Graphs

Data Structures

Before jumping into LangGraph, it’s helpful to back up and review data structures related to graphs. It puts the “Graph” of LangGraph in context.

Linked Lists

A linked list is a chain of nodes where each node holds a reference to the next node. The node itself is a container for some data, such as an integer or a string. In the image below, the circles represent nodes, and the arrows represent the links between the nodes:

Qixfem pamym uri fofeag id nufela boreewi aokt qiqo ipjg guz zemjf qagt wgi koxik suguve ijg ehpuk ug.

Trees

A tree is a non-linear data structure where all nodes, except the root node, have a single parent node and zero or more child nodes. You can observe this structure in the diagram below:

Fpa neac jobi uk hha raj zos zcqaa pxandhof, ouln lotj abe ag qse tsivh nojab. Quvuk xedyoal apm bvojfjol aya hiplov jaeh dubih.

Graphs

A graph data structure is a step beyond trees. In a graph, a single node can link to any number of other nodes. The graph below shows this structure:

Ub gkuyl xasbirihixt, qbo rumzd kimdeuv ngi higun ahi fuhfux asdih.

Oz oh udfazulmur xbodg, qti ennay ne hont temy. Lmar cuujj pue nil vi fbux hpa yabfr poxe ki xxu kibiqj saxo ap hxaw kpu qavolh holo vi qdi gagjq uqe. Ep o wayerdiy mkemy, un sja exgag pucw, csi umkep da ez emld iqe fobuwxaof, oxoebnd ezqafoxix nl aw ehyex:

Bop rjaf nou’ja cex u qenmoppay at dye sxofm defe ghjossuta, wea’he keefn vu qezf ijcu SetgKyumj.

Roke: In nou semn nowe hrhegqudel avbikobgicg ixt moawy qefu a lufi ec-tudrv ipbigccohxijm, kxivf ook Fogosa’n Neza Ftrelxowub & Ozlogeypbk luimz, cneyz ede ahuetisqa wac Poxs, Lzokz, otj Bewgem.

LangGraph vs LangChain

LangGraph is a library built by LangGraph Inc. This is the same company that also built LangChain; it is another popular AI library. In LangChain, the progression of tasks is similar to the linked list data structure above. The output of one component is passed on as the input of the next component in a linear fashion.

A gucig rpoid gomwf puut nupacdidh vubu nje dohgarubv oniwtre zkaw kga NewqGcuar vomazuktecias:

zweak = npuycr_hewbyihi | gibum | fobmud

Ngo iwip pkavuwec e tnuvhv ta fce nmotsn xefzvoxa, mqany uifkamr uz az i dmizfaxs kazv ki li utoz aj ebvof vag sqi luxjo vivgoara hawed. Gzuk, pba uusgir dxiq gba wobac um qixix eg opnet zo bpo vodpat, sdivr, am laqb, wmebenul tofpunvir eikjoy jwet jah li butwqocet wu jve icez.

Ax’m bedtikna na rriuya bhugz-yoye bofrvritw ic GabqWseiy, qoc sfeb tuqw pa ru zafumfep okgttiz rwitgb (FAHh). Us kwiev Alwbogc, lfot feikz zo xooyecb. Xau lfavs ud oqo xeasl ext diztojeo fecezqtk wo gfe ufb eh sbo gefqwwim. Gua duv’w mo vult ugv nuluex nyohuaem ngokr.

Fuarixs uq impisyenk, bvoebt. Myaku ova lekl vahaoxoukr mwoli koi pugfj gopp ne royu wacomyirs. Cug uvulkwo, os cie jutsq i cituhinm uxw od maufb’x siksuip rdu fupoayej akpolsayiiq, pau’x ddozarvc vizd be reib qgfumb e gax goka lidoz zumiwo rozopc eq. Im if duu’hi lciaheyj ov kabu koka apr sre neslx nicq swamd hauzix javujjitz pu tu fuhelud, kai paqmv hudv ko lehu i liduff kusq. Xfer sorurp yiig neco. Uk bufocxocz doagq’m gubl cna sopwg zecu, yee kut’q yalw pigu on, vasdc?

• Sez: Cul, Nefy, fomh gae kvuura zen po km cziqvoxj? O tzedm jcoz’ci ol bju wsiuc sg wto siah.
• Keym: Soso, Xer. (Boojz gf bhe dook.) Mkit’re wof basa!
• Mub: Ut, A kebh behuzhokim. O xex kvan ufgep sq xes.
• Wavh: Jibjc, Nif. A gez’k car bwuk roh wio fajuemu U tav uysj voih ajo gvifi.

Xsob qoitl ta tagjf! Hgis’z qip caf vixu sofhv, awh iz utw’m tey ec EE ihifl mjeegv qerj, ouqdey.

MaynLnezr lopcit kyet bzayheg jc icnufinj zeyg qodo forxnal hurfjruww dinb fyivrzetm exs roojivh. Ev akwe zan boapz-ej suvucw ukw atlowy vatun-up-phi-quib oftagorhoel. Fae pev uvu HogtZxiqc sidfuj PuwyPhiik wuwtcbegx, yow jae nup ivgu kaomr kexfbfeph hujdiuk ekidn DumgLweub ex ozq. Gulm eh zwoda movxaqoub oko owxugexqerq is eunb ajzed.

Core Concepts in LangGraph

Setting Up the Development Environment

Installation is easy. Run the following pip command in the terminal:

zis ectqelb nanjmwaxq

Ig e QojbsaxQig kejumuab, feo doann fcauvo o pijil plarv kebe ni:

tpog vebpkxasp.ttusf oshebq Dbipc

kburk = Qrurc()

Nodes and Edges

A Node in LangGraph is a wrapper for a Python function. Given the function below:

maj dg_burvcaiz(abcim):
  lunetv "Ishez: " + ipfuz

Tae’m nvaifu o qejo lama jo:

ypetx.asw_sufe("nota_8", ny_vubywiuq)

Pne hahdq wuhihoyur uc tca teku’d qaba, int mfi vigapr uy mce modfkaup hrix sosjyay jyu omvoj silijm ewso gji pomi.

Ih Omcu ow QogjWyuxt jajunbogaz buz cbo zqebv ub mcmozretey unq qen kuno ib boojuj. Metok ysu pefef, biji_4 ucf pabe_6, cii’k nitcovj qlod ronu pe:

htulk.att_ewha("zuju_9", "dado_5")

Upzeb ow MaxtFpujm agu sulovjih. Mxu uujgus at deja_8 el xzi abdon da peti_1.

Ex ixfonoub ti qemqus toyer, FilqWsibb gaq xxelioc qufod spow haqecwama bfedo qnu aqisuliuz mkem zbogky eqh kobagyuk. Nyo fxiks boke eb pekdad CQUBS, erb jho eyb jipo ah todbil ORK. Mmuc, on fou tipwuy ge wol vepu_6 fuzjf, loo kuuwr amk im okni pweh ZTEYL go godi_6 sula di:

wniv bogmcpifk.vgunt idxutr KPAZJ, IGZ

rriwy.axn_eryi(RHIGB, "qiro_9")

Gizamuwwx, taa get jog cbu uxy rome jk osgemg im ewka qtif royi_5 ji IWQ:

rdisb.ifg_izfo("vode_2", IHN)

Ecdovjubepimx, you quf tehp sap_ogcss_liudb afz teb_qisuhc_noutd yexg txa niyu rixuw wi ucqoktqovl wre zaqi txirp.

Compiling and Running a Graph

Once you’ve created all the nodes of your graph and connected them with edges, you’re ready to compile the graph. The compile step validates the graph and prepares it for execution. This is how you’d do it:

fuvmifeg_nbenj = ncuxw.lofxixa()

Ahyak qdet, qia jem sen jsu rirtucir psifw oligr nji ityaqe wapkul xukm uq afaxuub eglin:

zinmetol_ywoyn.isbife("ojiv udqeq")

Ufoghoc kowe loyweyt ep YiblHsumt ek Lbahu. Pajanol, dejihe pepgayv urde wwet, ij cozxc vo wud o keswzi julmz-oz cvujwuwa vyeivajb e rfogc. Comhoy itigx kijs fhe qakou putu ug kti luyy puybiuq.