From e13264862bbb2131684860fb389a0fee4761ce1f Mon Sep 17 00:00:00 2001
From: Heidi Steen <1612796+HeidiSteen@users.noreply.github.com>
Date: Thu, 9 Jan 2025 16:59:44 -0800
Subject: [PATCH 1/7] Vector index size by algorithm

---
 .../vector-index-size-by-algorithm.png        | Bin 0 -> 22997 bytes
 .../vector-search-how-to-create-index.md      |  14 ++++++-------
 articles/search/vector-search-index-size.md   |  19 +++++++++++++++---
 3 files changed, 23 insertions(+), 10 deletions(-)
 create mode 100644 articles/search/media/vector-search-index-size/vector-index-size-by-algorithm.png

diff --git a/articles/search/media/vector-search-index-size/vector-index-size-by-algorithm.png b/articles/search/media/vector-search-index-size/vector-index-size-by-algorithm.png
new file mode 100644
index 0000000000000000000000000000000000000000..e49ddcfba65a6caf2c22f467a5b2504bd31654ff
GIT binary patch
literal 22997
zcmdSB2T)U8)F_GtumLs@k)l!*kPbrVic&)F5V~|i51|K8KLL><C6v%adI?AgNR0^6
zLg>9kqy!Q=1f;*9-~IphX8!r--MRO^nRjL~?6c24d#|<jTI;O63h%WvlxVInU7?_$
zpixnNp+iA&v5kV_9OWe{a?d3dq6hiUIf#zZbBfX)=4JBDMf+#!&nPI$W3C=qQIhX3
zyDJ+*C@2^>&wl4rbT~H1FN8Vj8F?A0t4UhBx$s-rxV^IF_jPe6kEWoImh*MDvIg6F
z-G60k@8~M?XuTf&=)R+k%p*fFbwPD^1zQJ4Wq(gwU4IQdYk#mcz~+&hEX@^ZUrF)|
zF1B7)_kCTQT_KXbG7tYuEJ<#kbqhR{mG-o;lhk>k`0ohvoy<cAFE4jV0RbN$AATPZ
zem75h0U-bYARs6#AS}#B9>E9kbM><F<#UCw|2x48TZpx%qq~=*o9q3v39VkaLA_)i
zLZOZ}l6F>hVy|p$#Q0uWiP-Q73E5cjS=opP@!5!o*ocb>NeJ5sy?XfX@?MU1|GB;^
z<X<w72_kUzL_mmN@C@X$wxp(~qb(VVvn6GPr2jnsfAmQUoB{HG15EaB4;fc->pv)S
zMyCIuuB|JXq&{TYJxNHuN<m>bs`BEQp0D}pae%MhLgVQvS`erO7(0KH<1+_ON&#gK
zWlmS~O?hF<g)ib%^g6p`T6`D5_fa8@dL>i?z%M*27D5^Fdy9QB*RNkPx$i<h@lcEN
z7Tsk^>WdEyF6qh71)ds#?M6V54i1j%$@sat#kx2s0@^SNTCZK-o9@PM?_d10{S>V!
zAJQ)TZHD;DTVDIy^mzY`@o($b&DTQzj^sRV{kIjadd8Gz*Y%`Jk>~!j?(^SZ{5y}l
z=|jOYZl$0I`TF92enP~4pll|@a?nE$&9~vSiS6XMH_!&SDWO0uwie672c`8!!PieX
z+P~cbnfU9mxHaj>G(pO(nGtWwWM@9X*ZuXkk=CsX;!C^QHHBB@{=&rUtN(%-TsYN_
z8;<D5^{>|t-&~P2L&8t@1g3@e6riS6hU*5S68YZ%yDIMt#jsL@I<}nw>`8AF%ka^Q
zcd{q>5T`#VU5b2AiqeZ=MGk-dl^oPWyvJ!a`Md=L$QKgR9AIN57WJ;V6`Ihp8RGKg
zMtX5_vuRiCTWa#5J4UD`_dtzdW#CseLvvVE>1ObRMc&2XB`@gGjs>$E-}ltB`LE*~
zfbS)C-H@<_%&w!2hcXhoPRA#UZab6b%RI}jjV28In!E+7Khm{b`)y!sT{ax&ngqy~
zx0XCAO+;=k@!~h?oR$Y-6mdlwJ+o&MhJ1ZydCj9pF@u!(xKR%Q*mT0G)IM=<8fIdQ
z=QuWTJ6)GOb}$s7KRS|>nG$LSoMXbALHqmMG3<D9BG_27)=kqx<HpO}8RJ?rf{-Fi
z_ttQpEyQE~Z1Vd-{Rvx<tE1q(9j)H+VDIQl<);e)L)(cK%K|+&q6obRKUF&0#s(bV
zVH3-i)6k;ZkhOf=-P`dw9~L}OeXR+L(eGPo)qIYWl<2FD6>C)+Cgzx78p-%yd@@7Z
z8HU5jN`a@CJ<$W77hc*Blp`z!As(O5XNq%~E}~^)zn=JU42W~_d?pk#<G=ipZ}OlP
z@`tNG#a?H;x<O69)(_5<Y)_ZLbNP<=7M()70gt&z=>kvltGuuteiPM05!b-#tr)Q<
zBKpB!SL+k4`m6d|=0IKgP}ACAsRd?Z-Z`Vx*H19{LC?C6{a0CQGHTb1U4q@hs?k9f
zQ(`xykM#xJ#thqwp*voJY~!0{>AIO&TQxgfssf?M4f<<oe`Kgn?*`-c;f@RPSWw-p
zJ`ub+NxH0dzx9L@A?p5y0cKkBslPDhj??#VnNE(@ETP$9sNdF(Hm4j=kLcoJS``Ge
zv1+R<4B7|a=kjrC4v>np90`!BI>uTkzgtUox<3(kP(2d#m<Ib53*d4M{A!yLG3qk<
z3|5LRGs&Y_hw<yXjE2H7JNZ}eLo`|NI-8RhdzxPYh0P?JNG}_=22A{M06%L0nSmOs
z)Pf~fnE%Lg0nKZn!IPR%LQ6Nbn41Ga)^u;T*6|@%;o$F4)NvzjDXixPK3ii>ugdw$
z)5zLKi$BN6NbrEWsc6i1D=L@@y9QNy4gF29VuZyP_yT|Bp^lx!xINxR*Z`oEwX{id
z+jAgC3@nfgdh3yUjARmNM)LE?4Ms1lXH<Ir*~IJj&RfUj$PxFydy;WePhVrqD`hJk
z&V!7lZ9R|kJ+|SC5|UuJ7SUL$GAjO}k4L&Ut1Pz~3k6@rCm%TW=hm7YfNV*{!VI5v
zlSE3}Lm>p<bdavn@>fIn(694nqQSK~b+Ij)btqnycgF%1L<?3yRoU;&3eJ5G9APf8
zfK(5lK>1Q)C7C(J>wRBJ7yK8|E#kJ2#dlr)faen=O$+@*F`prsGD2pL<M&IQLc7bw
zUBcTL$F|jCcl3Wt+w3~}JJ=OMt|%;dUnEvDV%!%&B5}V*Yu{T$HkVh@lf|Gn`XI*}
z+uLwA*Wz%I@E~)S85&)Xc^t5-Y-UzBA}QFtKQH$xIAvNvX8j;tHlfNDvGA3;C*4vf
zi0BdRO{*LS47R<;c9JI2d-XJ*72i(Dy$V7ZqG%1qZY`tHrL6lMwCG~n5ox>E2!~9f
zCdOij7c6}M9G<9bV{}uUVe>FQ6XTE`W6P5F`>LHLI*Wpp`>!6+Ff%oAPg>aR^@V@u
zPfXML!Bp)Uk+I(=WVKv2v|WlT#2i_!73eFBIyqTAaciDUAg0v&JGdxr1h5ef67wef
zDMjC~>B{ZDGoTz<H+G!3jjZJ3?e<RgLms`3Ws}t|31e<<Mt5g?hMEOu>1z%Ngy~oP
z92>tDL1{YF4ahlR@-)sx4}_C9{y2rxFQ{W*uOw_oDoQZslrB>++R9Kx0qdBta>sOj
z;%@DLsrB!H%{Cpd6t&&~FDb2BiLUXkbl4pmsw8fegAE@h4-AN=@<}!k!JT!k`s<JZ
zp9#<cW^8-ncCp->*=JelB+v#XN!S<xy|G?!TZW6VqE_a5trrdM`0WH^aKk}ng_BD6
z{IL9}d8vDY_%6o9Gb@W?DUGsig2U0ypy))4nBUljimRI%lkNU0nAy$22|yPc1dmLJ
z?dB}}VOxJyFcO87h3WSqRR$H@K-<C4fyOeq;;h8Z9I{?{S2HA*KgN)@Bzi*X`}Uk=
zENN6_?_@=zb7H=72OzUOn+~!hMr}Nmaimf^|7Vui(4HFSuoSX%e#duPT0WYV8olKC
z8_X(G!=+A#m8s02ZJ})Md8t)mooY9L&%d2jYB9|snakpo$3H^LZ@rtC2LhYIuR$(W
zM{cX6^iIT_PFWNX!_b4<H=Hg~!BrKmdaVy9J`+m2pom0SF*&5HhiOVcaDdXV;`PC|
zDU$hs14PNz>I9?#Ubll5^QFn1E@V|1n5BD2StL7}Df?RuSf}rkw;x6(-eJAhvPaCx
z4Zcs_irZ&$Cx0X%{<@sY<`mOQnW}wY1`7*?!bjj2!D_3)0Z3V|i&w6h%~vR9bkFdG
zP2XU8UbkEK?Vc0MJ7e=ZNp(f0tRi*RWh6Tf=pB>zXVy|dS=1$y_d38RrGTT?PersU
z*4|k-E=J;10MS2zGUIQoi9JDDYH_A4{INwE#OYAwM1ke`jKQs?o4KPhJYXW+Q(pry
zPp5d0f*(|ngANUe#1J!NW)*l0%<9H^(~WvwYnatBihchq7Ih6GV;W$F*vWd7XV<bh
ze;gdd#W|fbIXM{?ycc0Guqi-#2m3PX{*IQ_Etg-$Y<G6GOiNXz9bF|pSOtjpJJYN8
zqg(wfozYK`ymUwu<in%`YwcpKd<HT&=%zLO2N_m?iNVvR<B9F}5F_8yqns({^Y+s-
ztOUR+A3ld5+9Xf6%!eEl5bbq-GkX1ebGb#v@uy@Cl)G7xloyD1hAwlx#8t!5cHEJB
zUuW7QwDaf~b!Ak&a(-)Ku0PC97ZlJ`*2h&bo7=gdoX0Q-=vx<mofjLs{oz3c4~rZ>
z3O&NP41xKX4mA6??Ef(LTYh<L;fI2>eJT=gscm_a>7x(UI2B2`b0z@4lmn^TWML*?
zxoeBI6|kA3cjUbR<DNRrx0+5Cf56OmZI&$M@Q(t*-ubLT9d!)BtinV*)CBqESO8DB
zn_GCsZaY*x_uyx$eA;{W?W?$)r>kO{{*DWYZ|!H&w)&o7_l=mwi(xW|&Cr8c&ETw3
zf7RaoJs&a~@L&^(n1fCHwc-!Sy|2kkIk4w_5i;@4t0N@5>$I?iP%tm5Qm12Bm5|_7
zoI=Fx*XoK(;gfQz4aYpg0CKNQU(Kd<Hk{#cUFnykVD;%L>Y#5ta-cU>pwj_l*SWl4
zPc?eJbnP>LVhHFX+8Z?Yb+>MVg^E$emFndbZN8?(@Xncf8YhAzPc>jh$&){y#kRIW
zuHTO5;N&6pBzo$zj0VG5eWFX=&Vd?^zDm28IBE1!O(e>f3P6IDq%#Qui;(-@GF1h}
zyzXc-2N`0jgYr}d{i)8I;~GE1y*4uaaYBxIWDddz%9ymxtNl?sArd#+UzeYK6Sp?}
zYSrYrzi@nA-}}_BJ7+e+WqU}Ph{OR98Z&v+o&!5pS(AypPN$gKtVYA9pETy!hO__y
zMMsr(lBvp})3of@$-=_hJ;fjVeJ=>z|EAkhMx>=~W!tpf2Fd7NK4XrysN^|aWxn?|
zm^dxIM?}+_mb~%k^c4FEw_#QdF8egw`^XV(o@&-RccTUH<#fSf{6bbP7{#wv*`3Fc
z^%5fHHe-4jsI|R_9d7V@L$=zmCZdMhs%g67(Z?o9XNr~^>rxCKF6>ozD(kIk8E3cI
zH_`Ub^;!;aMDFPOm0KfvN%_#kg@0(?{E!eh+pE@Es=#!)-ej@Dl1A;&CGqZ?pO$h0
zEcV2?xAC@J@I?mV1EtAMjX8_aqBK!tDnmC;)QnQmlcWeq%?MmKra>)4gNm)z0Rh+*
z@@u#(%9Q8^Cm%mi=fFqoKRsh6mu9!#|7_Zy)r>N~p3P+~SH{sHHt&R724z3Gvp)F8
zn!jJ+rs=SHx~7Xmigg{t6qDTBFXC_8cU%hHzqRSZbXr&4iyrirB{lru(^P~7Tt==k
zf6S5DZLk~MUCI()Rd-26?3~+kS_#hp>X?vNJ<8VVa*;dJ8Fk>5#slpl2qE-3qJ?<c
z(0QOemKVW44ItY^TT7=U0JQAa=eQ3#PrL{sihFy@1uZ5>oNme7D9FF2>SFVmtny7d
zUF>+3`d2zlL^6Bv5L#!+XhIF8IbRdN*j8aeLg~Ey+W$B|6lf2i_)zn5lFQNSrYmV(
zJ5jX$yWn3DbD%^0H>}J7sG#8Og`W5B27#q=d;%jGi8X|itmuq8*;`A<q#5|Z(F-5N
z%gTR@#a|a*3(1QeY$=qr@ky1U9_28&Ai(obEPOn-7Nk5-IOvbh9t73mt9H{8<4Ro$
z;l`bHD6;u*Tfr;=-cW!xgbqQ)Es(0|?CgLOO}JmtP!rCVM#Cfek0IDfHU#CriAx&o
z*9KYmKj&@CU)ZcEZBPa}4VwCV<u_b&F)UJQWwMnhZrXBaNnI!WRKbTY@i$hZ*O)&R
zCHCAnW1Wz%gRK|-J-*7%h2!QA&w42+!omLskFx*$*?8#e6rOg02tM3h?RoYW9QpX6
zPyge*{WI{HF7R)6>;E@L@Ba#3r^W64z@FD6=&#nxE=GHaJUp`67x)<{u0KMEf%Arj
zh@!qr>2*h2nDp#3UikD(%)xRchBuMemBTUZ54JG#x&iN}pnz_#*5C-!KDd57H63A1
zJNrL}?-YIhb?eP5iV*+$rOzL{h)9^e_U3!Y?K9Lxzfwh6k{tqPk3~HDU*73wW+Qih
zGk$iP>_j=c{!33qZr(k{!^Hvv{!^pnm{o&HrN~~N#o*7z!BR!>J&u2PmLf#bDeiT-
z0PksGQ;Z+Ua+nhVv8a$eTtFSHBz5}N8@`z_Umwoh-s{?qg7E)c>%O<TfZ*=9`E>bj
z9ARq?Od8JtiwWmO#Z8!&<~(&7%67ZcxLsU~${}6O75J?ekhYzn8$2p9w>}stPA8!x
zT89*v%3ry2vc~+^%@Xn$VPv`Tm7z?!G`<Ep6qk`CrNqSVge<wtBD%dJv~aST0CBzm
z_yiYO*WLZyr+I&aG@gnOI+2yBoCf^Sh!hk()atx~-oGvU*W^Fj(HuoXBBx)vh=JuH
z$RnZ^i&r#Q8Rn_CvsGN(J5^umsX;$(@8;C@TN-)P4LCE#$QK?ocqNiW0?C4_eNj{G
z9(`%}vnr&PHf<oF=Z3v%d%fu1f+0yu6MyON@H9Gvfn`Z)6O{JvJ;kfRs`J(^Hxu-Z
zU7WG(=-&nbWPePZL|7)DHY73y&=pi`8U~dw4qooi<XZlg>Ng8XN;!X-RD-tE*nU$z
zk$0)ZH2<5YeG~VoPEC{Lsa!###)T)?XXG}vhM`Wj$EC~rDLc&*Ol%8wMdF)m@Ncey
zU1)gK>ECU18YQnjYF_Gb2bPOlFXAga;pT(w;Rs7koJkP9cz3v>?0!*11}k#64%m`e
zjej(G@EwMz-2$m^;rRpntEz+rL?sr?^6my7zfQre*b}VTz<Ba4Iw_BGD{EmXU}gc~
zNY!$%L*Vtp^&2RCA)|oVp(71<6x0qz{+y|AJi_#hZp`~sbuc&_)}P?ZV5A&Qw#gh>
z>Z*gJ9*T)`$P?SF9SEeZ5SEL4hY%9c6rqcJFI;v*&19a1<tVxkMv9@l*#3u@^2egc
zZ^;wjk&miXJEwlA-G3maeM$8V{_bv{udMwph3K_RfEXL8^k9Lzc?PcVCh_5$O9bDf
zyr>3Xm|>G6-9x{!;f_ogPLe}-9mTXiZ+0cLrl~CK4E>pfgUr=9|C!v`PBLVtcTtts
zsH;e2)H$+p;jCWqLqRr8oS75)On`yA4u?&w6)^M=zCC-`{B-DCyDV5vSczQ<ak|r>
z+7h4JG6NRttU$IktS^}b_kj;nL930xmSETY=nT2R9N7UmgV5s3)PFF#Zg%Txq)Oe+
zLo<)99O0|7BW^P7&;iM{)H(lv<95Op8n@KEY3Mk=FcKSeKgY1^$WlH(gZ7BT!lJ>7
zJoVyOMf2=~I`6&!HUZQ5P8I3-zYdqjO9BtN1LOzv34=r)M<VV`b4~9_9&)Bw^r#(0
ziR<=rd0VOzz|v=K|AMD)M`SEvNHz*$Y`9!BKT!iETHs<2A}^1hrkB+Lw^;jR4=w)y
z8Uhk4{5F<U&od7S0%o_FXLniMaqPSo09`J_3~h?H<&Up4c1^)z8BTvml3i%sfI~kk
z-0KT*KDBlePM@dqS18vd9>L?J#+@wF3yb|psNwIzZ@gf`_-k)rah&M!^W%u{Y99?l
z0cx*r_e!a7WF8#2oATE?8Ll3GIdcE)tCZ}rVYWJyUJ_dlp|QP=U?I2u>4!p7Ha^rx
zYoVm{fN-afY5Zw3dFkwJeM6PbL}_ChQ+B?z=uSId<eVAPxY9wp#VM<U;&{_29n<~a
z-txS`Xw$I6`Js%fNb_!x?E|sjN11KEHU41io&_fRb_2A!LAO?3ne{gzLrE(IvEnuQ
zNf?3ZNGUlpc%aJ|$8Y=Yi5CNIhqxU&vt00#*fQD11ExXOVBO+I6z8;@2=&Q9G_4f%
zh%UaE87u!+CVTn-bdfJ<Bg`lyy>*m=-vr17-wd>Oi^^;)v`=f)8R?V)?Y!YEKRHuH
zZv_2n{ZHg^gHoW{t<2f&xZw}R*_cH1iaOTqn_aZww3s3;zVeY8d%p1}L!byc<@EG|
z+oG|gnxH?b+q;ME4=TS#05p+ieb0nc2KGpq>}3P9aKA3r;7q#)M~-H;{rO_V5T1pv
zVi9w&aBkY43srM4ztmZrIDQicwrPrZ?vD~3?F^8|5f_*ZgJD65WwV`$E(eXG$Y#&T
z&Lz^;LLf~NyWC_~@pDPxKkHG1zx-=om6ZAIYdZSRu=g}u!IsCfO%j80rTE7_84W^z
zVx_T1U<(<t5Yl|KxJJQbZnpO5>}@Rzd_mh7z6&;&5Ndnlw$$NC>8bI!mdf70#IwLZ
z7WB?N*)T!`tv`J1UCrVPNjb@CQ?L7rtGld((rckK7sZDMhoX=L6k=zqm+A4c>>t3s
z?SJ@Yl=hWS8c5%GR1|S3;_sZw|6$~mF^LL}lo*S^4p(b>n#m^h%A^}wztRqy_V#S(
zr)Ki!`-vDyvhi?D>P#t-w*LKYYdaC3J=$lB^!@zTMGs4t@OXZ2q%k)lLUSnO10_Z4
zdpj(GoBTEntA9Q}`p6USaQ1?O77f$Cu>p#nJ2VpsH_v)0C?qVd|L+MI{8x6%|56O%
z|9=yP=$gAsE)H|!H$;A#N$V_^ibjD}pwW_tOjd^>TrL)|inRj?K|ZmFZ}h&bQk?76
z$Sw14@013wM(%5x8zTJii3JmY8PB&Wy_3I~DJj0~V?61qg8b>a^>(vg@*o>RGL<Pr
z9rH)jg}QQ{Z7+C4i>?M%Bx&2p)D8j&((W&KxoC8D|9RHszyCb&T~l8Tow`c@bXKo$
zk7oQO26ir`MD>B6mv4#wp1CUiZEWYfHN!BNb#Q9n>L#Zp+Pofbc<=!tNI?;o^8!Uk
zD4Eyj1g;HfNSbE3V79~nm8l0Zpw9#*{Eo*8j-JO{@TD;<Q>zd%<+s>T{ScdxT<B~L
z>c7ajdoL^UqRQb1)a(Vkk;+8jFYy=^puvdQbUHf`Ut*3!4$0=GC-iB^)K&RJH&B=^
zO@`%hYywY3)GFfQLH91)0u`J69Op7#6@c{6HyiU&fB&#|2q~s5bV|C9st3Hh<FwrG
zb-@}5Duzcp{OGQo=p@^q_e*UYX4;}AzIbFmbv~-BUY*GOWv|G~`Ao9HIfCm+se8|L
zbaX<|(z~0hN2A*K<ZX@du0W)3{`2-GkLYuV5X?bm`U4enq+fkEz+j>YR9wsn^#pII
z_r#LC49eDDkOFpkc@BT}B8CO}0bA$Yv)tGaaV0NL?31G=Hnw`_<8p|>dAYCcQ=>q>
zniY`hjUFe!b@K*X=B-1l!7}v%53CB!KQxfNOx0Et0NzOU9*E`ie?vYb%1f&%>vi=3
z{9#QdNDe=SZo^J=`mJ;F)<C_sOEnyw^^PXW5GKuK27Of^tI(M5Wh#oF(r5USpYK>;
zrh!{el1o3sdN#fDci{!@T}C9LZM8{LVbYXtM3u<LoNjP6l(q147dww%V2(e|MopZs
zd6T6uR?oQPu65+prR8aAZu?D*fappDd5Hg;sgw03XlezkK<%gazH=0aXoI&wpG!32
zoPc^;(YCG4NS?H~!kKC8p{~z1>u&*!Xk4r`)U2sOX-9`nq+KbdDTQZ>Q^iEI#dhYA
z%bw}!#+3Z6&;e=dnY*dcj`&~POj9!I%cZVNE9i9tH~rbxXKg-4>y_u)tF}p|wxm@C
zD;RQb#hM4^UsCHbJrv;FRGlJ@A7~KGrRx;mW}ydrj*)x{gwO$>{LntRg?rz)d1QZO
z{!HdEl$~XiGk}a3-!eEH6;Ky>N=Y>_I*F!D^^97WcOi#%k{&-AG<7XgTX-T8{96Qq
zQ8%|eB62g{PNsIyIiN|BdZx4Q1RpD{6m~J1gC~@9H!m-KnJ9&{6v8+W;{Dn|d}GFk
zBs0j1Nd~ppNpzs0IEhv0<;%$!<3!is6M-I)F3v;fz1vSFj}%_<emE+sxkFjDxz?CK
z+A*MvU`Sm$%-cd^1H1P4%e&VtlFSk1{dG|Wc6Zk;sL5h)-=p)s_WI#2C8pe+4SbSM
zFjEz^E;((w;VO55q<wh&)F0puoPln`MRuRgHO|=1n53_7l>Z*p;KOcP;1)@TI9s9V
z%wjq7Qb0BI(k=Ec(pUA?5oIgp&9vv7Vyqcg7BKg11;&cft)%wC&6{4_eEfm$&~sO^
za^p)0x&(l0ft9eZFjol-`UR%OaWON-5Ai5e2B$w5PH>#b#;{KrU7O5E{rqxLqqx1V
zpGnNFN?1pu(9^o9B2NM@mG`TG4Lov~F6wJp2U<>+F4NQ=iQn(KE2L|y@^)cuT0?R{
zU!_@-)XKH}WmvDkVa27(&o69f@;9wd9eLNenWQ`SS;%M1P_Nw7!T_FKL<|f3C6k!L
z8wQt>kEOkR1wyW*HOrX`)EWa3Z%_PU3U~V195)nRPV8=Sqt=Nd<mXT~AERN5-}!~9
z5%@<A1E&VXho5AD8q%EWZGpDOJQff|&Atf4nkOAl|5cPnX8KOtsnBvVa66QnxcSP@
zt%JNqwisb|cLFVBVa%T4o}(#2#>%S8FTas0rb7$(i(7x4N2l7)&F%D<jK8QEl0&7F
zAY)gh7<IQ~NZC)-iAPWL#M@TJyd*u0bMzB=43|P-(a3Bt?-$p#6xFJ23*@jAq)L$n
zm_)liG!RC`J+~~P{P;vWtD>#plQsV~AiM54XH4{H+G-rXYX486?BV)KA;;p>?&GcF
zt77rgJtmir7kUzMgyBa&wssDisgUCWg_S062XAjf%^MvPg+tY~`=#h5r?X<FtQ9fS
zm5sE)exe5?7uh6xwASY?HyyZ;UDXt9lDN~(iSSupMKlQSbWT++<s-_Angne6F%MNF
z^(9qP_7;nCwvs()VwRA)ypJ56KCN8kFRq5g3wuO!K@+PQwIEoZSc2F-!jK=;6{u55
zodQT@j((DAldyR>$!i^{-NebpA204qGsggAac&sADBFn5b6K70+NYaaC#ctUF(3XD
zL6@6~S;^l$1d6WDSSjvP4yiitO%^PKR68{*Tt%Vs!l+_Id-f6r>3O&riwiN&F(Khj
z-cCK?<%mkB{G0XlQF})j$b~`)Q{r*0ziz3pQun}s*|5{#BvRX2cz)mpyP}||oG9lI
z+K~AE6!+XjOD0i5k(6huwEt_Me3W3=^bgd%mWwX+^Jkw1C%Hb;7%*+I^Qj6xAufku
zl&(67h5fMOvCu@P3^ZZW$2L}x2J!jxs!nEXwwP0-$+B?t`g|R8X6293p%qxaxG=J~
z7ry(&?L#lwkwkl#7_&}*<U&d6e6j?x&!$Q9)V-z`J~E6)lmi4O^QC-#N5gLY9>pKp
zy>;^k8D{djG`Q_sk==xcLwmnsq84`iec!Gp1IEjLW!}R8iG+LmVVdVF-C!%!Z5!il
zK8(2i3%H$|)-2b;V5)6UQtd#{eClbFtvj-z$*^7a*I_033x2=p-P8pImy}twJ&X*5
z_u(QPZDZJepc2f)?x^o8US_vcXlXs>&{dO2fE-&kxT(Ce9SFfL!nR#;9|Brv=t|>*
zSxn`Enhj^sdrha20xb=hGqTo@pRxhI%fU>8(Lw!tg}r#G{oR%(b4N26`yJy^abH|I
zC{Xy9%;erUxGBJSZ+C1r1vh)j;#PwB*$y+gaFs@KKXG5peX^yAZ)B5R;6QO^Y#0wb
z)WpU023C_&PpWO}zPV#$0}rjX0duan=a`^9H@7l?)cKZ`b_R#f)v{~EGdeP%yYc92
z<cI8&wf6?0Cs<nCt(rfC_?h};NY+gLA7Xt;-*4H`r8{qJKa!!`-EFZ0?0t13ipx%-
z2uvFg+*acwKGn+$XsWlP&=OniFHbVQka;Cg7T2j6con-(ta1xX6ozhyGzp(J9W=Kz
z(O7lyqrV*_8Bt|O6QsPq3(Xj~rf4|tV(b3wy#lU;Z&5OBY$f&Nf|BuiW!eQf3zxf>
zUi?Hy2Rlns|0Z~$qfBXk2WB34A59;)u5IrFy8}wmfmgPt9~=!{3vRZDNlWg&bRV}`
z?|t<2cixPHsmLI%x};q^^S3#(i&}6DT6#n7>eO!;oD90MosX>2FJh7kd7t1Qo?&jT
zKkt5tUic6ne9SsydDnNqXXPry|I}CYh;u2&4dXnQvb{T=3TtDw8()4>d1Q-^$tb_(
z%!Kfc5>nBTit?A%EWKDbU*4{NGt1m&OPzZw@itlM>n4afeDvQ-`}|5}K!~OC7&riG
zS??6g?$IeubragYZ}a#tW9XY+<KeEzi3F#LIlP2dB!~}jvxJbcR);;xZ7n_yyHI(a
zqEA_aa?KHGQuA@wO?O#V1=;4f+xk;R%?TM4zos9NL-=)bHK7VJ?Zgs0bewhGHrI$t
z=0am-B<(p46>-u>?G!%a>@_0W*WPNPj68Ro4Ohu@b)nI4oOG|vMA3{r+Eo;@$yzm|
z6%QAC;M;4U!$v}zTdl2@OMK=7R|CmDymtFyAIq#~lQZ109Hfi`RZ?ZNX6ML!R$P@X
zXK)d|ERAg5TuwY*3+^e9^<Im+e1Wuee2vD9)6t~7nmM*V(lgyqr*7)5V*2ak((UwO
z)IoSo1^{92M^%<?XmUC)R=QweM~%6!f}}c8n=4JyYXosdU&)vbJ^)7%OmS8HsDzh^
z6%zOi@8<EFy71*)aXzuuDmRYhJV!);o0KE&IhN`0Ya**7-<}(*zG89(rVRGT`t*(*
z;Mul8;&KPK%6sH6j}G5N2-zlb&NE<+HLVpOUJmv=K_?Y_1?lVu)*fSvO&x)mUs@fC
z78fWlkp>0#CT*aan?*JrO?H}hi<{s27q;JKKmRFv_=?3SccgbGP~+py=2Zm3FlPXm
zooH9Q{!dxT-Hkmyp2FCn0EFGODz(&)MJp<bvTf-^@kx_Jv!@_{ZhbL4cdAG%+KStv
zLJ8FLsJvb=sv;>}C`mwrB|ZvdPGr^H9mFgMU7<rAXsp`Wk@8XysFiRp-3;>sR7zTK
z@cRf1r~Vz@cHE00c;3!yO^1ArRi6<rslA@J-;#5B#u4ITW<~rXx3;SbUg|tL{EfIm
zAGMmRO}7Bv-*w{LgYx2+owv_Ta~r3BuU1pm0~6I-JS%`F)CV@T_Oiv_?Vrny+uWt3
z5UoZad8Rq$tonvEwhZ5|Cp^IvCqMX+>!ng8TVx#<%_71Y5f}eFucT&o^*diN3S^SW
zDWFlcXK7PyO^_AZF$ewbu0#m+`Nw-dQGM^U)*#ouk`u|OS0M@YiWW&BGPu^8^3N^o
zj+G~~p;r09wm3S{4DC;5)urrfK429S{f6amy{2d2T@?ZV*n(YD6f(oNM>93U-4_g9
zy760m_6K^kro!frUAVvK45NM0(LX*XRy+n7uiVBo2|+U@)sH#+WFN=79;D<cIy_&-
z`)|<D&%~D+gw+%|EGm<T<Eq&iGoJ~{*nG8_q(=^0Jaa$1XD(tsct;t}kh*D&d%xRf
z=+AmpK0K#oNaKM<J{c&ORN}#>&`)fx+mKjevukg)C{cW_d!hhIoafH2)T`yOh!?3Z
zZ2!m&I`H75DLWoj3fs*ZJ*E+7g1e=is|$h+O&WN&UT+WAX%f|RzgSApY8uN?9~`i6
z?}U!ua0&2BRGgksZ)~40u1ajMnJ~<`tQ!I4cwjcT%_paKabz56Y&DX-k&<b|Fd&-7
z_F9N?a)QnHsqR&u3C$2);v#s4I_?15-zFyDxHdPKAU1^SK|Ns6B@#svghY4dfSwvx
zDdby<Oic@ZF{wDti4wRl;m0$5rb%#Cc&G2j3Rx-^*_*<)UZ<s{_8J)=FTxE^0W2dT
zYla(jD(PqERJOq4%H}6+8<#VmbBPWfw<*k;WhdqSU|GiID@bL+piW;({5FQSFktcH
z$E0eqm@9-SV9JvJsZZpc-+Zjr_e2{jP<?_^F2Y)7LO;qpzjM2#Y4gY`3&@EAkAe;?
z%Nd*_zC1zy<K5-!m0Rs{T4^9HVtm{LQOihr<oH~f_2GxEhYQ`j@e{SEjh6v54WDdC
zmnuu|!iYM9beHr`4_CSA<>Cc2qlVTuqj=0sKRwEe)>Z61cu4_*Vhm;v%qGegIk8Of
zMY?2r$$m-=-liiZV|sVD-!;1>WPZ2WUXW9?=ESf@Lh%Aw7FVgTBN6B|o#hI9u|f+e
z{a~$}PPuZ90iU8mt^St%t)Z&;!||j9mQu0r<xhdwOJ*^VS-XfT^=7|YjJnV3JcC3u
zR=r-RT8I=YBWT&C+>ZK-)IUW)NO{8(PU%aL9L4Q>CaRKoxs)%9s!j-=MbA|YGoA^P
z6PTPJgz#!U#$xT>1eMFnh?7a@xvWBn8;SU&(Eojgk@K$m<Ga{b42^j}l~pR*kE%NB
zukXg?xLnOJP#LqJh==<(a=;z&ht1T;u2GAG{-0S^Il<@{4oCd9X7SL$KZX#sTnzA`
zT*!}~dPATaodglV@vlj8jaqi9m+ui}E089(u?(dmPF*|1l*io0or{M*d(zu3G;rv<
z`D^obE5(U;6mfNTol{p?pH+l(MF|kz%lUCalL9OSpD+wUX9B{7Z*sV#met+}Fur!h
z95(_UKQT3LT&CpPH`1v;Ap}1)fp`J6o!;aetLocKCldI0K#l^#uO`Ifs*W$KAGnnb
z1w<S0r)JGuR?<6Kn%nhrjxN};-mbqj*(v6QxMI&_i@>uJkDGttOhf}3_Fo<T&fev6
ziSvT6krH!O1sqD*9~+w0nR3!-%{-9(5rjrvO}r2W9cwTGQ5Qj2b(ib>Ur_AoU(C3C
zQ}^I8ag(x3C05U@@QP9^#yhw=(Q1U4o%j6Zhe+R->p`#;)DM<d5!NrBSOE2Q{ADnA
z!r0;TcG!UzsCsS%z||n+H5DEl5{Pe&%h4r&RvH#z_fhvYbL>n~<A6GNRziQ5uWb5Z
zT;madw0RRbW_xdlBTeqL5Lu%sK-&H}V#u9e-+LOA1&Zh0OE5;HOFc`88J+ta{`qjo
z&$A|e=ULNKO|)K5cH7>ywe&*3<f~3PPf&1bK#ZMh1rDnbyhUv*w;@+lK|}Uc*4$KQ
z6IFgoO(X1S=Y>`u7g!l8Y+XZCwH_3k)^YVR=X+m{%fGMN*sj*Uq6C4<%zI}Ws|`3{
zQ=IfVG`o}YmSt|`vj6C+ZA_ZF1&MN0+8Ibwk4q>DdK-y*thz<zI79|e$m8Rh@gtEt
z_AL(Lp4E9cj%DR?E}X3Lcx|QVVLvw$6fB@_&a@oMcjfd#c7)j68aG0Q(@=E}@JRS;
zg*{j=E{ARrGhLrlk;jNj7ju6Tv8(c4VOtb4rSuw_Dy-9}G>_4ZFIXGI?sJmv*+>rs
zoF1~$WF!}l>nb|+&B2}4J9f41aEmjdKN;{dmaR;g+REKpp=EUd)nQ<UU=`b~!25-J
z4m8zO8R5&4=qCz*!Fpb8B|YifB!7F2zDOl|$F^2AQqYw29=j>7^b~<C;W&isN4|eM
zwEp@Pi;6?Ob_~8CU<{!d#gT>1)6h(cjrr}Jt=5tLi5!yAdl}cbrlfY5XP3XIX7ZUG
zIFd8f@027865--fRf-S;&m>+#`D!|0BFz_J-%J+;qB6yV4@mAB&KGZVH@qTvrQa0C
zis40MKLBHtR~5nDu5~%=JVD>4N|o%n?bQTG8C7~S1#*fMvBL{N_nMfM4d^QUygXd<
zw5ik>^NiPx(430&0v*$n!F)Xfk(cN6jkpUTawMVkWwN!KWb1GsfE9k?4pZwdFcA@3
zzrbB?pJ5ksEy~R3$L)6IrLs=Ccf1y?x<AB7k1f7S)H>GrA6hfV^yu^?o6afqKf7?d
zbm!7My>5k$0Dr%!>bTJ1J3h(JYh9f_#pxxz`HFyP`_@|%2E8+V_XhXr8FfD&sGp*y
zdMrfh7M63{MG^)G2|VKbqoIw3h~tAY+g8<k%Ec#$dIF6)TSAdRK1Q#?xz@n>iSBmB
zI8UHpqMK7G+tJDmC@8STE|JOVi*Dx8vs-z3geKfk{)FTsYKqo!-J+RwxDVQJ=B-XK
z@z7x?TcFTu@?O`n-Kjo*InEhg0y7wg>2hkmH+aH3QXR}$y!YE4Wi_2<NfYvqo-O+5
z5g!(-1tjVg1?C&^Cc+EUmVrVLSIVuyrDW-QhG5M5Yka;!N;DHjTo3fe%UtwkWu}Kq
zYYityo{UDoC%q(oAdM@#`J0Fjv(R<|J&DC|FTxyIhP^pFPf87rNv)EnK5T<MQEff}
zQaK1S^dny4f}G=Wwks69@}=DM9&b+S6oNF7S>+YzuE{|Q(@}+pB&7KQXM7@1Srzei
zPcrTtMCwp?-dbFK|Ev>O0{H9#2I_h9Ossc*s~v_F^rz{>3AbIV5zmg?l+?U?8Va<)
z=(drN&^piJh$KG4_ewxbp?hpE>zV|JWyZv(Mec!YxgEaz0yExf=?8Yj?yINEm+e>I
zRo?eIQdQia=z4rB0tYAzqCC~y4wW3q9f3iBxiQD4sxit)#qJTC%JBy9fOD<MT}Ru+
zgwU%|D8ra$*icY#p}`ZAQhE#!`W3=vD|cv5Zx=ewmJ5ku)8cSEHGpLNv~Ouww983&
zUj}XwnH!Sf);`1V)wrjNOx(l0>=>t=yGPeUeD9E*Z#sZJ*a61>l~xf5rkfQ9zo!?w
z1x6l0pR6y?7G9XwkSeTzw$)mgazWXIOjMIJ<1v95;a<TSO?x!(rl%%ruJ0wCWexSs
zr_9!ra9YclSOk|zD`UHI%9z%Is_$w&oxwUs84ycE?}TqM8%yF?R=hYYKP+l+KTVDC
zN4exSt{9bP={({@F&TXlJJ~vZdlP9?ZOWPP0?Kw;lD7-x-<|^hO%HK+k-z7#so6%@
zr_)qjT^ni`4bGM-b=UZlz(aA}+|eAtRTk$jcVbWf&e1q*EZttLjh_Nr@9^t`+tO>c
zljKi-%S{U6b=d^;W|>q7rIC}DBhtB@{w*&NeMUAp9}|b;3H^JLs6?-oY#N?vs9HWp
zt>>u2k5(#m{~P~NiX!?<37FY8)NY8W#9a#I&O%L051C|h%{y-O%@@d6Jbd~e(XgZr
zq5p+SmH$3U^ly64SyWBb#ljTU2)XXwe6W_!CPjTt{_XugB{FGYO<xcE-%y5MO(Rk;
z-BRcN8?O6*UsY4s9FUtc=|EAy=5KPIVu(_P^uXM`^n!z0)J?|hzVjh<St}PQhUoWb
zTd(#&DWcxzCH#rJQG~0~fUH-1NkZuw>xGN9lj+$M6xv$e=P3vg0o1=J@sc5JXNgGK
zSb7S=yNX*BT82|n*99a-&xvv&bpGaz{BJAx`R~d2pA|&Q(&RLip|48bys%?!eE2pl
zs}UHSV~UoUXYThx!fb00^ee-x|E8&gY`6N|X1vf7B}2pvuf$$KLZc}{6m<|ud0t7U
z@x?m$i-!@SJc2V@we`y8_$rFNZ!5M#%Ji!cjoEqq{^<l``J=6(r8T3jD`-B16|cZ&
zELg(??054?n4Pm{G-N9nO}ZQDx$<1m^4d2_msQ^S;T8DXo@V)Yeex2W#Z#aqZo`y(
z(|ex0Vt|zkR&{x0;(3<?Pm+-~cpHko5a9NJ=zg}e%cTVEfrbaOT?K-QPbw0OKg{#@
zj{fv-&`Vs*<(6?H$HYSN9L{2QRF3AgkQZk#cZsRc*WTk>_yM%_@z!wI;OEyXhgkAO
z+<773^O?W$b(fGR-^I2Nkk{QfE}U*5(;~T^gN7XcyJD!ahQB)0%bXzX@j5Rb?l=Q!
zxOiToeV4w_UB52x4%OQYl0fzWcx~IYFc1ZNb-C!AL~k;xG;|&_$4uYPfMtvmSa2PR
zcwc@rRP*xcm9Df4*{Z5ZyiT=q`YIkNrjE-!H>|Xx%^sg^XP=(lN}|%TXD*1Ei<d-2
zJUv;~Nnn~C)unK_HWN3zl|y3~id<1K2$eDep(Lxu#Y29h%5>;YCRT~t^PbUk_JdCJ
z7-U-Vn^$(&(i<PD-2Z{7-4?%=Bn1)-9t_0t`e0VQqrbf?>7;5KX{s>6vR)2qTlLhi
z65Nub%!hE{=|r<9^sQ2QGM8qQm)ICtt83xb2tk~-6khmMhv9;Sg-G*p25Dgt*FOpv
zS^g|lgku=10aU*@w5o;}zOxNB8H;XT+ZcRtL!vZnmuI>nZKJ)d);u=vssKlOa&G0t
zLqCE<>FZ_Y!$E0=U5NP6t`eFya+RqDBb0t>1laW$13wO(yY5e;zf>NcF3{Si66)9e
z9jU3DPa8dV??kF4tt^p*-BI4sqa2a(jeOW`Prt}WRn2FE`{8bO0j1KY%@6O?wPIP)
z|DhB|q%x_xM$sdj&G61u`Lbh0dRpAWLLGW&iO?*vB;owCAdz6ruUv6<=0EOU^@Ohh
z2j}(U4Ag}oM@A3|!1m2|iw-;dtSUkGe>yLvA?dXd@}atQrAACb(pq5IBG}6=?vHtL
zV>mz_1Gn~@eRFy~!I1|o0G{&!fY5FITh}7*3Vce*tkGN074O;`irSJHHt^2|s<P;o
zk_ArZsl{ipljS^A!qWf+i!K>`r)r`n#JH2k!6bXi5CcEyNUF01xtk~Dcge1oUJ(n(
z0ZLJEq;6B8+2<)G;}inmYesEMqbjzF0q<w@v+Uf`62S5mfwiLrAA)^{J#wWzpU*uZ
z-mK_>rtrs^DOLTp!#tH6HZaz2hu?HbZE?<bD@oXIBYV#kH|C<s^nc>^G^Y!?&grZj
zZ8XP)OY1xB7QJZ?cE0NOG+-6u5N^$A5ao$qABl54aZxsSHW}Y_?ef&nW1kcI0a!CM
zAs@I*xc~%sy<12t&|W+0`xLb*$vF936?bV`Nfq~{q`m4atJ~1-SuFx?%A8!|DgP$1
z$%@W@cv&LwBzNG#s8&(XH1eGu32q?y#vx!NxG>i#>&*j~74{NxB>TNfZf<?r;pwMD
zUyf0%AtU~XOpw%IQ<*l<Zh18CkLnmYrzv*xg)Vb*8x@@zJqQlyiJ~bv6x{DMB$xi}
z(23)>_1@7m@db(bUc-b|36*IdHksTS?6s8VleFix|3~jge#5q>-nVEGJ{c?{#`--%
zY<$a8+)1d+n}W$=>^_VTRX$8rPIi){y%AO&-0TqR1!iKB9`R}F<}(y@>$(onUY_3<
z!qdekIn0K?Qm?+)-ta-m$^9AdewcNNeRiG{c>cVE(i^#pk{8CZI=32mx;m3Q?+kHo
zEG9_{DY?=Y_wBD#mA&|}uv|_(`MgUgtqfsq={$O4!2s3A1eRA;0SO~>k3$0-$~<Ls
zMvPR~@@YpMupt-yp0asdOb0n&k5v|NE<5guR||_2nfkQpd<3a|zA94kcW$2~Evjy6
zA6K_t(tsOVY)P4BSCsQ{^d>zJ1AjNJKlzhgA7y*DWzDVlNxGivS9v(+W4l9h6`eO%
z^2TdMn|h$>{BK+fqt`VC(#~BbSHwK*L3<y2_?fz_ZbMb|7eX!)Z5BOLwVJD{em043
z`yxG5R8^n9y%`JWiFaMqv%LCMv|A{$RqVd8YTf?ncBWxg^TQ;Pw8&_`F7*9ET0$s|
zBX^R9(|fu5C}Oy0@l8GVOz5Fb%R0N^<WK+KF;KYkw)b7ncNKcsKcujb($e-U!cBUk
zk<qberiIcPs+wr0g+sA8;udJD9M#{EdW)m?@*%X2_z!1+9kbMAbzu~1Q}3lCtnl98
zgke!tm5ZvrB<3oyE_7DT0#?1;?b%ils1W5<xxfgVfNX#ZS96&h?>=1#+Um=)+QICh
zyYJGyZBtD<e$DIm3m7nPjGx}ReeH_H;CYIkEA}p<g6B~U-3<!t432BxelBeY6r1QZ
z06l9(o;wv8@4vNwm&kVGU_qdQuWTz@Sji>9#uh*5c)3qhuS1vL?+O*S($(|568Ag@
z^^ZbiBo@u2^|x)%GsHY}-eMj`R}jY#F5Y#+9^w%OBC|v$!qn1vwKRU#qC|?LC~N^I
zBZZF3cTvS&ZV<g!$6@wx8SGcmd>OwL$DgRG6T@Nuv-4M9637((>HTzz+Tg0E>c<Ca
zkP>+p!E7ougHTegSsec`p9?3s_Rm=X>RvX$PW9vV)<b@kQrgQp!{WRDgrYR=xTL==
z!EWn39sMUrGsJi>za_Wl#^UBB;b@bk1C;?m6TY0j#h3?TerfIcF7tId%@pQunOl^<
zKM`MkRjZf1=S-iKHkd*j8<C)97b<<r>)g!vj#){;Ks?}j$MAz^1Du}k#@mC+*{F3p
z4ni-xrX1E=hS$nIP^Wo|y&ff>E+gSwznhNP62ZJ?p^gb15&V$iXC}Fudb{>%YGuh%
zoY#A8k?lw)mh-cW*pMr3Uv^rnP88`!4A`A5Uw38rs1{$bCf=o`U`i8_d&O8iGu4IC
zicfGQLTk`d>>QdNDqsAp)c|3UKT`sVL^|L+hKTw7j_|SEsgL|f#O+3DN_SVl`6)$e
zw!{n$@dYRM*Usr7LrR`)?zMU)zvRF1=>UFdfyugFo1CY~0>?w}UpAz}oVvN*Mu#XS
z=LL{F1$C}>kQuOt=4pO~_$axE%uZK4Amm%|6c66hDdAAjVYQ;|hHW}uZJ98=vmJxZ
zHl}Mz!+zsFb8i+C{?nzns@Cct@rhJ;+vf+-vj8h|>emfM&6-_{Mtc@sWTFki-#<8P
zQr%N^K}|h><6@_)NPNV&p*|o1=2Hx&(F*=T_$j`XjMZN~{5FtNM~hF70$8lv^!gwY
zI>IN`_hQ_rY~p;Oyfbi{t8i>nzMyBE=h}9$UHF&%PKr-f`)}2r($`xDE>;ke&_X#%
zm>`8!nT8(;5C@A~9u9grORPX*p4aGoEH9l#qO^zYmr%a_A0b@aRo(^T-F1OAJgAo<
ztdA3mGt?iu94+&9hot&=WJL^aiK3!W=<jfAiBr+?Z^_1~TvTWLW&$>UKy06pE;&oJ
zv~Mk$j-&60o&P<C@Zc=4M5JIa#v%k~$tuH?RB$A;G#3DZF``m>;zA`t@&EX-T-<sE
zkh5p40)L#dd^#!WWOx_*n5Ywg0g3SCP&o|z@Z@ezY{49G-y7h{VQ}mwNM-7Vf%SHW
zqMDC9tt9y=2yGq68&Auj<eeqNjxkX%MUN}2DZw8!=NvrBq#Y!#eRD))807uB>Gp-H
zy$`f??4_Yy#Id)X$hA14*<^e2S}~(Sxc6Z#W?M``?M)B`{!L@3eR$P9==iVa^cV+M
zN18X9=A4Dn7H`4i8k+0ZTHX5Jyr~d;R%`SRcf0$H<Ez&~+wZ1R0+dgV6rL&S=Jf??
z(Bvt6_BVnE8?Q=c<vviK|1N}3lT5XJnV7>#E<(l&OE7%zW}#R4XVHF3Jf<?-dun7&
z@^1BAheojuA!+f4=F~JfS<x+DT=^nNqL2%U>UHZji`*s++m;Smd=uqY3y7qJJGM;<
z7ET`e|JWtoK=rrOy1?lNA{h#b9}A>&7B3Vo<PIjc@%gX>FJBBX0)QcRyJvX7#l!T8
z`)@;{w53{gO+ODLgWVYghJFwUI@a0f#nRq6CF)O|;X~(?z9>ztOF>EwQbnQ#5tgnS
z3E-DQcB8Z>@_`yw*VL=oFB?YB1`f`jw?3It*qu41bxNyzpCh+lgM1{H-8T5uU1gQ{
zL`AjRoYtigz`BJ$SNUj;wpXo#HBYGnRrbQkpI(h3NaKyQoeLAV&$9QR_q*tERm7L{
zdY**k5<?u{@XG6c^Lo4915aCj=FY`lBL(Ib2>TJ#a%J!%D?2eeD_Wrj6J=_}X%W`B
zZ*Y%YGsPaFpZp2YKdYcDkS$q+Yx;$IWG5V?3C|Aef6HXQFDKf;Xxp@}sB>cZ{d8lu
zr0mNmt;hxB19kq_l7v0W4AX`EuJV%!$6a3=*zyxBWXOFip}3jS)^mZJe)EBwqO~LN
zeOl5j=Qm610G}+Bfk7m2n|v@yX8jo_5{l7p0=@e&OQvP*_Y#5L&aMmsZK_;1$XpWB
zV-(~?(Pz}aQ#U!2Gv4vYprkXg=buPnuBtQ#M#b@2?lL!bIZv_<QjNbFIqsxRxpgJI
z?`!@959Vol>>Z~lVvaBp5WX0k?Ex)B-Hb|6Qci75TwpVdDIYOaL0zheBp(TD6zV&k
z{X;ui(9OmyMZ{Kie@o*;>*q--_6l)9q_Fq(ETw$R_;F(lJ=|g|C-?LL^3_M$+^GWn
zh){>~#M`c?qa?<RTPmO}y^1UI9odGS9?D_2NW+5d&DSjThlk1&;msYo45jRp*<otr
zS)!R?=8dD+n^i>jsICmB;wL7u)jXXQ{IBoNvDd$?{r0fC##-JpQav19jh73UBYtF+
zeeJ(Yw!br80#Q$IFvgXU6Oz?m-(EopPm^Pk)I4G^7)vlGWr(Dz!7iJ)Q(YvNYOH@x
zRL4YWDzAFHT-P8~Z&#n`v-C>1$Y-^TEidxd86y_F4p#&?P}Ng06ga~&<{e(?`@SVn
zUkDgC&WBRFGbGz~D>YYq|EkfFaEr$Fr+ck_*f)cc1;!p;Ecst-^a3{20zF8izb*-O
z^VK4)O7R>qnvZv`st=M6M?k+*9sLm$<l@*LzX0KRlTX58u44rQAn3MyL*2(-C<Wg9
z*8f$@eFrt&t$6^C3MfrQ1*9omdXXj_>7hyqHS{W>89)q35fDW|I)sk&0HKF2il{(B
zk$`|m6+)CMHPY`7-}mm$ot-<gb9eUN%p@~8Dd#+&^L?I5@o4Ip#OkHT`VsLHY$KKZ
z0lKF-<;!0>IO#tn`QHSEQvgFnXdMUlHxnk!0|v~WZVlw_*m<C`_ki><XsLR;<uSrh
z2YAlAj6!}M=1;(>*zaLNK7-`zc9m62yQ-9aDb{%k^{<qmvI^?eX`?^ob>B4M7|8~_
z{Km4XJb)5F#S6-(%>Q@R@!#I_zqN+{VEl;`khxJJzT4mb-a|Bwzo{dCd>W*E9{n$R
zQb0i)3&t~=+f}cJ?$@3MW~i_RAQhVj>niQD(DR>>?mCozgyugQo$`Nqcg0&k>ipjP
zjj!nK9jzR$%!X4qskE=&y`u$X->noiuh$Z282!6vC_hF%9%#xNR<pmX;>6dlYto84
z>4l*DB0@Bn>970jP1<l*`&oh9#cb)PY)J6#wns&HoBNry{9@exvW<g)v($@rVQn>|
zGo<yHWIY~u!T5pXCf7>C@y<?|dDKq4gB@t2x1yk}3tGVu3lm$Iph7UfZ6gOZ=E#VY
zX&Q;Y$GTdf#6b9zoi^~MpIgK1zM@^LS^Y0k44{C_roJs<RMoHrt3a4YutxRH*&e1;
z{alW_e>P9qRq(4U6G$>8glDr^#tNIG0Z%8wd`B3&gstw~TfClDxuPtG72T@$jVhv(
z#jdR&HK^K=2FHAcEQebPc?Afy6_=tW=cdWg%?(780(s<nvUW$4Od0Jh?66eGk<LL-
zoP}w3$e9nXfu$fY7a<4(bcro_foZhlON`gsG$f#rlIzj4J8lYsAFr@VToZjBniIsx
zSUxWMIez&#0?@8I=WL>jdP%0`(Xv_~m5>!d<2ixeqsPC_h#|h8)i)FzZYMV0;iU+#
zuk>qNG-!yPIryj9s78>Y%S4d|S#T)?Ksu*Y{imAy9gC@Ln9uuM@7|piW_1wdO1{M~
ze$L_?HGnD${356=Tt(o9wo^{_-P+5Tb!zsGf0|DKMf*!?NOoE&?OrGR{Ub90GY6s0
z^#=cz0^3sC)NARzscCDhbQEJpPa{re1?g*i^hTtJn3o6G*BSfN9IxkzXrPSj@Ss^C
zZNM{#HQ~Slv+IW`iDD)17B9aj9AS{?E}bg7*8M9~Z3<uh#R&GYX!0^nx2mfIN-M&b
ze6TkGbp5HWRG2<}`|x0Y91A*8*d?+Ha=90?7_&+(B&W_9#0&op>GEwUJeqZ<n4R(_
zUV!#wdIAN;DaR$wx=o4@uTgMyoA}DP!H-o;P&V{wKe0RC)Tp?(FVS53R)iJTN3K8D
z-(IKU{TZ*6;}1+6x=^nKh>v1l=<VG?uJfY+F<x4U{E>Yi)4X0ltr(gpXIOS}Y;%BJ
zyTHa06`JlRuiDY|Ff{6`8(q}G_4*a-1EuHwG_2jj3e&qgv~LFseUfW00W?+lEG$g6
zaSSni-9uUW$=0aCNv5K4)ye)zcPLa<{Z2gn?j!jz(L-^+wNlr3Q+IUBQN|5$Zh6ht
zvz)=(N-IjccGWuyd7ydndc9n#WtD0Hr6j0~`ePlkaKBqR`5lrzNiVb(_~g^R<LsOs
zx<^eoV#-Z5QkYp%Z$1sqc;yHXqT)Rv^EJ(WwjZoaxlMJ(FKR@AmRMP9K?OJ2GH8c&
z>VN}>aSE`am-R^H?ssb?9h+}w7jn+Fz7><~e21jt>p5&M7RYNg>L~S2Sw}VESs+$R
zNI0<4sdal-&>My_=;DU2Ec@SAQO5N)=~*}(09cp_9adG_S{)<8!x3Ap3XokyAf)Uo
z7i2=5{cE<&Z?@NGD)`D@2@(>oGP_x7_5^;EoC1n`ptKPDHZfZIj60xN_3Aer-9XE+
z<uZjlT|8L0mW+9K<xnTLG2O%YJg&$A*l|dr7}jSjm`{+x$-N=lO(*40x7M&{0Wc0o
zNO9_`{GmU)ja8YwHVc2+mb3ZO%r_etszc&?6B!SEJ>~oA#=!I1FhyBm2*9m^jWakp
z3z!K5Cwi@e+1{Siy(Y!m5%6NxR?a1*>VPc0{|P~Nlv2-KY1pRK`h_;=UKDic5b(3X
zZ$GoGWlOJlpWB_}e@|B-X?am_MB^Bg8FDn*Y#=a97k+y;SvB6PX=HXr<YZ^T=L#&l
ztMQ1%BGf$rt_4Q;-kixBxj?-7U5DsNh)sBL^TJ~9FOl4G1i_nNktxb_$>C$BC-~TE
zW>OY(&&Tyw&%~j;y-8J~=n#IAKNC;fB!F?lBYbzuQdsa^9lx1f9Gx}&dd9~z1cqWc
z_BLZJis&0l3XOpO7K6K%zeCQj162~iC}WYfmb+=NestwFY$(i>$ylOtlgmw{t0(E!
zVh>tOUzC(u)~ul8=Y6Z{fLar19a)ttm@H?oN)C?OI4cC!!6)4pUi~6^X%$kXg=L2I
zu8+(yqnQ%e2N$_sz0;>gw<z}>wgHu-I|t;8_BpvFhcMr=E-3+Da4zYsWF({3&bOpw
zIIXr>#*Rh@@Hopi)y>CDn-Q#*r;0N+d~8!|KuVpiNUCeyYx;<E?M;wQns8s}r%WP7
z74PB!CHSIhDRRHN)85w$;FL~~nkm@IQT`&nhC`TuAKO%)*tLkaQ(KwwUX5iZ1_g`x
z{y`VGlkz9u+!fj1n1u`1F1DTYZAQ0HaKpedCt=5aB9ayhb-9sK6R3Rj0;=@`ykno#
z!qd#uB~9KuK{3`9rUU_#lgQ%@(>cufbfv7?hp&XAakZ!<UaK_5;Ri8%eF!0No56Tw
z&T>3%xUqQDV$^5+$Sbut8H*uPkWi!)K&CNFcGt36pUAHCu*s~1N|bqj6Y2FM(5E>~
z-2uJ<x<DJ1Fe@ER5Uq&zkg7G_lK<3jjIAVU8;<7aK+K&ble5&z2~*gOlxHX-pkC!9
z?|VN{@EwvA?6G}O{ZO<%868taqUSHQ;OK9tR5ZVM%-5aRE-z<zx8ntU7jB~*oEG9h
zhF2w#ha+i)YLsUx2a{o6xUC1{k8boOR{-@MdQc$?4*6|llc`G@8=3S+P%VD*h+{gl
zKZkv8cJLC|wnl&=2o{(_bFw+fF;vFna@#`@Gs23aMsWv#Th-wd-q|?aRtpiZVp72f
zRCc?V!JNn4kt8<k-!^$g`-0cRb-bs5-l~xKGcwc?OEBkqtI{^prUr=n>J5|hwe*Py
zv*3rJJn_r${+|h#uRtXl6{7>v3oXYF=QqnV*JTB_kwD?dkCED~j+_52)ptyLRb4#Y
zTI|CGp^xxfe{k!EGBl&{RUORZFm8uNK|pm>ceDIjrQtTHUk8JnX<nQ4<VHutWRXNc
zE3Zyud|aL%0&_F{b4he3Z<=QQz?E4le#Y1dCrhT?eDulwFV=m5JBCPDxilRv-}f6&
z@0U4aTo@+DP{k`&9rIMiA}GW<tdI&;K_^|K;xgD)40-AhR81C6;T-&ct;*3n6Yuq=
z69Mrjanp|xTppZWbqEKdhe>15Fj3!Q#$i@ejc>D`>JF}{9eT-ztz;4GTs5hoS$a#&
z<0oNYRNkhA!6OOZwaZD9Z!6~p`xwM^xzRq^2`Qz5@oqNL3vj&|D<bRE3>7e|4Qmmn
z_|dW^s;4g`w&=5OE)SSY{m<82?i+xb7w!0crfYan_Q!TI>STI7+&={}=`XKzlJ(Be
z2w%TvwHF#!*UH0mMk36Mr+%@&*}IdV0SyeBE|WRzU+7zW)am0d7C)03gBjC=<sZSw
z&P8HS+5PHHa)zzN6q)E~ijIP?la|ZF(m64}s`BfxS2xao_rba!k-<uN?q_34irz+N
zEB6HcNO_3tS6}Uvs)kqeX^aq{4KZ(MHmNCVv=sBgf1J|J9bv<#qb2e=^^og}=KYr)
zwvvHHrQ7EqX}sX$#hF?eYnsLF7__E&SU+ZzZ_lYQsc=Cyd1-6@Zh75_yJtH3p_TAH
z!KaAPA^&v%z#c^}ba1KT!0uN`Pzeny1P34oWH~oWt1axI^T*R7g;K<e&z6thfBtaR
z$u%zHdb1q2wig;vS$Q*f7!@QAOO?{-T9aw=18x>PW%FW>h=>#2Rq-sNSIZ1E$Txvv
zR$kXj3-?zmx(N?3UfC-5)K=~45&4P90u34NeMIozZ1dRO0S=a;7xys<k@`@JA~cVD
z%2XC9iq5t?5QA0ved`}Q0tX1_t^m^0h45E;%`cv`@=W)l*I_x6Vyz@7n*{|g2Is~L
z^x5*^RN?F;mwMB+j5p2=Ot>VOav1Jqa8Hp)u9mv?=mF&$+hfrB66`E8(#au+j>4DW
z`Wpz4E#?@!H?+;Nl!i60aLzM&_$46p9B`b=k0JlmmmcaC%CQHNBWLPQRrQmWLSBqn
zqQg7)H7rM^MN3A?pKmQL2QEOi_fRTTx4H6v#hGRH^TmayZPdN>AG1X$UGlOuX9Rw=
z^u^Lfze`+=e{8^dj^rz?spsYUC-03etOY0=PW+ggY{XLC-yQcK3CUV2d-6)ZVcu9!
z!tm?&obz2|U;21Ia!~HCa;EWMo-5c@BJh=&$9qvF+;CM(pWdY(7>={UAMn>GLCi^X
z<F|tb0!9`$!$yg{Jiuug;a*jZ%rerv4D(4l-P&5Awc80l$AC{95Y>Ulnsgb;z99EI
zS!NX$KjCibl$KtZ)d&Jc@9MzcN|p_n*YuFlO7og1nZAhF;-IMWdgprnC)uo+y{nJq
zgS8bJ%;&S;D30nTr6Hy2Jp1W^ZEv6D)+%^-FcZKQoV9aDnRV97fHtV*zSYZq*Obt%
zR!oA@iGan+N;B7fChOcXpr0J-l-I|xI6szf(DaR<X;7Y2trp23o_#BL)cj76vt)#F
z(};5Dc(dbpiNvr<H}Av)R4SeGj%O9sRZ|Ihi3`K^%M<1i2SvDqSFT>dZicCyCtc*7
zoP$KEq)lr%%?reK`Ml3Xzpnz?x)qb5c*7E=ma-`80rkXwnT@#J0x#957C!@W%a<I?
z(CY5Hwdi@)_WbGDTr%wTrU->!q}LFQb-0IaKB>oEsa`m9u5!+0H}@yjCVz!bSu9Gb
zMg?I1Vn}iUF(}3Kv<6zj7qVR*1E5E~Kh0vM?ar9(C*)X_<^oyuRES3A+#`c>(hl0$
z#V`P8;vF_nP7RzR)By7VpSp{+%U3wxf4PtH%qZB!YKx}-M00-0Sb~RH!aPAbSQw{V
zb;Ak0moQMLGR-Mbicj_GFL4S5GZV`byO}`C4_oTWJr*dFF9}>JWK_Z(hd`{ZN_8Wb
zd=Hu7C%pFufXk-xl};5kA!6^?lWebkpxSlydCZ1Sb{M__VAE>~S?Qryx~s7YE)H^o
z_o8-!otxnD4fT2~p~@}-&Fw1eq{OL41Ge`AB!n*H(@5p-$EWM-KQKx)$XU!lQzvy-
zCuF)Ok8Z)eWLu@Uq*`?BMNkLwtcuV+t^QCuM_OICl=halh4aE5+<-N?N56-wj(75*
zev&G-`xriB4<7L0*IKsL<TZq%o^oBAIH>lr`70;ztFp2iCks+5eiKW1K*J3g&rLSN
zh42oloO_02(-mz9g_0PHTmjS}vOeNH&6I?YhU0T0=|~rWOGOBNoCU*O!VC+jcMEAT
zo_=eZ+A@$!^+4nS)KTjcRs`4Bo->{%P)z=Kj&Y&%E%`FbtQ<s{@7e?CACJ&yc_J=Z
z3EbFv<08%CCrtwy+>X+%1l(>2WW!khj2u!i(K6AI6f5j4LZ8<GTgH8kf&+9}>{*pK
zq6%}w9!1qZnKxEW$pMA8exH8wsI%o_zBn*4Hk>#7UxeiUGhgyI(MW83{4xfla6pc~
zrVN!IUOWq8FA%Nj$OV!wXa6K$X8#(&6BmE8h|Uo31$QB!f&Bn*oqsc?XEWrlRLzIt
ZlS@_ix6S4{Z!w%c0@g54uTr&-_y+|B6pa7?

literal 0
HcmV?d00001

diff --git a/articles/search/vector-search-how-to-create-index.md b/articles/search/vector-search-how-to-create-index.md
index 573c19a496..d66d9a3b0d 100644
--- a/articles/search/vector-search-how-to-create-index.md
+++ b/articles/search/vector-search-how-to-create-index.md
@@ -30,13 +30,13 @@ This article explains the workflow and uses REST for illustration. Once you unde
 
 ## Prerequisites
 
-+ Azure AI Search, in any region and on any tier. Most existing services support vector search. For services created before January 2019, there's a small subset that can't create a vector index. In this situation, a new service must be created. If you're using integrated vectorization (skillsets that call Azure AI), Azure AI Search must be in the same region as Azure OpenAI or Azure AI services.
++ Azure AI Search, in any region and on any tier. On services created before January 2019, there's a small subset that can't create a vector index. If this applies to you, create a new service to use vectors. For indexing workloads that include integrated vectorization (skillsets that call Azure AI), Azure AI Search must be in the same region as Azure OpenAI or Azure AI services.
 
-+ [Pre-existing vector embeddings](vector-search-how-to-generate-embeddings.md) or use [integrated vectorization](vector-search-integrated-vectorization.md), where embedding models are called from the indexing pipeline.
++ You must have [pre-existing vector embeddings](vector-search-how-to-generate-embeddings.md) to upload to the index, or you can use [integrated vectorization](vector-search-integrated-vectorization.md), where embedding models are called from a skillset in an indexer pipeline.
 
-+ You should know the dimensions limit of the model used to create the embeddings. Valid values are 2 through 3072 dimensions. In Azure OpenAI, for **text-embedding-ada-002**, the length of the numerical vector is 1536. For **text-embedding-3-small** or **text-embedding-3-large**, the vector length is 3072. 
++ You should know the dimensions limit of the model used to create the embeddings so that you can assign that limit to the vector field. Integrated vectorization supports a finite number of embedding models. For **text-embedding-ada-002**, dimensions are fixed at 1536. For **text-embedding-3-small** or **text-embedding-3-large**, the vector length ranges from 1 to 1536 and 3072, respectively. 
 
-+ You should also know what the supported similarity metrics are. For Azure OpenAI, similarity is [computed using `cosine`](/azure/ai-services/openai/concepts/understand-embeddings#cosine-similarity). 
++ You should also know what similarity metric to use. For embedding models on Azure OpenAI, similarity is [computed using `cosine`](/azure/ai-services/openai/concepts/understand-embeddings#cosine-similarity). 
 
 + You should be familiar with [creating an index](search-how-to-create-search-index.md). The schema must include a field for the document key, other fields you want to search or filter, and other configurations for behaviors needed during indexing and queries. 
 
@@ -50,9 +50,9 @@ Make sure your documents:
 
 1. Provide vector data (an array of single-precision floating point numbers) in source fields.
 
-   Vector fields contain an array generated by embedding models, one embedding per field, where the field is a top-level field (not part of a nested or complex type). For the simplest integration, we recommend the embedding models in [Azure OpenAI](https://aka.ms/oai/access), such as **text-embedding-ada-002** for text documents or the [Image Retrieval REST API](/rest/api/computervision/2023-02-01-preview/image-retrieval/vectorize-image) for images.
+   Vector fields contain an array generated by embedding models, one embedding per field, where the field is a top-level field (not part of a nested or complex type). For the simplest integration, we recommend the embedding models in [Azure OpenAI](https://aka.ms/oai/access), such as a **text-embedding-3** model for text documents or the [Image Retrieval REST API](/rest/api/computervision/2023-02-01-preview/image-retrieval/vectorize-image) for images.
 
-   If you can take a dependency on indexers and skillsets, consider using [integrated vectorization](vector-search-integrated-vectorization.md) that encodes images and textual content during indexing. Your field definitions are for vector fields, but incoming source data can be text or images, represented as vector arrays created during indexing.
+   If you can take a dependency on indexers and skillsets, consider using [integrated vectorization](vector-search-integrated-vectorization.md) that encodes images and textual content during indexing. Your field definitions are for vector fields, but incoming source data can be text or images, which are converted to vector arrays during indexing.
 
 1. Provide other fields with human-readable content for the query response, and for hybrid query scenarios that include full text search or semantic ranking in the same request. 
 
@@ -69,7 +69,7 @@ A vector configuration specifies the parameters used during indexing to create "
 
 If you choose HNSW on a field, you can opt in for exhaustive KNN at query time. But the other direction doesn’t work: if you choose exhaustive, you can’t later request HNSW search because the extra data structures that enable approximate search don’t exist.
 
-A vector configuration also specifies quantization methods for reducing vector size:
+Optionally, a vector configuration also specifies quantization methods for reducing vector size:
 
 + Scalar
 + Binary (available in 2024-07-01 only and in newer Azure SDK packages)
diff --git a/articles/search/vector-search-index-size.md b/articles/search/vector-search-index-size.md
index 969c69366e..2aeaa87008 100644
--- a/articles/search/vector-search-index-size.md
+++ b/articles/search/vector-search-index-size.md
@@ -10,7 +10,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: conceptual
-ms.date: 09/19/2024
+ms.date: 01/09/2025
 ---
 
 # Vector index size and staying under limits
@@ -27,7 +27,7 @@ For each vector field, Azure AI Search constructs an internal vector index using
 
 + Vector index size is measured in bytes.
 
-+ Vector quotas are based on memory constraints. All searchable vector indexes must be loaded into memory. At the same time, there must also be sufficient memory for other runtime operations. Vector quotas exist to ensure that the overall system remains stable and balanced for all workloads.
++ Vector quotas are based on memory constraints. For vector indexes created using the Hierarchical Navigable Small World (HNSW) algorithm, searchable vector indexes reside in memory. At the same time, there must also be sufficient memory for other runtime operations. Vector quotas exist to ensure that the overall system remains stable and balanced for all workloads. If you use exhaustive KNN algorithm, indexes are loaded into memory only at query time.W
 
 + Vector indexes are also subject to disk quota, in the sense that all indexes are subject disk quota. There's no separate disk quota for vector indexes.
 
@@ -67,11 +67,24 @@ A request for vector metrics is a data plane operation. You can use the Azure po
 
 ### [**Portal**](#tab/portal-vector-quota)
 
-Usage information can be found on the **Overview** page's **Usage** tab. Portal pages refresh every few minutes so if you recently updated an index, wait a bit before checking results.
+#### Vectors per index
+
+To get vector index size per index, select **Search management** > **Indexes** to view a list of indexes, along with the document count, the size of in-memory vector indexes, and total index size as stored on disk.
+
+Recall that vector quota is based on memory constraints. For vector indexes created using the HNSW algorithm, all searchable vector indexes are loaded into memory. For indexes created using the exhaustive KNN algorithm, vector indexes aren't loaded until query time. There's no memory residency requirement for exhaustive KNN indexes.
+
+The following screenshot shows two versions of the same vector index. One version is created using HNSW algorithm, where the vector graph is memory resident. Another version is created using exhaustive KNN algorithm. With exhaustive KNN, there's no specialized in-memory vector index, so the portal shows 0 MB for vector index size. Those vectors still exist and are counted in overall storage size, but they don’t occupy the in-memory resource that the vector index size metric is tracking.
+
+:::image type="content" source="media/vector-search-index-size/vector-index-size-by-algorithm.png" lightbox="media/vector-search-index-size/vector-index-size-by-algorithm.png" alt-text="Screenshot of the index portal page showing vector index size based on different algorithms.":::
+
+#### Vectors per service
+
+To get vector index size for the search service as a whole, select the **Overview** page's **Usage** tab. Portal pages refresh every few minutes so if you recently updated an index, wait a bit before checking results.
 
 The following screenshot is for an older Standard 1 (S1) search service, configured for one partition and one replica. 
 
 + Storage quota is a disk constraint, and it's inclusive of all indexes (vector and nonvector) on a search service.
+
 + Vector index size quota is a memory constraint. It's the amount of memory required to load all internal vector indexes created for each vector field on a search service. 
 
 The screenshot indicates that indexes (vector and nonvector) consume almost 460 megabytes of available disk storage. Vector indexes consume almost 93 megabytes of memory at the service level. 

From b18a401bc9773057147548fedde29f27cee0e76a Mon Sep 17 00:00:00 2001
From: Aaron Hill <aahi@microsoft.com>
Date: Fri, 10 Jan 2025 10:29:35 -0800
Subject: [PATCH 2/7] updating rest api

---
 .../ai-services/openai/includes/use-your-data-rest.md | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/articles/ai-services/openai/includes/use-your-data-rest.md b/articles/ai-services/openai/includes/use-your-data-rest.md
index 2827c5d4bc..bf88d10a3e 100644
--- a/articles/ai-services/openai/includes/use-your-data-rest.md
+++ b/articles/ai-services/openai/includes/use-your-data-rest.md
@@ -5,7 +5,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 03/07/2024
+ms.date: 01/10/2025
 ---
 
 [!INCLUDE [Set up required variables](./use-your-data-common-variables.md)]
@@ -20,7 +20,7 @@ To trigger a response from the model, you should end with a user message indicat
 > There are several parameters you can use to change the model's response, such as `temperature` or `top_p`. See the [reference documentation](../reference.md#completions-extensions) for more information.
 
 ```bash
-curl -i -X POST $AZURE_OPENAI_ENDPOINT/openai/deployments/$AZURE_OPENAI_DEPLOYMENT_ID/chat/completions?api-version=2024-02-15-preview \
+curl -i -X POST $AZURE_OPENAI_ENDPOINT/openai/deployments/$AZURE_OPENAI_DEPLOYMENT_ID/chat/completions?api-version=2024-10-21 \
 -H "Content-Type: application/json" \
 -H "api-key: $AZURE_OPENAI_API_KEY" \
 -d \
@@ -31,8 +31,11 @@ curl -i -X POST $AZURE_OPENAI_ENDPOINT/openai/deployments/$AZURE_OPENAI_DEPLOYME
             "type": "azure_search",
             "parameters": {
                 "endpoint": "'$AZURE_AI_SEARCH_ENDPOINT'",
-                "key": "'$AZURE_AI_SEARCH_API_KEY'",
-                "index_name": "'$AZURE_AI_SEARCH_INDEX'"
+                "index_name": "'$AZURE_AI_SEARCH_INDEX'",
+                "authentication": {
+                    "type": "api_key",
+                    "key": "'$AZURE_AI_SEARCH_API_KEY'"
+                }
             }
         }
     ],

From adb00644d83666351c0d307204e111787853f604 Mon Sep 17 00:00:00 2001
From: Aaron Hill <aahi@microsoft.com>
Date: Fri, 10 Jan 2025 10:33:12 -0800
Subject: [PATCH 3/7] rest api example

---
 articles/ai-services/openai/includes/use-your-data-rest.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/articles/ai-services/openai/includes/use-your-data-rest.md b/articles/ai-services/openai/includes/use-your-data-rest.md
index bf88d10a3e..1098b17a22 100644
--- a/articles/ai-services/openai/includes/use-your-data-rest.md
+++ b/articles/ai-services/openai/includes/use-your-data-rest.md
@@ -84,7 +84,8 @@ curl -i -X POST $AZURE_OPENAI_ENDPOINT/openai/deployments/$AZURE_OPENAI_DEPLOYME
         "prompt_tokens": 3779,
         "completion_tokens": 105,
         "total_tokens": 3884
-    }
+    },
+    "system_fingerprint": "fp_65792305e4"
 }
 ```
 

From a3f8a9d69abd5cc44aec111b084060fae08cc106 Mon Sep 17 00:00:00 2001
From: Jordan Bean <84806584+jordanbean-msft@users.noreply.github.com>
Date: Fri, 10 Jan 2025 12:34:12 -0600
Subject: [PATCH 4/7] Update configure-managed-network.md

Fixed typo in call to `az ml workspace create --provision-network` command
---
 articles/ai-studio/how-to/configure-managed-network.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/articles/ai-studio/how-to/configure-managed-network.md b/articles/ai-studio/how-to/configure-managed-network.md
index 18525a9bb6..1572d583cc 100644
--- a/articles/ai-studio/how-to/configure-managed-network.md
+++ b/articles/ai-studio/how-to/configure-managed-network.md
@@ -634,7 +634,7 @@ During hub creation, select __Provision managed network proactively at creation_
 The following example shows how to provision a managed virtual network during hub creation. The `--provision-network-now` flag is in preview.
     
 ```azurecli
-az ml workspace create -n myworkspace -g my_resource_group --kind hub --managed-network AllowInternetOutbound --provision-network-now
+az ml workspace create -n myworkspace -g my_resource_group --kind hub --managed-network AllowInternetOutbound --provision-network-now true
 ```
 
 The following example shows how to provision a managed virtual network.
@@ -654,7 +654,7 @@ az ml workspace show -n my_ai_hub_name -g my_resource_group --query managed_netw
 The following example shows how to provision a managed virtual network during hub creation. The `--provision-network-now` flag is in preview.
     
 ```azurecli
-az ml workspace create -n myworkspace -g my_resource_group --managed-network AllowInternetOutbound --provision-network-now
+az ml workspace create -n myworkspace -g my_resource_group --managed-network AllowInternetOutbound --provision-network-now true
 ```
 
 The following example shows how to provision a managed virtual network:

From 108ca94e1f0ff1df178326410dcd4cc13d59aad2 Mon Sep 17 00:00:00 2001
From: Heidi Steen <1612796+HeidiSteen@users.noreply.github.com>
Date: Fri, 10 Jan 2025 10:36:20 -0800
Subject: [PATCH 5/7] Robert's feedback

---
 articles/search/vector-search-index-size.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/articles/search/vector-search-index-size.md b/articles/search/vector-search-index-size.md
index 2aeaa87008..f745610a68 100644
--- a/articles/search/vector-search-index-size.md
+++ b/articles/search/vector-search-index-size.md
@@ -67,17 +67,17 @@ A request for vector metrics is a data plane operation. You can use the Azure po
 
 ### [**Portal**](#tab/portal-vector-quota)
 
-#### Vectors per index
+#### Vector size per index
 
-To get vector index size per index, select **Search management** > **Indexes** to view a list of indexes, along with the document count, the size of in-memory vector indexes, and total index size as stored on disk.
+To get vector index size per index, select **Search management** > **Indexes** to view a list of indexes and the document count, the size of in-memory vector indexes, and total index size as stored on disk.
 
-Recall that vector quota is based on memory constraints. For vector indexes created using the HNSW algorithm, all searchable vector indexes are loaded into memory. For indexes created using the exhaustive KNN algorithm, vector indexes aren't loaded until query time. There's no memory residency requirement for exhaustive KNN indexes.
+Recall that vector quota is based on memory constraints. For vector indexes created using the HNSW algorithm, all searchable vector indexes are permanently loaded into memory. For indexes created using the exhaustive KNN algorithm, vector indexes are loaded in chunks, sequentially, during query time. There's no memory residency requirement for exhaustive KNN indexes. The lifetime of the loaded pages in memory is similar to text search and there are no other metrics applicable to exhaustive KNN indexes other than total storage. 
 
 The following screenshot shows two versions of the same vector index. One version is created using HNSW algorithm, where the vector graph is memory resident. Another version is created using exhaustive KNN algorithm. With exhaustive KNN, there's no specialized in-memory vector index, so the portal shows 0 MB for vector index size. Those vectors still exist and are counted in overall storage size, but they don’t occupy the in-memory resource that the vector index size metric is tracking.
 
 :::image type="content" source="media/vector-search-index-size/vector-index-size-by-algorithm.png" lightbox="media/vector-search-index-size/vector-index-size-by-algorithm.png" alt-text="Screenshot of the index portal page showing vector index size based on different algorithms.":::
 
-#### Vectors per service
+#### Vector size per service
 
 To get vector index size for the search service as a whole, select the **Overview** page's **Usage** tab. Portal pages refresh every few minutes so if you recently updated an index, wait a bit before checking results.
 

From 1eea3b53b1eef4c043b404d7008e1e10b58b6f0a Mon Sep 17 00:00:00 2001
From: Shilpa Sharma <v-shils@microsoft.com>
Date: Fri, 10 Jan 2025 11:26:31 -0800
Subject: [PATCH 6/7] Fixed typo

---
 articles/search/vector-search-index-size.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/articles/search/vector-search-index-size.md b/articles/search/vector-search-index-size.md
index f745610a68..1a4a6789d7 100644
--- a/articles/search/vector-search-index-size.md
+++ b/articles/search/vector-search-index-size.md
@@ -27,7 +27,7 @@ For each vector field, Azure AI Search constructs an internal vector index using
 
 + Vector index size is measured in bytes.
 
-+ Vector quotas are based on memory constraints. For vector indexes created using the Hierarchical Navigable Small World (HNSW) algorithm, searchable vector indexes reside in memory. At the same time, there must also be sufficient memory for other runtime operations. Vector quotas exist to ensure that the overall system remains stable and balanced for all workloads. If you use exhaustive KNN algorithm, indexes are loaded into memory only at query time.W
++ Vector quotas are based on memory constraints. For vector indexes created using the Hierarchical Navigable Small World (HNSW) algorithm, searchable vector indexes reside in memory. At the same time, there must also be sufficient memory for other runtime operations. Vector quotas exist to ensure that the overall system remains stable and balanced for all workloads. If you use exhaustive KNN algorithm, indexes are loaded into memory only at query time.
 
 + Vector indexes are also subject to disk quota, in the sense that all indexes are subject disk quota. There's no separate disk quota for vector indexes.
 

From cb333a45c55dcbda0bc0c8eb93677b9e3dca2d94 Mon Sep 17 00:00:00 2001
From: mrbullwinkle <31510320+mrbullwinkle@users.noreply.github.com>
Date: Fri, 10 Jan 2025 15:32:30 -0500
Subject: [PATCH 7/7] update

---
 articles/ai-services/openai/api-version-deprecation.md | 7 +++++--
 articles/ai-services/openai/includes/api-surface.md    | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/articles/ai-services/openai/api-version-deprecation.md b/articles/ai-services/openai/api-version-deprecation.md
index 797cf83093..9b62f584c3 100644
--- a/articles/ai-services/openai/api-version-deprecation.md
+++ b/articles/ai-services/openai/api-version-deprecation.md
@@ -5,7 +5,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 01/08/2024
+ms.date: 01/10/2024
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -25,7 +25,10 @@ This article is to help you understand the support lifecycle for the Azure OpenA
 Azure OpenAI API latest release:
 
 - Inference: [2024-12-01-preview](reference-preview.md)
-- Authoring: [2024-12-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring/preview/2024-10-01-preview/azureopenai.json)
+- Authoring: [2024-10-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring/preview/2024-10-01-preview/azureopenai.json)
+
+> [!IMPORTANT]
+> For features that are part of the dataplane authoring API such as batch, fine-tuning, and assistants files, continue to use API version `2024-10-01-preview` to take advantage of the latest preview features.
 
 This version contains support for the latest Azure OpenAI features including:
 
diff --git a/articles/ai-services/openai/includes/api-surface.md b/articles/ai-services/openai/includes/api-surface.md
index 80acca3393..ea8fe27a03 100644
--- a/articles/ai-services/openai/includes/api-surface.md
+++ b/articles/ai-services/openai/includes/api-surface.md
@@ -22,7 +22,7 @@ Each API surface/specification encapsulates a different set of Azure OpenAI capa
 | API | Latest preview release | Latest GA release | Specifications | Description |
 |:---|:----|:----|:----|:---|
 | **Control plane** | [`2024-06-01-preview`](/rest/api/aiservices/accountmanagement/operation-groups?view=rest-aiservices-accountmanagement-2024-06-01-preview&preserve-view=true) | [`2024-10-01`](/rest/api/aiservices/accountmanagement/deployments/create-or-update?view=rest-aiservices-accountmanagement-2024-10-01&tabs=HTTP&preserve-view=true) | [Spec files](https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/resource-manager/Microsoft.CognitiveServices) | Azure OpenAI shares a common control plane with all other Azure AI Services. The control plane API is used for things like [creating Azure OpenAI resources](/rest/api/aiservices/accountmanagement/accounts/create?view=rest-aiservices-accountmanagement-2023-05-01&tabs=HTTP&preserve-view=true), [model deployment](/rest/api/aiservices/accountmanagement/deployments/create-or-update?view=rest-aiservices-accountmanagement-2023-05-01&tabs=HTTP&preserve-view=true), and other higher level resource management tasks. The control plane also governs what is possible to do with capabilities like Azure Resource Manager, Bicep, Terraform, and Azure CLI.|
-| **Data plane - authoring** | `2024-12-01-preview` | `2024-10-21` | [Spec files](https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring) | The data plane authoring API controls [fine-tuning](/rest/api/azureopenai/fine-tuning?view=rest-azureopenai-2024-08-01-preview&preserve-view=true), [file-upload](/rest/api/azureopenai/files/upload?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true), [ingestion jobs](/rest/api/azureopenai/ingestion-jobs/create?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true), [batch](/rest/api/azureopenai/batch?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true) and certain [model level queries](/rest/api/azureopenai/models/get?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true)
+| **Data plane - authoring** | `2024-10-01-preview` | `2024-10-21` | [Spec files](https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring) | The data plane authoring API controls [fine-tuning](/rest/api/azureopenai/fine-tuning?view=rest-azureopenai-2024-08-01-preview&preserve-view=true), [file-upload](/rest/api/azureopenai/files/upload?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true), [ingestion jobs](/rest/api/azureopenai/ingestion-jobs/create?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true), [batch](/rest/api/azureopenai/batch?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true) and certain [model level queries](/rest/api/azureopenai/models/get?view=rest-azureopenai-2024-08-01-preview&tabs=HTTP&preserve-view=true)
 | **Data plane - inference** | [`2024-12-01-preview`](/azure/ai-services/openai/reference-preview#data-plane-inference) | [`2024-10-21`](/azure/ai-services/openai/reference#data-plane-inference) | [Spec files](https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference) | The data plane inference API provides the inference capabilities/endpoints for features like completions, chat completions, embeddings, speech/whisper, on your data, Dall-e, assistants, etc. |
 
 ## Authentication