@abu_salem.09: #العودة_للمدارس #حارة_الغاوين #ابوسالم

abu_salem.09

Open In TikTok:

Region: NL

Sunday 30 August 2026 09:48:41 GMT

27138

914

59

587

Music

Download

No Watermark .mp4 (2.29MB) Watermark .mp4 (2.48MB) Music .mp3

Comments

🇸🇦𓃴𓍼ོ🦌🇸🇦 :

عوشه بنت مبارك ساطيه وشخصيتها قويه 😂😂😂😂😂😂

2026-08-30 10:55:02

8

عايشه :

الولد فاهم اكثر من امه😂

2026-08-30 10:59:06

2

صدقه للمرحوم ادم الشامسي :

عاشت عوشوه بنت مبارك عرفتله راعي الباص 😂😂😂

2026-08-30 09:57:02

8

٢3 ☘︎︎ :

عزرايين يعزرش 🤣🤣🤣.

2026-08-30 10:10:29

4

3𝔅..~ :

😂 صدقها ! طاير من اول يوم و يسير يعقهم من غبشه

2026-08-30 10:45:37

2

GBK :

مبدع بو سالم

2026-08-30 09:57:58

3

dyqtb32lm1sz :

العمل كامل موجود ع يوتوب حارة الغاوين

2026-08-30 10:31:46

2

كل نفس بما كسبت رهينة :

عسل والله

2026-08-30 09:54:43

2

🇲🇦lحنونه 🇴🇲 :

😂

2026-08-30 11:09:11

0

Nasser :

مبدعين كثروا من هلمقاطع 😂😂

2026-08-30 11:07:03

0

بحرينية :

😂😂😂 بالضبط

2026-08-30 11:17:21

0

🤍 :

عزرايين اعزرش🤣

2026-08-30 11:27:11

0

أبناء السلاطيين :

راعي الباص يتحمل مسوليه اطفال وصيانه وتسجيل وتامين والطريق وكل هذا راتبه٤٠٠ ريال ىاص ومحروقات وصيانه وسائق و٤٠٠ وين بتحصل😂😂😂 والحمدلله

2026-08-30 10:55:18

0

user1299145786358 :

صحيح بيروح يسوق الباص الثاني 😂😂

2026-08-30 11:08:31

0

عبدالله المقبالي :

مبدع يابوسالم

2026-08-30 11:33:58

0

November :

😂 واقع للأسف

2026-08-30 11:13:31

0

ummkulthum :

😂😂😂😂😂😂😂ياربي

2026-08-30 10:58:32

0

R.M.C_217 :

واقع🤣🤣🤣🤣🤣

2026-08-30 10:00:46

0

11:59 :

😂😂😂 ادب

2026-08-30 11:34:44

1

Haleema Alkaabi :

😂

2026-08-30 10:54:13

0

Maestro :

والله أغلبهم كذا يسوو بس الحل بسيط روح اشتكي عليهم ف المديريه وبيجو ع التوقيت اللي حاطته المدرسه

2026-08-30 10:52:04

0

Ze Yad :

😅😅😅الحين ماحد ياكل شىء

2026-08-30 10:48:02

0

S.A500 :

2026-08-30 10:11:58

0

To see more videos from user @abu_salem.09, please go to the Tikwm homepage.

Other Videos

When an interviewer says “we have millions of customer support tickets…” they’re not testing AI. they’re testing systems thinking. Here’s what that actually looks like 👇 I’d break it into 5 parts: ingestion, embeddings, retrieval, generation, monitoring 1️⃣ Ingestion is offline, not request-time At this scale, everything is async • Stream tickets from DB / event logs • Normalize messy text (typos, threads, duplicates) • Thread conversations properly (not just single messages) • Chunk by conversation flow, not fixed tokens • Attach metadata (user, product, issue type, timestamp) This NEVER touches your request path 2️⃣ Embeddings + indexing built for scale You don’t embed on demand • Batch jobs for new tickets (queue-based) • Distributed vector DB (Qdrant, Milvus, etc.) • Hybrid search (BM25 + dense vectors) • Sharding by product / issue type • Store metadata alongside vectors Key insight: metadata filtering > vector search 3️⃣ Retrieval + generation (tight path) Keep this path fast and lean: query → metadata filter → cache → hybrid search → rerank → LLM • Most queries hit cache • Many never reach vector search • Rerank small candidate sets only • Send 5–10 HIGH quality chunks More data ≠ better answers Relevance wins every time 4️⃣ Caching is everything This is where scale actually happens • FAQ cache (repeat questions) • Retrieval cache (top ticket clusters) • Embedding cache (hot queries) Real flow: query → cache → (miss) retrieve + LLM → store result This is how you cut cost AND latency 5️⃣ Monitoring closes the loop Without this, your system slowly dies • Are we retrieving the right tickets? (recall@k) • Are answers actually helpful? (feedback) • Latency + cache hit rate • Auto re-embed as new tickets come in BOTTOM LINE: RAG at this scale is NOT an AI problem it’s a search + data + caching problem Most engineers build chatbots Real AI engineers build infrastructure #aiengineer #ai #embedding #rag #softwareengineer

When an interviewer says “we have millions of customer support tickets…” they’re not testing AI. they’re testing systems thinking. Here’s what that actually looks like 👇 I’d break it into 5 parts: ingestion, embeddings, retrieval, generation, monitoring 1️⃣ Ingestion is offline, not request-time At this scale, everything is async • Stream tickets from DB / event logs • Normalize messy text (typos, threads, duplicates) • Thread conversations properly (not just single messages) • Chunk by conversation flow, not fixed tokens • Attach metadata (user, product, issue type, timestamp) This NEVER touches your request path 2️⃣ Embeddings + indexing built for scale You don’t embed on demand • Batch jobs for new tickets (queue-based) • Distributed vector DB (Qdrant, Milvus, etc.) • Hybrid search (BM25 + dense vectors) • Sharding by product / issue type • Store metadata alongside vectors Key insight: metadata filtering > vector search 3️⃣ Retrieval + generation (tight path) Keep this path fast and lean: query → metadata filter → cache → hybrid search → rerank → LLM • Most queries hit cache • Many never reach vector search • Rerank small candidate sets only • Send 5–10 HIGH quality chunks More data ≠ better answers Relevance wins every time 4️⃣ Caching is everything This is where scale actually happens • FAQ cache (repeat questions) • Retrieval cache (top ticket clusters) • Embedding cache (hot queries) Real flow: query → cache → (miss) retrieve + LLM → store result This is how you cut cost AND latency 5️⃣ Monitoring closes the loop Without this, your system slowly dies • Are we retrieving the right tickets? (recall@k) • Are answers actually helpful? (feedback) • Latency + cache hit rate • Auto re-embed as new tickets come in BOTTOM LINE: RAG at this scale is NOT an AI problem it’s a search + data + caching problem Most engineers build chatbots Real AI engineers build infrastructure #aiengineer #ai #embedding #rag #softwareengineer

Gen Z katanya paling lemah, manja, micin, bahkan katanya lebih bego dari orang tuanya. Padahal mereka generasi pertama yang megang HP pas puber, dikeroyok algoritma yang dirancang bikin gagal fokus, ditambah rumah yang harganya 20x gaji setahun dan kerjaan pemula yang dimakan AI. Gen Z bukan lebih lemah, mereka hidup di zaman yang berbeda aja. #genz #pendidikan

Gen Z katanya paling lemah, manja, micin, bahkan katanya lebih bego dari orang tuanya. Padahal mereka generasi pertama yang megang HP pas puber, dikeroyok algoritma yang dirancang bikin gagal fokus, ditambah rumah yang harganya 20x gaji setahun dan kerjaan pemula yang dimakan AI. Gen Z bukan lebih lemah, mereka hidup di zaman yang berbeda aja. #genz #pendidikan

#fyp #whatsapp #xycba #fypシ゚viral #kenon

#fyp #whatsapp #xycba #fypシ゚viral #kenon

Cách pha khoai môn Latte ly 500ml #khoaimonlatte #botsuakhoaimon #nguyenlieuphache #congthucphache

Cách pha khoai môn Latte ly 500ml #khoaimonlatte #botsuakhoaimon #nguyenlieuphache #congthucphache

كرار سعيد . . . . . . . . #foryoupage #شعروقصايد #الانتشار_السريع #مصمم_فيديوهات🎬🎵 #شعر_وذواقين_الشعر_الشعبي

كرار سعيد . . . . . . . . #foryoupage #شعروقصايد #الانتشار_السريع #مصمم_فيديوهات🎬🎵 #شعر_وذواقين_الشعر_الشعبي

About

Robot
API

Legal

Privacy Policy