From f052977e24f09660ce80b08a8fc10083a74dfd73 Mon Sep 17 00:00:00 2001
From: Li Jiang <bnujli@gmail.com>
Date: Sun, 5 Nov 2023 21:30:28 +0800
Subject: [PATCH] Add support to unstructrued (#501)

* Add support to unstructrued

* Fix tests

* Add test and documents

* Fix tests

* Fix tests

* Test unstructured on linux and mac
---
 .github/workflows/build.yml                   |   4 ++
 autogen/retrieve_utils.py                     |  16 +++++++-
 test/test_files/example.docx                  | Bin 0 -> 13989 bytes
 test/test_retrieve_utils.py                   |  35 ++++++++++++++++--
 .../blog/2023-10-18-RetrieveChat/index.mdx    |  10 +++++
 website/docs/Installation.md                  |  29 ++++++++++++---
 6 files changed, 83 insertions(+), 11 deletions(-)
 create mode 100644 test/test_files/example.docx

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 6432bf0e5..5bc831913 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -42,6 +42,10 @@ jobs:
           python -c "import autogen"
           pip install -e. pytest
           pip uninstall -y openai
+      - name: Install unstructured if not windows
+        if: matrix.os != 'windows-2019'
+        run: |
+          pip install "unstructured[all-docs]"
       - name: Test with pytest
         if: matrix.python-version != '3.10'
         run: |
diff --git a/autogen/retrieve_utils.py b/autogen/retrieve_utils.py
index bc4fdfb75..b98ba862d 100644
--- a/autogen/retrieve_utils.py
+++ b/autogen/retrieve_utils.py
@@ -15,6 +15,13 @@ import logging
 import pypdf
 from autogen.token_count_utils import count_token
 
+try:
+    from unstructured.partition.auto import partition
+
+    HAS_UNSTRUCTURED = True
+except ImportError:
+    HAS_UNSTRUCTURED = False
+
 logger = logging.getLogger(__name__)
 TEXT_FORMATS = [
     "txt",
@@ -33,6 +40,10 @@ TEXT_FORMATS = [
     "yml",
     "pdf",
 ]
+UNSTRUCTURED_FORMATS = ["docx", "doc", "odt", "pptx", "ppt", "xlsx", "eml", "msg", "epub"]
+if HAS_UNSTRUCTURED:
+    TEXT_FORMATS += UNSTRUCTURED_FORMATS
+    TEXT_FORMATS = list(set(TEXT_FORMATS))
 VALID_CHUNK_MODES = frozenset({"one_line", "multi_lines"})
 
 
@@ -123,7 +134,10 @@ def split_files_to_chunks(
         _, file_extension = os.path.splitext(file)
         file_extension = file_extension.lower()
 
-        if file_extension == ".pdf":
+        if HAS_UNSTRUCTURED and file_extension[1:] in UNSTRUCTURED_FORMATS:
+            text = partition(file)
+            text = "\n".join([t.text for t in text]) if len(text) > 0 else ""
+        elif file_extension == ".pdf":
             text = extract_text_from_pdf(file)
         else:  # For non-PDF text-based files
             with open(file, "r", encoding="utf-8", errors="ignore") as f:
diff --git a/test/test_files/example.docx b/test/test_files/example.docx
new file mode 100644
index 0000000000000000000000000000000000000000..f377c63c12986bc872f2b22d5bc316c941fb341d
GIT binary patch
literal 13989
zcmeHuWpo_LlCH>NW|qaw%q&^V%*@P^Ww9(~X0Vu<$zo<Ei<vE^*E2hJXU2E-y>s5*
zz163)Ao7dq%8tm0%=}7T3KR?#2pk9!2ndJ}$ah-1*8>;`DDDFg5DE|^h?cOOt+R=(
zv!1ety@`_!ox6?o$2>3)iX0#iK>h!0|BG9oK4H|dmjO}qKIkoAy0K5Pm7<_;I1hp1
z=LZ>neWFMdB@N`6-P?P-!B9$4`ZQys7_;*ZGh?asw|16cRAHKoaS?KxaIgx;*6Mue
z&v03qO+=w!ssRq@%r)H<PaUJ-=lWZWWaW*FC`Lp+<R;2SG=zl{`FoP*LQs993~~5#
z>=E+1O{?sRoKof`qKRJ*T?iPyhUV@%OjKFL`I3e0cG{NLG68R-3jsUm$X2|?&uEf<
zE7!j3bJ*HJV~1>E%q_J>P(Rx6uoB8;eDoEtlXpzcXvryXwN$KSTDPh5o89xst)5o1
z<>Lrqyv|A{v!NnIbsg_YB%b-M&%-Nv*2a$?s%{VOn|Pxehy~9-DRwpbnf}v63n(Tw
z53iU}2ZsLxnBnUw?s!f8GTLw^LC@n5IoFHP>1}Mq94-EmQI6rg-Xclu?evX-3y%5R
zSF<i6KX8yo5Mh={Ha7@?gp(i2SU=>_s=^Ad&5`%6#m-&<#`gXW3MBtGk9|%x5hnn6
z><@rL!T>y0&(Xx%iJtDa@;{#Xzt}zh^62GpJ(8e|h`|^B7l@7*6Rv1TM~xUr=%^yc
zpb^8TY|X=gB$m&2g)@27XEValj|bU4omfm-<u>$ulp?*ANwawg{uzcg+G?YVd%e4=
zVJTA<r^^bo?5KN&UpyGSa`BaH!>D)ihbZY5924WZKtn7=(T#etv@7dzX$oIp@!XX!
zmXMT9JV3YXf-?}9MDwk%u)Rt99e0irtZlXO53}aKk|x7P0BMptrv2>ux<(K;yc$9p
z9HmIhT6RDqE^rZ!OS{FO;KDV1Wz(Z56bU8hkmHb5VFYXLIe`L)*TtfT%W{~>Bj)5C
zIDn1D;g}BH@5)XFs!W<N&ksIt6hVgbr5=B?m|$bi!l!-Erow^tB2@p9{$TST{b{o0
z)QK1j2xtib2nY#K!_CgonBLgV$i)T_27ilxeaWk~J8Xyon=n5KAbA@E40S$7B6-z>
zo_!Pm0UN&qH4jY+Dfs07?bN-iQ&{raB(bp8zwt{<|0piJSupe5S#ncGF0DcuG~dm4
z-5-SCjbi1qCffPCDk{nGXTWd3n0toDR#DEpQ{SIP&ur5|nunm+ArZCZ+?cXFQW+hO
zpSdPJMY+%y)gWtHOVgvb(6ixSqxg_3Z;K0JHnW$ANY@A7o-=M5o~blHRN&DnxI=tL
z=eXQ~r54_Zinuf!n(DeDmyw?X2IG$SPFCu}Xt}FZft@2rj%Ysr5w0zEV|lF@hte``
zVExl8nZ-=x9Ar^D)(;_M_yC+-N9&vtMgGBKFTyHdnwngzk>X`gX3Tj^>BoC`Y`;0b
znEUu}C?kFhD1+B;g(0bG6nquCRS4Irw-%IouXrSoR!uZCZaeYpz4av~Dmbf&+u>9-
z9A%GT4AuERxbm-K@UAOaFvl#1?ubFHom3}RhpYD#p4;XcDc0@58Wp;(btWXo`N@I>
zVeB;f1oI-H53Cl_b`g69gSb=o`<e|#ca=c%!1Yn%llt>arKy4m2;`dfrjiCr_Y-t$
za6MV9mzW^l%EzDt$jOH3@<bYRys5+CCaU?sT1n$Z6R`2^pI`dKm|oWe-R1LQ#Iav-
z&#qFC-R>M6fy=n$i@s|6$fhpBN)07=@OVqN$h(gV5Od%|65(<pERlnSy*gFxj^AqO
z5vLoqbFP&x5G}9zKp6#;^g;6r$-^h-&%fqv-fPp(kr;Um&Lemh*#}6yrFaNVbscTe
zp7zyR39>co7jj-Z&g`Kp3t1;g_EaxRP3cH|Un=uMK74fbuSH;f*TlRMc&M<$xjTB=
zOxC^LRbEK*EG3OH(5A`@T|u^sDi%v2&ah^Tmhg{2ge4W3O=v^^uCHg4V<m-2LRo;c
z2Pw%+4;L*hHpO2OPnE%bk8BjG6I3YDM5z4i$60%n{}EcPOz^?(>5!N?49@dA73t-!
zh2PfR@`6|77cWoGg)ZWu6Z3F1v=1p-l43ix<#$u;)!E9ZbaY-MFr*&>sirhN9{9r$
za6WVgeHZzt8pr(byaAa!`h_L+MQ>w@1p>wHj*g>@#2~Vjj-rl0&5X`hV(BCJRYmz`
zM#vJ9$%pcrN<>rXCC`iYCE5kn9!^kNKD>k8{>6{j!EOghaObwcWy9_+rpxvWt!)Uc
zny#`fggH?S(`Za0IMv;WxBR;x!+jgNC!QAr{$w>CHC|5|Xib?vZy{iN;3y*U{FD&F
zY&bHy+v-xJvul_`e8V+4D2gc3OmjRrptPN6Vf%I*Qewx4&Bg46evEKOX*&@Ia#|Dy
zIgDGjsCQGY&odeyG}}IOevxm~md4uK4NAkTKaE~1*0Y=LNMh~f{}MO(4v4}39-$YE
z>lA(hdJ;xZARt^INZ{Xll>Z9Tf9+TP6|#W=$u%IJ|L@+)<Ni!8Q@m-pz2${=ttAOp
z7hZux@%f8spvHf0bya<mIGNIKy>zThahmjHTb=9)bBmbsD#{shL_CbB@>-;FFTt-m
z7eusDvpT_}!i?3|($%%jnzEFYn!EKA$>UI*V*J{WV9bTfV#1drMIRX*u+K7}3T~t8
z67HCI;Kn42C7;F6U#W`dcFP)K3Hw0MXqUF}BY@owl#5S^kl+42V(f@RQXNmr_(ME{
zlt|2hsH#-h6hXKVQ;|GPX?K2qNw+~(S(i?2)-2syBf-E$b&6B7#!T*26m>@vN_6%i
z1)&_D=ObXO_3u_==KE4V0S*K-{t*ZW4PXqvTaB~1iH!;U?<M1JvFKD|JRFA|wF~2k
zKcs~lKe{W~J%GPX#x<Vw<l8RA>UG3I+VscaHbz4EI3@ZZAx%%pp9{j2a4b_(Qtv52
zfo!kDR2J5gLkrF~HMzN`*bBr*_gP;&FOH5hoNiYFVti5hI0_X;DRmt1eDfGHe+=1i
zx_u20>IK&BHV1)<lpodjc&@$r`ZK=FUL1@<L|{bxGel#CK!|&h`mWJ3+#?!x{--Dz
zN|@XjnSBg$*euBoLQ2m{E$U!Iarh8@iusK!*(*%HT*af)%7pvS7YwLMu7N;2%K4#~
zsiooaZ=DbRZcw1)G4;5dlYv?A)1X^GAT2SVw1e|LvJUr_4zwa7QPyI%Iqyl1Qhvi@
zvyNi~6(80+7mE`Xo>+ZDY_z*_`K-LLfd-9QW&)+qwMrM(f}8qG1%~rQ-Rg9y(jOw;
zt{dM>D|S?1+rder6VF)T(_VGwyRGD})z`l_=~T_q;JCv{;#+AwNOtMmKY{B8fcWPx
zv$d+)u~<s|#AYfmo`kkru(a)H3M?u%Bx^-}{IuJz2^md^^U2qh4wVDM5GkJ$S4x{3
zJs|*ppV1EnqK_d@+qF%%gaou|+w&y4kz-AefjHAS@=-N;8}uP%OT9h=N3ks4ul@7Y
z_UYA4-C$QHuZQE^14ec9tAP6Mo&K)bp6>g@?dGNr@Y~bv*G0LmnjH`H_u~V4z1O$F
zt`ZFJ3cKtM&$rV(H@(-#StXeE@gEd01lx!X_Ar_L+$;$&_0qm#r)MO=z<nB_uDec{
zf}}=*_oDhacC;V;(6u2_UE2qZTdRSqCZplLivy>_SOags3W2%{P#(#f>deZpsx3g@
z3^mD3>}#yyLCRS>xv{seWe+l)*T|T#3xJOc6Y0QvqY?toVP+B<Beg}>7%YPFm?q4Y
z0Npbl3RtraBSuG<O9tK9Q@qwzBPG1CSv%PyI8)S=T;!slP~L-+uqB3Inzq9qfCQ@!
zFpy~M@}c@g?oRth!UZ@H@}3b33HtbRG!3tr!UUYlP~0TVpFtQSrF|m191C9inqV5s
z%XI?I5K)ogfNETmeU%EU0101G9hb8YuV8Zofw|ZEj4u}4Ho3X#W`bP{5rUn{yqY91
zw-yb<6f{)WJ}yMu--y*HCT@0)liLxE=vQR#kJ$X23MXgOyH9z9<2Od-HDsEOGZmpS
zABC9Q5JzQ86V<;4xlFt}i^~TQ9@$sts{pBywXem@Z2Uw_#-2~BJM3=yO>u0lupz#A
zT-eCFMH2zkJTTGH$*Y|%Wvh#Q*+_B!0nd0!YjmjZZJ-fL$WS^4d<@aB+D@uTvCrOz
zDz7mfJzZ<BaKBJyU4D(iQwTRx3HX&gF<Nxn&=Q~f(z`UXJ+M||XLpN@I-Sl0<>d;4
zjh7=DK9)y{W@@x`zqaymbCK2K`LQ;wrQDRR46AJjqS$l>L`)B~g3hZxiQ#_VEDVYh
z8OHyvh0eQq?K$4>bPkTTzSBGm^szZ(qWcl{*sQzw0XO^yg>Owp;Wx9(N5zIoLFpEn
zZ09DGChU(lm%g$|_wJ<=Gj8dMKw<Tp6_w8>C1i0Mn!Fv5I%SKrdU}nOkQB>Jgt4h(
zBnpi&#Z_FBgt=<2gfwaB=x_ym$w6<Lo}&1&K&4h!mZSzGy)wZ+MII?*^*rvs^Jbb!
zJ1u9Kc*ykM8uHl03<ai35TOM7@$j&<(Jw8I&lQ04nuOV4-wu4eY>*_vY4H;=g~=G<
zRjZU_HNtGlD0x{XA?Q^<-l0+w+!m)bqe%+>l01gYOy?N`0VRz<dV)|R0E>t_qCVN`
zCqmg2r>180@@bfLJ$lmdiTcEtB{Q#P=tv^nkw(D~&s(nAa;k;I8&z7iCuD3Hj{;7m
zA~^w=JSDt=l|047pSxjOtX0!ibO%npRg^Fkw3$btc9_TS<bXAEjEiM<TqX5v&rqz>
zamFjV^#G>CPkLsIQ(&&dVv>O1JZ7?5@}{$gN@6{|rLtwj#iOY2nE(>Y^2ivRwSP&7
z_KdYeM_(`|)fO+!!>ms<8$4a13_e6fr$kGOzUk;tUF?gTYMB#Jb0L*a1H+O|N0Ky?
z-?@%SG6cvNmMtg3x@FtUZRxuIYVjRRqGLZTOX-<ou1-ag)T`z2nM=F)3<VLS)V%Sz
z-%E`g`l#D|tIx@+cQaK(RfL85w^n#MOM}<9&fUGPE(mqaeS>ivmeFz9iYb~Vh#<+T
zSqhf62H9M-lLfB;-KG_Dczn(uA_3HAj!lXu?9dI0O<Kis+M-?4G;`Ehi<NV$kzWd4
z%`L22uIKMZ+S3-#`2peW-vb~UdQJo{U?2t$`<H>3lZmslg{_&>Z^5r#b=7v21JPSg
z|Gj7GhAQr}0&=db0r?f1=o(!q>a(;&f@mOnOaflflFud~sith5776WjoV=6i1nh7x
zR+ra%_n~=sBANeWz%B{ASW0pp(Pw6a&W(!ib^71nw$bwZcRZ>Gx!irOp6xDNQwIio
z)A4~nEMid~2pUC<<$X$qGyRke8OrI~AP<Z6pqw5;=(0IdjVetf3@sG8EWX1b8;~V7
z7NB}nUId9nnK+fl#zunTA|tu>euH#O>d_WMt<VVTw8JC@tyC;%zm8bKi}S3(281J5
z`#Me57~$EagWRRx#+_R#+$S|s2do&1Yz2qWS4<ysNqF@WYnt#LYWKY9u=pcS==yQ<
z_3{biz$D}hGJkv2PWeH|$Lo}@%2hiO2t39dOC+x?hEb5tCZ+o-G)6v^v5}(Ste*&!
zjj^sy!qV^#@2ok9W%TmW;9E(9gi5{QJB-y+*R7l7i*w}RKbe6w@jK2hciD&BWovCi
zm^B?BY70cWqxwg>ruLNveg%OeiwYP5`6#Dw0FIS2RNt4-8l|Kd@o|T4m7*_4%{@H4
z#6D8f@?1U^hp@*YT;Hf@C#%*vMyQ~ND!CY}QK}~rdG1+dJDwqV$_<q#obS5}VVfnZ
zuFhs&hxs^CoEsiICWm45ExC>rEtNI34VuRz-ZGGy3==oq*0Tr*S1l1*XPtOfI&VMq
zlC&)TmA@K+mJK9B>&7h%+DkFen9cs=$GEnRKI#Z*n87=-;kEH{idd_>1bOy$kcxH<
zCdEZ{K@gA?t$>UWWNx<!0)|q3#7+fW`K8Stuy)Rl5KJ9<&_-a-)yZ%fw^i%kW__G#
z%rFlU@51SYQUa`aIJ0T0$aD(O@nVeA=;)uDexg3Ur`*iWp3F&bav7VX;syCocGb?{
z)zEDt*9al8Xs#MyX+#UH(?i|6`{fdE8Ijn*AOssgm<Lnn^bmS>qm9>wnR^6TH5FQY
zV*|Cj$bFlI_TJm^8@;0}e^bs&#A{Xh<Qn&rZrFK69NE?u>c({)y(M~kN;o<vNiDl+
zBy-lDr){hot*yvAJVQByet&CmO_xq=g@#4&=0^<_J^$@-9#zvww-t#Ad9`8u7^oy$
zq=a>fUlsHh)0SvM=JT4G-T}OQK6wjvn2lG%>d20>A-ipx_#U>~#v}c7k5%jHf{i3i
zEl^rfK|ohf@m$cb=&xAQJO35f$MhIpkp0tknJupGwusr`K>)rD^9xWfxLRL#m6`-q
zF#hQ&RuNnKePQJ)|5ZbZOOhPcsrI>^+fS0ElD9U^(-bNw3YN_}!xTPpovj4(Ls(?+
zM5GZT9}b#S(?klpQ<}`D1D8y?i5*dh$u(c*N{{XipPpM}3+>w!giM#*O<B3*Bcc|~
zAPXL?z}b02TspG@2M%7T8F$Xqg5m9_?6>tNf@_R_9-=)bkcIsOO!#OQ0s#Sb|CMYz
zIeS=}{NB@?>a04hiXnS%mcBxuX1fxg>U>g24vUL3wmQ>XRiN>>;Q<RKB0}u_ATT<z
zc(DfLZw(uQUys?}kXWh?Hf09x^u$t#ll*vfV0T0EFjB{Ze$@Zt@@s%#_pH2#!;?MZ
zgQHKK8yDoYe*uz|$Ot|7BoD#M%k1X+-Oj9sE)O{m0*OFc_GE8(PdNqp!Sk~R$Bt9d
z`$u%1MD8M@^g5xpG5os&8ZT|SJ0V8BYND(@32mMW0zBLZ2z0U&f1<)!j$J#E=8T*A
zsk>(^Ig-3jHyZ6jQuRf2=5j>g=&6t%S)=h;<luG_+x7mOxWG9cxTZuHv)d3JOpW5$
zl4%6^hh6)_&_6IC?7@Hr2;YNyIT|pZXKJHR#5pn?f>6X+al0nwfUb)}Oeqrb9kuTh
zX{nbY_UgEZ23?Mu{k^iv7}LHUTo5S6)<_V=lAQRF&`ot8zhA%1^FPVG$=InCF+50E
z5+ZNm@R^K$8=9XyWvk;qqko-@{1ndP&SmC-Ie1?iP@CvMgY(%fb^l7>e2a#j?j~j4
zt+Qcu?k$z8dYWl0d}Y6kBMjoXbXq*C!0}!!NgFn5tnek;vbT86vEr$rk=EcyxFxd4
zOYi*nwGH!yakcI38=H)=5(a3}*}9HpZ|}4RGJmyU>hMy|7Yi^Hq1r=Dc;I(c8jU>o
zjV2?bw~ELm!<*#uJ^!GZbJTQnZLzT4E5Bnw<g#vOXGhJqhj!(c8WTcmV(ji0t)6qx
z8DpT>t=$O`)|O;B{*cR9akro~2gWIz;YhuWP1Bko<K0%wjLhXox6k-p;rSs&4WP3c
zxL2E|Jg;##<_)ilIC$Qt!SXapkN20x<#?3C`AwTbo$@u(=Q63=KjWD`%}tNG&o{HZ
z+d;VkLTPQbLm`N#eKS;UTeLriBD%+!bvk1*&Ov3g5G%`?ig3OTt8;r<@Iag8p|KjA
zg~df4A>2(IT)zcL72cEk60E>_@Qyq&_8=h}OO&vbIqp~GDGqqj90%N}r~!uuM(n|@
zLdXoEKsx$z&gZGEv$N*aDx@#XtMpKSq6!F5fOZm`-#wgvZR5>&-m;C}09*=S#b1<e
z@V{3ywV2j2Q6daeM&*%@-`FsxNmS<=E$C6g;LVE7AOVgDwZ0Qt!=W{Px_3pGCc5p)
z!l2TC?PEz9K%m+?T6f6$vKOj;=_?xBM+`RBEIootyuCAvm3<viL|Ei(%_W}*1%Bkn
zM|e5@!Rur1wuK1KXHp^w`C?qn{YhrhxRmaa1DY|B_ev-+bOOFUkM|nIk3I8D5*$bi
z<k%Rq>aR|qaI^fZQw*=nza20ZJBYE0phud2qrsl`)nLhUV1AQewFO*Q16*j<sDImW
zCBO)Uzq-{JG`L?`cOjbd4&8Wd4ku95Nj!@*wkqtQ9bFP0K(7-(YfLvdIf$@1kQABh
z;q7Ow5Xwtiw8BtmIOWi}BbZ`kp>j}h7r8FI3;|Q!x=mgZ=af-Jsdr;}99wr(WC>Fx
zc0oSFlS(obTGg{DKfExY243sakR=N+RR=+M`&L*NCL1=?bZqh-RZ;ykYROC$>pCff
z{F4c3i&zHp%YFNgROwNCFXHtO5+pgEJmGd~CWFrvbdSU`66C{One?VK(Jqzs;M1>)
zdVJG}pN+#e$eq)xISK%O?nXwxgaCVhyW9JfusuCG)wnXKFsM6en9$fTgAM5=LD$tV
zzXg{&W&DqysfX6|p(DcBr(9&sLzpB;NQA={rWpeyi}I28c5ggLG~wn`w#>HpL{uC|
z+j!~pW8VS<w3z7lh986(aAw@!4K&J+g_QGJ$$`rf;coVJ-SF=aT(U(36tSL6G!CEg
zvyLsTxSHQ)16iBjl)%Od+j%J7Nja7QXXI_*;x4s|P@^|X9x(Gb(Z|kGJjXX@*)JMA
zu_4y2(ud&HU?ey_$T8NCqO}=CoO@VSJl|0k+~*FY4w<l{b4ZG=-V*zfu&}Tr!l2;9
zL<7L{w*>-Xk*D6FGO^X)2c0eTU$f^K^+l9?u`v^~V|Cv`&#&jYi(jMz6dqH-^RJoV
z#P-a3*@3fV_efICk(C0zUAJJ9tOt?NK71x*O5#Nk?38%`C8mhMu3wdwo?j&;VnuL3
z5h%rW5#m^8vsWg0A0Ri@QBqHMB`OZ7B|-8pZftD*VLp0mw%C|@#4hORw#8;Zm>o*8
zow}2;*2tvS$y{Y(?W*UNue5w4{K7!(-=?8*R@EDU(5RUN^_;eR2cACg*;+5wg5`NA
z-<^}58(Oar6QK>qDq5GBPOr^^QFokVfhL+;^E=z%Dy>@GF6(G~R8sZ$Y*dnFkyVn7
zr+aVhpqMy^#Z5NVpcBWYL^_7bK;(EMr=rR7u0OerZarDz4<^|8b&w%h_VMPkw$MSF
zXoXmu55(l`l4d$BgezcosXmeOiFhb1E?)DqC?C&HB%F(e9#0fgT3=V-iq7d>I+9U}
zSPle<C#s(#%Ni(l@CPTh2H>VS&zlLkAU?8-6n)xd5f36^mpoY74L-#EwuX3U{-Fx8
z+5E$q!!-2Dvj}y_HcEx(7|0r8W)Y|@WW78gm}W7rDYPwQg1lc#vOFQQW-%fNtumw^
zI#q`6Rv`45gHX^NpHL9RZ(s9Vp+6vh)G0k!+pst%RSxk-rwSB+K@-XeDm@72{eQs#
zb)nEwyr9tXa)O`<r-XtK&2!V#;9i6NAGiA_+;Mu)|Hu7o-Yo1CTJh`n`_y<d<xbtY
zTuiucTi&SL@GO_`N>3AU%AVUG)r5G!BkA$sT{@@XNU}(3rbsOZZEm?LzmR~q?A#=u
z+_8T?KIG+ZHQo%Gx|ariC@v!{E{Ryt?zDx9Ygb4wTBPkMcbY@@K1uq)#9;~3s+qhe
zOnL1H7P0zWdi-I^U<19vYTrI&)zEnyG0I-cxDx9-ux<DtYwwQ0hXa|Dov0m_$}IX1
zkT&P)!W<67^(~~krLcqYm^u<p#Lgy@kyD9c>>y!sfQdnMcGNTj_5^}?c~kY$*Pvsu
zZbdkx_F`~`H)UZ8yHY}cgn_}ZBp4DP4XDHE3AY5=kz)<KF2ojkRDh#5Q7<I~NwN&_
zEoeRXunhGV5xLuci?E5@72xz=N`mD#0805w1(PBQv5EA5S4!xQF%LA5Z3($2!y0Ir
zuc@Z6P%Or%%{(ac-7>ft#&H}GBf}~fe_3&Sg;}eV(A`ujrYz1$yHS~Z9Pkvp>_TeT
z>yQ+DnGEiR>+<Ho>+)ZecWMjB{&<wg(WH#u&Q(htmKCYzo2`dsSn0GZ^RSa?SryI*
zGS(q=|3@(Zn^t`8A?W)3K?!iISu$WEW&4{R6o8(RP)qH`IT3&|N5y{$D*&oU+5aZ|
z{Z5>}A%7G8{xfF8Es#+@gB;sV)Dq=9>#lJpO+qic?*!`2L>v%3j^z8^Df8z{IKErh
zJW>Z$B;UsmVmOY?VN6+7QH$=wRHMriJn)q!l_(CBlKbiKj@d5YH8xqvgs<33DWNrY
zsC|a~p%$)ngia=%HBWEJBCu2P#9-L#x`()TSDSi*H9EGDSe7)X&R99Icf>QgQ@rMF
z&%lGD+fmcxezt8Aok7nxe0R%sD}3GS^lH^mxh&$XBpuZ~MPqH6%*owQind=SL(oa4
zB9+9oDt5x<bb6oUvOgz#z~y9>R0cTOFSE>SkuPaKUK~F(F83BDC@1dj_qBMfVk`Tq
zNHR4aDX2~>rM6*RNiSvAIFBB2<B&yMbhCsgvcn^emtjUK<+PSYp|{j=+UlXTUKRnn
znd${cyX<n$wCdTqICZ3(M1y^g{e}Eo1-_-Xqmgr(PJ3@?Vr>C^Xbw<eWax<M?hzkb
z4XeXZjkCf_66-Fv=n(yomz3?ji>>42gq@dnd+7-2u7wsmn&XX+N2qM~wm&M1Pd~}m
z<{CJ?f99e4A@RAp_#9LgW2$z^LY{+9>D`7aP}9X?5B|PJbNpWMW_}h&He*Ad8kuFo
z{#wUfnDYlc7NYCedr7<xH+AmT`_IJdu1E)3|IFj}Ly_0Tpm%mur#@!#_arpzx5>A>
zmt^6WxUeEKo`isLp=SeEalCQ5YGrT2PxMvwM=((;DY!f<+e>Wt>#uamtW5=ztt+dV
zKr9~&it=6V>J8&COZNyal=jT!Mx;u!#5Pm>;-0HK;yxSio7dPAq+OQ8g|B(J=X4FW
z)c6=CCE2f-J>dtU==*dq@0+z{r}UE<-8e?nZInWv!Sz;b&K+~l;CXXs?>m~G&jF{u
zYLyk(-p!oD!Uw3lEJK<{a@hwlo@`AZ?!!yI)2HWAvZBdi6o`u?tZ?Zpmd)Hx+GmfD
z#u+FXJ2Uc-7%p84PhMuL02SBG7rBQRkIp@6TSta0)fNmd_AXSyxPMZWt{CqhVML;C
z<au~C56OT~x^TQ=AlvRqI($Pu&Z#o~NXaNljzLN;lCZ?JOr1E8E$d(M()@{ol&DAd
z!#i@T`_^Y4Zqh=`oxI%$z?{K#l`=*fRb48Av2|3#@(N4e(o>q4Ceng@LJbs7sVg|N
z@qSb)Rn%}UbHC&5&W$1`mKJ&*?zS@ARvhVFz^m!5ZciOv8S{);hZ_7S@nmU@-gv<%
z?cklKR<=&MjdPwh<I*9i_q@6jYm-y^M7isI2CG%GW|>!fjwM7;oK&?c<0=TM<k*p;
z?OO=S!&2h<<9AZqQyMUPA9IwLb+S&Ygyx|O>M0j;N2j+D@+f*~jXI|BG?4VMlnT_e
zxlcC!JhkyylVw(~7Hr;q7X}t3j%t;wA6BeWwW8qXe00?FWdqcN=Rb+-CC+iU)K#kx
zapSd^Cabu~sE#^XM<sqKF=+5gN9fJPTzSG8AvE&-Dz%=in7ve2xx|)ya!5BXv3fC~
zLeRU)V{_TSlabHj4t6Zmvd-=LkdlNKzCYF2nKHt5e~7$&Jl-JMnk$E2(;W7*YrnIY
zk1jdOIC<|)nAfoAE#|FYJ5)6r-*vLq-38({NK28a+N|-c1NwHfSw+UE$Y>qMTX^wh
z=Ic+mHy=wZ)CYyKle-Sw@=)XO!A`FArh%dPB2FF9X0AND1RA^B+`QesdP{NYWI@sv
zQ<$_G(D<S2$I(b6+V>HkCxU;RjJ$xRl$8an%6<W?;iCR)g22thQ0Xu8kr}gkR^J&A
zfiCZRI)#VZ3P(^WRSjSVbqDlUAwrJkgGpQB!pqKQFIGyN9t`i}-tTwl2ygZ#mUmG=
zuzt2+!YRf2E~;a84fj8<S~8$OiSEIeObgT92^h9CccijwfS#y@#L6jt4=Wlw(pF|%
zNKN=gZ66k_9&j*@9H10iWI&t=O|a^jGd)k0)=)!szQ-X`wA~$Og-RopzXg1|;1{ja
z4y&&rB9~ZlRLr_)4i}sUU+foh;&3<UH1dGL+}h@wF%1kg%CTz*kL7~;HG0N&_mrOD
z2qJ>sw<K7H-^i7LL_CYT@bExdE{bv@<DJwATplUBG?|HSqs-b!ML99=SUd2GgpBOk
zMuXd~^IiQF=G;ncUscv+FDc$yqqfhgi|~@mi4Bxt4*|%DdB&qZTJW<koM6mZZ7q6w
z@_~5P5Pz5H72H2f25)w76bJ!U*EIk%RpfuQzbSy5s%&6rZSvb}@LK$|?Fs{G@CEr9
z9?@np2e42WHWjpJ8q2NW@wavCL6QYS?rTOcd;^3!jHPk>qAJEgs08%VI30A6?HBTc
zos3OB_9iU_cbq~$>eQT^ud#z9DwN3@{+;}Em4>^1giNGCaWsP5;D@f)kAPJ$T}q4Y
zx<_OH(}04#5cipHDgz3HSB1$UfV$uV<DG(8=f|gm*7iKfguY8s`sU?F!T}^p#wX-3
z%?b_^C(%WJiJfcjacC)JWJlfaS*kihWeKuU6%?S=yy1CUP~Z1}QD9{S{FN#MDx@db
zW>t6P*?7BcNyE&#t8qT^0E;Bpv@vccZLN+O!OOKd<bi%I63=+2-iHJ#k+_jfu)iqN
zJ3tn81bJkPb)mL&?>-Ybi_O`gPgPE%fsv|hJ712x!ENqbc{@qhs;!tkL7)1D_n`_~
zipYAuo&`EX+9}U(J{FD=Igs&seO2Vrut_a<8%QQ+H+bL6TbQLv%0j4{8ArVrnS3Zq
zKBCt>5Sz4k_<Ytb@iOO!>QR?+@lNyL56@|;NnEv}&3c!ajoAx5IiI)Iw@(K6<&9PD
z6UKJ|D9dcZ-$2lD)2bkdOT+8$?^fF%MhZB%4v;l)=7+zPFdt2@E~d;yn}ttXGkV)7
zB6b+fbiZ+>{T%uLdf}(C!A@FEd;kYkLFmm>@54}k!iS&1y8BWy9ktpY`@9nK+#gHK
zTo$ptwLV<a^5uPrC1VuNL1}B8GvULs_s^rt&TATWyVECe`~X+rc%Ogtc&FGv92<bg
z9{{Wl3BcL_P&MQo?d+ZCjqDtMH#h*h@;_7!K+{FU>Bt5A=6EtM2;c7Ip+gnEtLK?w
zm`X`!OuMVCGOI!qShO*|b$kHFalqKfj6P`R^<H)ULIZOFv=SmYfe0nE>t~FH!IYhQ
zfBU^lJgY|8QBxV&v=}&GfB8&iMEN@vTve-LP6f~oC#eN;p{co5g(L%;H4G`MAMrOU
zTPhvJ6U9s;(dDRp-+YGlUQ+dul7eQmpYz2bvT+%aah6r#vcAl)9}+%R^pJdf7}K08
zXyKZ2p&L?M66;ZMHjnx_9fDMT!d1Kj@A8cD(xTbvqIMf(-C^ikn^4yWttF7O?Q}>~
z_x=WK`h1<zoMMsFIJ2ziPVYa`4jOD|bq}A`I<wY1EwRr4A8e6Z?$xL3u4wNp7^%~u
zwhs9tdb}UY$BVXd>*ESRY-|+f>`!C6E)4t0<+z_@@R`vMM;;vl8mMA5azgxMCzphw
zpOAy~&Me~}>-0S|f4qlXDLWt@uBUz(KgIZ`UXi%JK*9}Rqay$tMf|Ic8ra+a)+heQ
zL;>~**fJDHWdT(6cH%1ph4VQJg)(THNO`2~?tI1BJL~22zV9`(t2uWU%Pffg&9So+
z<!(H6jBEH>@!t9&E6XZ;nW!GYs$2y&9V2dgz4J_yhRCW=J2aKoC<8A^db-_Y9MOap
z5m*vS%_HdvFK|W*Y)fGrxs3&~dqUL6J@U+IDw^9J@fWl!eWs!{`tH)^Xr<Krkoz6m
z<Kj<M#g4T%825X_@%Uenwd_QM-ezRdLLEy!uvN>ql1P_m?K0;<0O2SY?JDVe14Cda
z@7{o@>-DrE2@Z+C?AGmpEJ5~W-it}anm4>?jQ+?gQ@r!MOLw{H9uW6svR3GX$dt{n
z#T0g*NjfKY@)jKMFAlgIPi_P5QH2h$lANSAAOd+N)IZatrx~uvCF*EuzA0$CK)+(W
zPR9-6Ih?cZh%w%J^5l!+KJHFZSKjrhW<b3B<U^7on{8?ndHg)KDc02O{m$~}%t(32
zZFicUzt)?+l?`a}_kSa**WZMh+yW%R0E5K>>;WCBjES>>v4OJzy|jU$iM52Ssoif@
zs~q!R+%KPgbNW%mOm((K&~>yKl`es31)3>h_1P)Kr;EfkOSfbgCl0s$QE}LD(7SCX
zO-MWL83Cr{Cugl8ZZ0YbC3(^^A=&B}If~ud39>_m4+VtU-aUmvim6eKggD#YhUF=6
zc~mw(O(#jYt!1KUxDVhMrbDAdeY)@i)dWn?sID<q-P>a57hwvrJO%frGA-!8eOqyq
z6}0le9#kU#_Q)5J2rrMoVL|jG$?EfS;)c!qJtRGZ4Wey=;-ZY%pv7cjKCxOFG&km|
zgRKj{a@sHy;a1&XZOl_Np5YhVpJ~fnb?>W-f2NzjAhdwg@}FPC0W{a&wtsjnM_%gh
z3jY3Hz+cg|fE@NOZwdSg{FMOxClmzYAL!7(!vD^8{1XfWqzv;1{D0s+{;KI$2Hc;z
z!T>qqKl0&zRq-o_;7=9dfGqxZ6@O(E{0jedS@2KzJ?6jQ|Gh}~EBMzT!=GSG%0Ixr
z3?P2h@N3fhr-l@&KQ#O;1^yNP_Y~$&G!PIp?eG5g_k`wG_}`<;U*VPXe}VrIYko!l
h>h6EywV3`d&Mz<Z0YG{L0)hp6AOVK@mHD@`{{uRm9!CHG

literal 0
HcmV?d00001

diff --git a/test/test_retrieve_utils.py b/test/test_retrieve_utils.py
index 2423c1e0a..b85356ef4 100644
--- a/test/test_retrieve_utils.py
+++ b/test/test_retrieve_utils.py
@@ -18,8 +18,15 @@ except ImportError:
 else:
     skip = False
 import os
+import sys
 import pytest
 
+try:
+    from unstructured.partition.auto import partition
+
+    HAS_UNSTRUCTURED = True
+except ImportError:
+    HAS_UNSTRUCTURED = False
 
 test_dir = os.path.join(os.path.dirname(__file__), "test_files")
 expected_text = """AutoGen is an advanced tool designed to assist developers in harnessing the capabilities
@@ -47,7 +54,10 @@ class TestRetrieveUtils:
         pdf_file_path = os.path.join(test_dir, "example.pdf")
         txt_file_path = os.path.join(test_dir, "example.txt")
         chunks = split_files_to_chunks([pdf_file_path, txt_file_path])
-        assert all(isinstance(chunk, str) and chunk.strip() for chunk in chunks)
+        assert all(
+            isinstance(chunk, str) and "AutoGen is an advanced tool designed to assist developers" in chunk.strip()
+            for chunk in chunks
+        )
 
     def test_get_files_from_dir(self):
         files = get_files_from_dir(test_dir)
@@ -161,14 +171,17 @@ class TestRetrieveUtils:
         )
         results = query_vector_db(["autogen"], client=client, collection_name="mytestcollection", n_results=1)
         assert (
-            results.get("documents")[0][0]
-            == "AutoGen is an advanced tool designed to assist developers in harnessing the capabilities\nof Large Language Models (LLMs) for various applications. The primary purpose o"
+            "AutoGen is an advanced tool designed to assist developers in harnessing the capabilities"
+            in results.get("documents")[0][0]
         )
 
     def test_retrieve_utils(self):
         client = chromadb.PersistentClient(path="/tmp/chromadb")
         create_vector_db_from_dir(
-            dir_path="./website/docs", client=client, collection_name="autogen-docs", get_or_create=True
+            dir_path="./website/docs",
+            client=client,
+            collection_name="autogen-docs",
+            get_or_create=True,
         )
         results = query_vector_db(
             query_texts=[
@@ -182,6 +195,20 @@ class TestRetrieveUtils:
         print(results["ids"][0])
         assert len(results["ids"][0]) == 4
 
+    @pytest.mark.skipif(
+        not HAS_UNSTRUCTURED,
+        reason="do not run if unstructured is not installed",
+    )
+    def test_unstructured(self):
+        pdf_file_path = os.path.join(test_dir, "example.pdf")
+        txt_file_path = os.path.join(test_dir, "example.txt")
+        word_file_path = os.path.join(test_dir, "example.docx")
+        chunks = split_files_to_chunks([pdf_file_path, txt_file_path, word_file_path])
+        assert all(
+            isinstance(chunk, str) and "AutoGen is an advanced tool designed to assist developers" in chunk.strip()
+            for chunk in chunks
+        )
+
 
 if __name__ == "__main__":
     pytest.main()
diff --git a/website/blog/2023-10-18-RetrieveChat/index.mdx b/website/blog/2023-10-18-RetrieveChat/index.mdx
index 06004ba42..ec01db211 100644
--- a/website/blog/2023-10-18-RetrieveChat/index.mdx
+++ b/website/blog/2023-10-18-RetrieveChat/index.mdx
@@ -54,6 +54,15 @@ Please install pyautogen with the [retrievechat] option before using RAG agents.
 pip install "pyautogen[retrievechat]"
 ```
 
+RetrieveChat can handle various types of documents. By default, it can process
+plain text and PDF files, including formats such as 'txt', 'json', 'csv', 'tsv',
+'md', 'html', 'htm', 'rtf', 'rst', 'jsonl', 'log', 'xml', 'yaml', 'yml' and 'pdf'.
+If you install [unstructured](https://unstructured-io.github.io/unstructured/installation/full_installation.html)
+(`pip install "unstructured[all-docs]"`), additional document types such as 'docx',
+'doc', 'odt', 'pptx', 'ppt', 'xlsx', 'eml', 'msg', 'epub' will also be supported.
+
+You can find a list of all supported document types by using `autogen.retrieve_utils.TEXT_FORMATS`.
+
 1. Import Agents
 ```python
 import autogen
@@ -474,3 +483,4 @@ The online app and the source code are hosted in [HuggingFace](https://huggingfa
 You can check out more example notebooks for RAG use cases:
 - [Automated Code Generation and Question Answering with Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb)
 - [Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb)
+- [Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_qdrant_RetrieveChat.ipynb)
diff --git a/website/docs/Installation.md b/website/docs/Installation.md
index 508f20776..05a4b6bd3 100644
--- a/website/docs/Installation.md
+++ b/website/docs/Installation.md
@@ -68,7 +68,7 @@ Inference parameter tuning can be done via [`flaml.tune`](https://microsoft.gith
 - `use_cache` is removed as a kwarg in `OpenAIWrapper.create()` for being automatically decided by `seed`: int | None.
 
 ### Optional Dependencies
-* docker
+- #### docker
 
 For the best user experience and seamless code execution, we highly recommend using Docker with AutoGen. Docker is a containerization platform that simplifies the setup and execution of your code. Developing in a docker container, such as GitHub Codespace, also makes the development convenient.
 
@@ -77,7 +77,7 @@ When running AutoGen out of a docker container, to use docker for code execution
 pip install docker
 ```
 
-* blendsearch
+- #### blendsearch
 
 `pyautogen<0.2` offers a cost-effective hyperparameter optimization technique [EcoOptiGen](https://arxiv.org/abs/2303.04673) for tuning Large Language Models. Please install with the [blendsearch] option to use it.
 ```bash
@@ -85,21 +85,37 @@ pip install "pyautogen[blendsearch]<0.2"
 ```
 
 Example notebooks:
-[Optimize for Code Generation](https://github.com/microsoft/autogen/blob/main/notebook/oai_completion.ipynb),
+
+[Optimize for Code Generation](https://github.com/microsoft/autogen/blob/main/notebook/oai_completion.ipynb)
+
 [Optimize for Math](https://github.com/microsoft/autogen/blob/main/notebook/oai_chatgpt_gpt4.ipynb)
 
-* retrievechat
+- #### retrievechat
 
 `pyautogen<0.2` supports retrieval-augmented generation tasks such as question answering and code generation with RAG agents. Please install with the [retrievechat] option to use it.
 ```bash
 pip install "pyautogen[retrievechat]<0.2"
 ```
 
+RetrieveChat can handle various types of documents. By default, it can process
+plain text and PDF files, including formats such as 'txt', 'json', 'csv', 'tsv',
+'md', 'html', 'htm', 'rtf', 'rst', 'jsonl', 'log', 'xml', 'yaml', 'yml' and 'pdf'.
+If you install [unstructured](https://unstructured-io.github.io/unstructured/installation/full_installation.html)
+(`pip install "unstructured[all-docs]"`), additional document types such as 'docx',
+'doc', 'odt', 'pptx', 'ppt', 'xlsx', 'eml', 'msg', 'epub' will also be supported.
+
+You can find a list of all supported document types by using `autogen.retrieve_utils.TEXT_FORMATS`.
+
 Example notebooks:
-[Automated Code Generation and Question Answering with Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb),
+
+[Automated Code Generation and Question Answering with Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb)
+
 [Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb)
 
-* mathchat
+[Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_qdrant_RetrieveChat.ipynb)
+
+
+- #### mathchat
 
 `pyautogen<0.2` offers an experimental agent for math problem solving. Please install with the [mathchat] option to use it.
 ```bash
@@ -107,4 +123,5 @@ pip install "pyautogen[mathchat]<0.2"
 ```
 
 Example notebooks:
+
 [Using MathChat to Solve Math Problems](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_MathChat.ipynb)