,4648],{},"E2B\u002F4B on AI Core roadmap for Android integration. Larger Gemma for laptops (32GB RAM).",[22,4650,4651],{},"\"One of the big step ups... was they've kind of built in function calling which is excellent and they also have built-in thinking. So that combination... unlocks our ability to now do skills on device.\" — Brick on Gemma's agent enablers.",[17,4653,4655],{"id":4654},"progressive-skills-token-efficient-on-device-agents","Progressive Skills: Token-Efficient On-Device Agents",[22,4657,4658],{},"Google AI Gallery app demos agent skills: mood journaling (log\u002Fanalyze trends via voice), calendar checks, Wikipedia queries, music synthesis from images. No fine-tuning; skills as on-demand JS snippets with one-line descriptions.",[22,4660,4661],{},"Mechanism: Progressive disclosure—model sees skill summaries first, loads details (functions) only if relevant via a \"load skill\" meta-function. Cuts context bloat, boosts reliability on lightweight models (poor at long contexts). Patterns: knowledge augmentation (Wikipedia), interactive UI (flashcards), web services (weather\u002Fmaps\u002Fmusic).",[22,4663,4664],{},"\"The way we've built the skills is there's a kind of one-line description... if it thinks that sounds interesting, then it asks for more... This is particularly important for token efficiency and frankly reliability on edge models.\" — Brick explaining conditional depth over full MCP descriptions.",[17,4666,4668],{"id":4667},"tiny-model-workflow-fine-tune-and-deploy","Tiny Model Workflow: Fine-Tune and Deploy",[22,4670,4671],{},"For TLMs: Fine-tune Gemma-based models (e.g., 100-500M) on task data, quantize, deploy via LiteRT-LM. Example app (team-built): Real-world tiny LLM use, voice-to-action. Cross-platform speed via hardware accel (GPU\u002FNPU).",[22,4673,4674],{},"Tradeoffs: Tiny = task-specific excellence but no generality; needs fine-tuning. Results: Voice-to-function at 85-90% on small models, deployable everywhere.",[17,4676,4678],{"id":4677},"key-takeaways","Key Takeaways",[33,4680,4681,4684,4687,4690,4693,4696,4699,4702],{},[36,4682,4683],{},"Prioritize edge for latency\u002Fprivacy\u002Foffline\u002Fcost; use LiteRT-LM for cross-platform .tflite deployment (CPU\u002FGPU standard, NPU compiled).",[36,4685,4686],{},"Choose system GenAI (2-5B params via OS APIs) for foundation tasks on premium devices; in-app TLMs (100-500M) for custom tasks with fine-tuning.",[36,4688,4689],{},"Gemma 2B\u002F4B: 2-4GB RAM effective, multimodal, agent-ready; expect 100-2000+ tok\u002Fs depending on hardware.",[36,4691,4692],{},"Build skills progressively: One-line summaries → on-demand JS loads for token efficiency and dynamic tools.",[36,4694,4695],{},"Fine-tune tiny models below 500M params for 85-90% reliability on voice\u002Faction tasks; avoid prompting alone.",[36,4697,4698],{},"Optimize embeddings (memory-map PLE) to fit RAM constraints; track partners like Qualcomm for NPU gains.",[36,4700,4701],{},"Test on real hardware: Raspberry Pi 133 tok\u002Fs decode viable for simple analysis; high-end phones hit production speeds.",[36,4703,4704],{},"Extend models low-code: Wikipedia\u002Fmaps\u002Fmusic skills turn static LLMs into fresh-knowledge agents.",{"title":79,"searchDepth":80,"depth":80,"links":4706},[4707,4708,4709,4710,4711,4712],{"id":4530,"depth":80,"text":4531},{"id":4543,"depth":80,"text":4544},{"id":4571,"depth":80,"text":4572},{"id":4654,"depth":80,"text":4655},{"id":4667,"depth":80,"text":4668},{"id":4677,"depth":80,"text":4678},[150],{"content_references":4715,"triage":4732},[4716,4720,4722,4724,4727,4729],{"type":4717,"title":4718,"context":4719},"tool","LiteRT-LM","mentioned",{"type":4717,"title":4721,"context":4719},"MediaPipe",{"type":4717,"title":4723,"context":4719},"LiteRT",{"type":4717,"title":4725,"author":4726,"context":4719},"Gemma 2B","Google DeepMind",{"type":4717,"title":4728,"context":4719},"Google AI Gallery",{"type":4730,"title":4731,"context":4719},"event","NeurIPS 2016",{"relevance":4733,"novelty":4734,"quality":4734,"actionability":4734,"composite":4735,"reasoning":4736},5,4,4.35,"Category: AI & LLMs. The article discusses the practical implementation of LLMs on edge devices, addressing specific pain points like latency and privacy, which are crucial for product builders. It provides insights into deployment patterns and performance metrics that can guide developers in choosing the right model for their applications.","\u002Fsummaries\u002Ftiny-llms-and-on-device-agents-via-litert-lm-on-ed-summary","2026-05-03 22:00:06","2026-05-04 16:07:29",{"title":4520,"description":79},{"loc":4737},"916b0f9e88910f87","article","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BKWpYIWvAo4","summaries\u002Ftiny-llms-and-on-device-agents-via-litert-lm-on-ed-summary",[104,105,106,107],"LiteRT-LM runs Gemma 2B\u002F4B models at 1000+ tokens\u002Fsec on phones and delivers agent skills with function calling, while tiny 100-500M param models excel in fine-tuned in-app tasks like voice-to-action at 85-90% reliability.",[],"2thNTMamJ6HZicvDpyj21esgWMIloh446Bkq8a870lY",{"id":4751,"title":4752,"ai":4753,"body":4758,"categories":4804,"created_at":87,"date_modified":87,"description":79,"extension":89,"faq":87,"featured":90,"kicker_label":87,"meta":4805,"navigation":92,"path":4825,"published_at":4826,"question":87,"scraped_at":4827,"seo":4828,"sitemap":4829,"source_id":4830,"source_name":4831,"source_type":4743,"source_url":4832,"stem":4833,"tags":4834,"thumbnail_url":87,"tldr":4835,"tweet":87,"unknown_tags":4836,"__hash__":4837},"summaries\u002Fsummaries\u002Fgemma-chat-offline-vibe-coding-with-gemma-4-on-mac-summary.md","Gemma Chat: Offline Vibe Coding with Gemma 4 on Mac",{"provider":7,"model":8,"input_tokens":4754,"output_tokens":4755,"processing_time_ms":4756,"cost_usd":4757},6334,1865,16673,0.0021768,{"type":14,"value":4759,"toc":4799},[4760,4764,4767,4770,4774,4777,4780,4784,4796],[17,4761,4763],{"id":4762},"build-and-iterate-small-apps-offline-with-privacy","Build and Iterate Small Apps Offline with Privacy",[22,4765,4766],{},"Use Gemma Chat's Build Mode to prompt Gemma 4 for small web apps like landing pages, Pomodoro timers, dashboards, or games (e.g., Chrome Dino clone with keyboard controls). The agent creates, edits, reads files in a sandbox workspace, runs bash commands, and updates a live preview in real-time—even streaming partial file writes every few hundred milliseconds for a dynamic build experience. Switch to Chat Mode for general assistance with tools like calculations, web search, or URL fetching (online only). Voice input via local Whisper speech-to-text in the browser keeps everything on-device, ensuring prompts, code, and files stay private without cloud transmission.",[22,4768,4769],{},"This local-first setup trades cloud model power for zero API costs and full control: download models once (e.g., 3GB E4B recommended for balanced speed\u002Fcapability), then work offline on planes or private prototypes. Smaller E2B suits 8GB Macs for speed; larger MoE or 31B dense models leverage 16-32GB RAM for better reasoning on complex tasks.",[17,4771,4773],{"id":4772},"xml-tool-protocol-boosts-reliability-on-local-models","XML Tool Protocol Boosts Reliability on Local Models",[22,4775,4776],{},"Gemma Chat uses a simple XML-style protocol for tools (write file, edit file, read file, list files, run bash, open preview) instead of JSON function calling, which smaller local models handle more reliably. An MLX server streams model output to the Electron app interface, enabling agent loops where the model observes results and iterates. This powers vibe coding workflows similar to Bolt or Replit AI builders but fully local via Apple's MLX framework on Apple Silicon.",[22,4778,4779],{},"Google's Gemma 4 excels here due to its focus on agentic workflows, code generation, and local deployment—positioned by DeepMind as their strongest open family yet. Backed by Google AI Studio's Ammar Reshi (MIT-licensed repo) and promoted by the official Gemma account, it demonstrates practical local AI without benchmarks, highlighting open models' maturity for developer tools.",[17,4781,4783],{"id":4782},"setup-trade-offs-and-realistic-use-cases","Setup Trade-offs and Realistic Use Cases",[22,4785,4786,4787,4791,4792,4795],{},"Clone the GitHub repo, run ",[4788,4789,4790],"code",{},"npm install"," (Node 20+), and ",[4788,4793,4794],{},"npm run dev"," (Python required); first launch downloads models and MLX. Build a DMG for distribution. Limitations include Mac-only (MLX dependency), initial internet for downloads, slower inference than cloud (e.g., Cursor\u002FClaude), and no full SaaS apps—ideal for prototypes, demos, student projects, or quick experiments where privacy or offline access matters.",[22,4797,4798],{},"Pay with hardware, not subscriptions: on Apple Silicon Macs, it replaces API bills for toy apps, letting you iterate button changes endlessly without credits. Not for production refactoring, but proves local agents are viable for real workflows, pushing open AI toward usable, permissionless coding environments.",{"title":79,"searchDepth":80,"depth":80,"links":4800},[4801,4802,4803],{"id":4762,"depth":80,"text":4763},{"id":4772,"depth":80,"text":4773},{"id":4782,"depth":80,"text":4783},[150],{"content_references":4806,"triage":4821},[4807,4811,4814,4817,4819],{"type":4717,"title":4808,"author":4809,"context":4810},"Gemma Chat","Ammar Reshi","recommended",{"type":4717,"title":4812,"author":4813,"context":4719},"MLX","Apple",{"type":4815,"title":4816,"author":4726,"context":4719},"other","Gemma 4",{"type":4717,"title":4818,"context":4719},"MLX-LM",{"type":4717,"title":4820,"context":4719},"Whisper",{"relevance":4734,"novelty":4822,"quality":4734,"actionability":4734,"composite":4823,"reasoning":4824},3,3.8,"Category: AI & LLMs. The article discusses using Gemma Chat for building AI-powered applications offline, addressing the audience's need for practical applications of AI tools. It provides specific examples of app types that can be built and details on the local setup, which enhances its actionability.","\u002Fsummaries\u002Fgemma-chat-offline-vibe-coding-with-gemma-4-on-mac-summary","2026-04-30 11:26:57","2026-05-03 16:50:27",{"title":4752,"description":79},{"loc":4825},"6511d28fd46031d0","AICodeKing","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=KnrdxmsZEqA","summaries\u002Fgemma-chat-offline-vibe-coding-with-gemma-4-on-mac-summary",[104,106,107,105],"Gemma Chat runs Google's Gemma 4 locally on Apple Silicon Macs via MLX for private, offline app building with live previews, file editing, and agentic tools—no API keys or subscriptions needed.",[],"q6h-hwK6_2MFPVSekNtU_5JXhjdzwf3ICkrFNE7W7gg",{"id":4839,"title":4840,"ai":4841,"body":4846,"categories":4887,"created_at":87,"date_modified":87,"description":79,"extension":89,"faq":87,"featured":90,"kicker_label":87,"meta":4888,"navigation":92,"path":4911,"published_at":4912,"question":87,"scraped_at":4913,"seo":4914,"sitemap":4915,"source_id":4916,"source_name":99,"source_type":4743,"source_url":4917,"stem":4918,"tags":4919,"thumbnail_url":87,"tldr":4920,"tweet":87,"unknown_tags":4921,"__hash__":4922},"summaries\u002Fsummaries\u002Fgemma-4-open-models-running-agents-on-phones-summary.md","Gemma 4: Open Models Running Agents on Phones",{"provider":7,"model":8,"input_tokens":4842,"output_tokens":4843,"processing_time_ms":4844,"cost_usd":4845},6735,1939,15707,0.002294,{"type":14,"value":4847,"toc":4882},[4848,4852,4855,4858,4862,4869,4873,4876,4879],[17,4849,4851],{"id":4850},"deploy-gemma-4-on-device-for-offline-agents-and-coding","Deploy Gemma 4 On-Device for Offline Agents and Coding",[22,4853,4854],{},"Gemma 4 family spans 2B to 32B parameters, all fitting consumer GPUs or smaller devices like Android phones, iPhones, Raspberry Pi, laptops, even Nintendo Switch via llama.cpp. Smallest 2B\u002F4B E2B models enable fully offline agentic apps: select skills like piano playing (generates MIDI), SVG generation (10 parallel instances at 100 tokens\u002Fsec produce unique SVGs), or Android app coding—all in airplane mode, no APIs. Larger 27B MoE delivers low-latency inference; 31B maximizes raw intelligence. On LM Arena, Gemma 4 punches above weight in top-left quadrant: small size, high community-rated conversational\u002Fhelpful performance, outperforming bigger closed models. Trade-off: Use for on-device privacy\u002Flow-latency; scale to APIs like Gemini for peak intelligence.",[22,4856,4857],{},"Progress from Gemma 1\u002F2\u002F3 shows capability gains without parameter bloat—exciting trajectory for pocket superintelligence in 1-2 years.",[17,4859,4861],{"id":4860},"e2b-architecture-slashes-on-device-memory-needs","E2B Architecture Slashes On-Device Memory Needs",[22,4863,4864,4865,4868],{},"E2B (effectively 2B params) uses per-layer embeddings: 4B total params but loads only 2B to GPU; rest as CPU\u002Fdisk lookup tables, skipping matrix multiplies. Activate with llama.cpp flag ",[4788,4866,4867],{},"--override-tensor"," to offload embeddings. Result: 5B model runs like 2B on mobile, optimized for latency-critical apps. Apache 2.0 license now allows full commercial flexibility, unlike prior versions.",[17,4870,4872],{"id":4871},"multimodal-multilingual-fine-tuning-ecosystem","Multimodal, Multilingual Fine-Tuning Ecosystem",[22,4874,4875],{},"All models handle images\u002Fvideos\u002Faudio: speech-to-text translation (Spanish to French), object detection\u002Fpointing (e.g., locate llama in image), Japanese text explanation. Trained on 140+ languages with Gemini tokenizer—low-resource fine-tunes (Quechua, Indian languages) work out-of-box due to tokenization. Post-release stats: 10M base model downloads in 1 week, 500M Gemma family total, 1k+ community fine-tunes\u002Fquantizations, 100k+ total models on Hugging Face.",[22,4877,4878],{},"Official variants: ShieldGemma (safety filtering toxic inputs), Med-Gemini (radiology\u002FX-ray on Gemma 3 base). Community: AI Singapore (SE Asian languages), Sarvam (Indian sovereign AI). DeepMind paper (Dec 2023) used Gemma 3 for validated cancer therapy pathways in labs. Integrations: Android Studio offline agent for code gen (trained on Android data), Chrome extensions, finance\u002Flegal offline review.",[22,4880,4881],{},"Collaborate via Unsloth\u002FMLX\u002Fllama.cpp\u002FHugging Face\u002FvLLM—C\u002FKeras agnostic. Recommendation: Spend 1 hour testing latest open models for on-device tasks; customize with your data for agents that rival APIs in niche scenarios.",{"title":79,"searchDepth":80,"depth":80,"links":4883},[4884,4885,4886],{"id":4850,"depth":80,"text":4851},{"id":4860,"depth":80,"text":4861},{"id":4871,"depth":80,"text":4872},[150],{"content_references":4889,"triage":4909},[4890,4892,4894,4896,4897,4899,4901,4903,4905],{"type":4717,"title":4891,"context":4719},"llama.cpp",{"type":4717,"title":4893,"context":4719},"Hugging Face",{"type":4717,"title":4895,"context":4719},"Unsloth",{"type":4717,"title":4812,"context":4719},{"type":4717,"title":4898,"context":4719},"vLLM",{"type":4717,"title":4900,"context":4719},"Android Studio",{"type":4815,"title":4902,"context":4719},"ShieldGemma",{"type":4815,"title":4904,"context":4719},"Med-Gemini",{"type":4906,"title":4907,"author":4908,"context":4719},"paper","Gemma 3 for cancer therapy pathways","DeepMind researchers",{"relevance":4733,"novelty":4734,"quality":4734,"actionability":4734,"composite":4735,"reasoning":4910},"Category: AI & LLMs. The article provides in-depth information about deploying AI models on consumer devices, addressing practical applications for building AI-powered products. It discusses specific features like offline capabilities and multimodal processing, which are highly relevant for developers looking to integrate AI into their applications.","\u002Fsummaries\u002Fgemma-4-open-models-running-agents-on-phones-summary","2026-04-20 15:15:06","2026-04-20 16:34:59",{"title":4840,"description":79},{"loc":4911},"38b04ca9f5bb2faa","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=_gVFUEdhCyI","summaries\u002Fgemma-4-open-models-running-agents-on-phones-summary",[104,107,105,106],"Gemma 4's 2B-32B param models run offline on Android\u002FiOS\u002FRPi, handle multimodal reasoning\u002Fcoding\u002Fagents at 100 tokens\u002Fsec, Apache 2 licensed, with 10M downloads in a week fueling 1k+ community fine-tunes.",[],"6xsfFixPuiohU410Zs-h4QodMviVq5b8ofmdYHRLbBY",{"id":4924,"title":4925,"ai":4926,"body":4931,"categories":4971,"created_at":87,"date_modified":87,"description":79,"extension":89,"faq":87,"featured":90,"kicker_label":87,"meta":4972,"navigation":92,"path":4987,"published_at":4912,"question":87,"scraped_at":4988,"seo":4989,"sitemap":4990,"source_id":4916,"source_name":99,"source_type":4743,"source_url":4917,"stem":4991,"tags":4992,"thumbnail_url":87,"tldr":4993,"tweet":87,"unknown_tags":4994,"__hash__":4995},"summaries\u002Fsummaries\u002Fgemma-4-open-models-running-ai-agents-on-device-summary.md","Gemma 4: Open Models Running AI Agents On-Device",{"provider":7,"model":8,"input_tokens":4927,"output_tokens":4928,"processing_time_ms":4929,"cost_usd":4930},7092,1839,11145,0.00183105,{"type":14,"value":4932,"toc":4966},[4933,4937,4943,4946,4950,4953,4956,4960,4963],[17,4934,4936],{"id":4935},"on-device-deployment-powers-agentic-apps","On-Device Deployment Powers Agentic Apps",[22,4938,4939,4940,4942],{},"Gemma 4 models range from 2B to 32B parameters, all fitting on consumer GPUs, laptops, phones, or even Raspberry Pi\u002FNintendo Switch via llama.cpp. The 2B\u002F4B variants run fully offline in airplane mode, generating 100 tokens\u002Fsecond for tasks like Android app coding, piano-playing agents, or parallel SVG creation (10 instances on a laptop). Use llama.cpp with the ",[4788,4941,4867],{}," flag to offload per-layer embeddings to CPU\u002Fdisk, slashing GPU needs while maintaining speed. Larger 31B model maximizes raw intelligence; 26B MoE variant prioritizes low-latency inference. All support multimodal inputs (images, video, audio) for speech-to-text translation (e.g., Spanish to French) or fine-grained analysis like object detection and llama localization in photos.",[22,4944,4945],{},"LM Arena scores place Gemma 4 in the top-left quadrant: highest capability per parameter size, outperforming larger closed models in community preference for conversation\u002Fhelpfulness. Evolution from Gemma 1\u002F2\u002F3 shows consistent gains without size bloat—Gemma 3 (1B-27B) was top open model on single GPU a year ago.",[17,4947,4949],{"id":4948},"e2b-architecture-cuts-compute-for-mobile","E2B Architecture Cuts Compute for Mobile",[22,4951,4952],{},"Gemma E2B\u002FE4B (effectively 2B\u002F4B active params despite 4B-5B total) uses per-layer embeddings as lookup tables instead of matrix multiplications. Embeddings load minimally into GPU; rest stays in slower memory (CPU\u002Fdisk), ideal for mobile. This novel architecture, released last summer, enables on-device multimodality without heavy compute—e.g., Japanese text extraction from images or video understanding. Tokenizer from Gemini supports 140+ languages out-of-box, excelling in low-resource fine-tunes like Quechua or Indian languages due to multilingual design.",[22,4954,4955],{},"Apache 2.0 license (new for Gemma 4) allows full flexibility: download, fine-tune, deploy anywhere. Post-release stats: 10M base model downloads in one week, 500M total Gemma family downloads, 100k+ derived models (quantizations\u002Ffine-tunes), top Hugging Face trending.",[17,4957,4959],{"id":4958},"ecosystem-and-specialized-variants-drive-adoption","Ecosystem and Specialized Variants Drive Adoption",[22,4961,4962],{},"Integrate via Hugging Face Transformers, Unsloth, MLX, vLLM for seamless fine-tuning\u002Finference—no ecosystem switches needed. Android Studio's agent mode uses offline Gemma for code gen, boosted by Android-specific training data. Official variants: Shield Gemma for toxicity filtering in production; Med-Gemini (Gemma 3-based) for radiology\u002FX-ray analysis, further fine-tunable.",[22,4964,4965],{},"Community builds sovereign AI: AI Singapore for SE Asian languages; Sarvam (India) for official languages via government-backed models. Research highlights: DeepMind paper (Dec 2023) used Gemma 3 to propose validated cancer therapy pathways in labs. Real apps span offline Chrome extensions, finance\u002Flegal reviews, subway\u002Fplane use—prioritize open models for privacy\u002Fagentic tasks, APIs for peak intelligence. Experiment now: 1 hour playing yields insights into customizing for niches; expect massive on-device gains in 6-12 months.",{"title":79,"searchDepth":80,"depth":80,"links":4967},[4968,4969,4970],{"id":4935,"depth":80,"text":4936},{"id":4948,"depth":80,"text":4949},{"id":4958,"depth":80,"text":4959},[150],{"content_references":4973,"triage":4985},[4974,4975,4977,4978,4979,4980,4981,4983,4984],{"type":4717,"title":4891,"context":4719},{"type":4717,"title":4976,"context":4719},"Hugging Face Transformers",{"type":4717,"title":4895,"context":4719},{"type":4717,"title":4812,"context":4719},{"type":4717,"title":4898,"context":4719},{"type":4717,"title":4900,"context":4719},{"type":4815,"title":4982,"context":4719},"Shield Gemma",{"type":4815,"title":4904,"context":4719},{"type":4906,"title":4907,"author":4908,"context":4719},{"relevance":4733,"novelty":4734,"quality":4734,"actionability":4734,"composite":4735,"reasoning":4986},"Category: AI & LLMs. The article discusses the Gemma 4 models, which are highly relevant for developers looking to integrate AI agents into their products, particularly with on-device capabilities. It provides actionable insights on deployment and architecture that can be directly applied to building AI-powered applications.","\u002Fsummaries\u002Fgemma-4-open-models-running-ai-agents-on-device-summary","2026-04-21 15:13:10",{"title":4925,"description":79},{"loc":4987},"summaries\u002Fgemma-4-open-models-running-ai-agents-on-device-summary",[104,107,106,105],"Gemma 4 delivers 2B-32B parameter models under Apache 2.0 that run offline on phones\u002Flaptops, handle multimodal tasks in 140+ languages, and lead LM Arena for size efficiency—enabling agentic apps like piano-playing or SVG generation without APIs.",[],"0b0Eo5YTmWyS13vAf1UqtuKv0a104JqK-eNjI3sxQ4k"]