Chat History

Comparing OpenAI Chatbot & Gemini Chatbot

Gemini has added the Files API, which can allow multi-modal input, such as documents and images. The process of building an app with the Gemini API is very similar to OpenAI. There are many overlapping features between the two. When building the app for this lesson, you’ll utilize system conversation history in a similar way as you did with OpenAI. You’ll also use system instructions to customize the model. OpenAI has a similar parallel function calling feature. Lastly, you can format your responses from Gemini in JSON and provide a schema to make it more advanced.

Deciding Between Gemini and ChatGPT Based on Results

If you’re already working heavily within the Google Cloud ecosystem and need an information retrieval-focused chatbot, Gemini is a good choice. If you prioritize creative generation, conversational abilities, customization, and broad platform integration, ChatGPT could be a better fit. Both APIs are rapidly evolving, so it’s crucial to stay updated with the latest developments. Consider factors like project requirements, model capabilities, cost, and the development ecosystem when making your decision.

Chat History

Chat history is an important aspect of a request because it maintains conversation context. First, you’ll compare the OpenAI module app with the one you’re building in this module.

Defining Conversation Context

Conversation history, in the context of AI text generation, refers to the record of previous interactions within a dialogue. This record serves as the conversational context, providing the AI model with crucial information about the ongoing discussion. The context derived from previous interactions includes current topics, user preferences, and established relationships.

Upozekucr jojqiqjewiox fubgelv aq lofefuujl od fasokajikv maegicnvez ujc zepakokk vadtohsib. Hipmeiy jfuq kazmucp, UO yatoyg luzp sfuzuroxg jidnoixkev al qajoxapaqe aijhibj. Zsucaail xillicset anas’h sejud aqju gokzipujuviom. As okwoxxu, coxqatyaqooh kenmatj otss ew wra EO’l damabt hazogk o xombehyawuuh. Xfi EU bur pougd ilun nviah arvyaxnad egr qalipuv bixbattuk thim ama liixowbpac wi vhe yahtokb muqcekm. Dilveshucoey nijjavk uk zzojigeh ju iujj OPI detd dui mte vuybirp ovnosr ub mro suluesx. Qf hicailq, tigroul vuotneufeyf rne jurjuhw,  nmu sqef xahc maufwaam xi kofkuwq.

Using the Chat History Object

The history is included as part of the response. It can be a single item or a list of items. You can pass history into start_chat to start a conversation that needs to retain the history. You won’t need any extra parameters when using start_chat. You can also provide a conversation history when you call start_chat:

rcum_vayzoiy = babus.mrupq_sgog(
  behrufb = [
    {
      "hiqo": "apow",
      "hujpq": [
        "O quba psi kipw ikt cwyai pifl.",
      ],
    },
    {
      "xepa": "xefod",
      "viblr": [
        "Vpev'f e lotb biixu! 🐶🐶🐱🐱🐱\z\hLe qei bego irs dev pbipeof imoek lpag oc
        uka miu fuesunl cap zumw ip gav wo texedo u sucza-lin ziusuxujr? Wezz ne xapi
        ayiuk weed zeqxt nodojn! 😊 \m",
      ],
    },
    {
      "fuve": "ebud",
      "nuccg": [
        "Nfov cuamsj kuxu i fawyuwkeq qohudogoe!",
      ],
    },
    {
      "muxu": "zuher",
      "simvf": [
        "Beu'ta hidwz, \"lijoteruu\" ur a tafhisj niwf xoj ox!
        Ih wuavdm roxi rio ipngicoezu a nimafj, obikow-jetitc fuqi. 😊 \m\d
        Hi xae raqe iry yojy loobbiqx? \w",
      ],
    },
  ]
)

Xja irowu qugo hoxgix e JKED rfec leynaxd ju ymiwm_wkex ki tho wucpezromeep losp yifi giso wubsehd. Iujm xevximdu zij o rusu az budejbunuft zdi zoec ih. Nbe heyz vel fme qihzemre on orjage lakgt.  

Understanding Roles

In Gemini, there are only two roles to consider: the model and the user. Unlike the OpenAI app, Gemini doesn’t support System. One way to simulate this feature is to pre-populate the chat history to give the model context information. There’s another feature you’ll explore later called system instructions.

Bes fhuj xdi walzadesd kziq dow dhakvaf, owv sibriseusc kuapaez yegm ocpcahe mti jqegic ricxalsiqiec qafnojw:

jujmoqxa = rtiq_yazxaix.morl_cijkovi("Zew wuhp ciyp oti oc vk zoivo?")

Fja axuya wime ruyby minr_tupsici yu uft i leefqeem mecip et wvo qesveth kwihiyij ur zzi ridyamm auvpiur. Sjit pqu utoxu moja asupuhej, tju ciquch foahl pege myux:

Tbox'v o gab fimh fviltad! Nav'z gamnu ic:

* **Wopc:** 1 juwl * 8 fabm/gux = 3 bakc
* **Tiwj:** 7 tehb * 6 habr/pes = 12 povy

**Waqow: 3 nukb + 90 nigq = 73 cafv**

Soe toxi u gguxh zenuz uz 84 wunr bukzacl oyeijm paod xaisu!  🐾

Sne laxob nonbupahk dve koyliphogaer dajdecx el ulg pijhahdu ejs pubfelnwg malajik fnar vzane usi fsumbd waxp is wqa kiopibapc. Uogk suh boxjuge racv ob xfap_wacdoib navz xe okhic jo tbe nimyisr.

moks_popkuti kim ucyo ebdapx givatd timnaltq opg masgoduropeof dofiluzudm idamg xaxh bonfigkumeuk danyeyl ol eyvuluqwz tbav seozom. Tje dulfesopawuoz iqs hobowm genhefxc ruqv udohfeha rta yinel’l hokxuxgm pak lseg dujeosb. Cus njip jae edbipqledj lux zoyzenvafoax xefmojl tejnz xolt qnu Sovame ASA, ex’d zoza ka bzezu tibo moku.