namamodeli amakhulu olimi (llms)
Amamodeli amakhulu olimi (LLMS) Zisezinhlelweni ze-AI ezithuthukile ezakhelwe kwinethiwekhi ejulile ye-neural efana nabaguquli futhi baqeqeshelwe amanani amakhulu ombhalo ukukhiqiza ulimi olufana nolwemuntu. I-LLMS efana ne-chatgpt, uClaude, i-Gemini noGrok bangabhekana nemisebenzi eminingi eyinselele futhi basetshenziswa kuwo wonke amasimu afana nesayensi, ezempilo, ezemfundo kanye nezezimali.
Umenzeli we-AI udlulisela amaCapabilites ama-LLMS ukuxazulula imisebenzi engaphezu kolwazi lwayo eliqeqeshwe ngaphambili. I-LLM ingabhala isifundo sePython kusuka kulokho okufundile ngesikhathi sokuqeqeshwa. Uma ukucela ukuthi ubhukhe indiza, umsebenzi udinga ukufinyelela kwikhalenda lakho, ukusesha kwewebhu kanye nekhono lokuthatha isenzo, lokhu kudlula ulwazi lwangaphambi kwe-LLM. Ezinye zezenzo ezijwayelekile zifaka:
- Isimo sezulu: I-LLM ixhumeka kwithuluzi lokusesha leWebhu ukuyolanda isimo sezulu sakamuva.
- Umenzeli wokubhuka: I-ejenti ye-AI engabheka ikhalenda lomsebenzisi, sesha iwebhu ukuze uvakashele indawo yokubhuka njenge-Expedia ukuthola izinketho ezitholakalayo zezindiza namahhotela, uqedele umsebenzisi ukuze umsebenzisi.
Isebenza kanjani i-AI Ejenti
Ama-Agents ai akha uhlelo olusebenzisa imodeli enkulu yolimi ukuhlela, ukucabanga, futhi athathe izinyathelo zokusebenzisana nemvelo yalo ukusebenzisa amathuluzi aphakanyisiwe kusuka ekuboniseni imodeli yokuxazulula umsebenzi othile.
Isakhiwo esiyisisekelo somenzeli we-AI
- Imodeli enkulu yolimi (LLM): I-LLM yiyona ingqondo ye-AI ejenti. Kuthatha ngokushesha umsebenzisi, amasu kanye nezizathu nangezizathu ngesicelo futhi wephule inkinga ezinyangeni ezinquma ukuthi yimaphi amathuluzi okufanele awasebenzise ukuqedela umsebenzi.
- Ithuluzi Uhlaka olusetshenziswa yi-ejenti ukwenza isenzo ngokususelwa ohlelweni nasekubonisaneni kusuka kumodeli enkulu yolimi. Uma ubuza i-LLM ukubhuka itafula lakho endaweni yokudlela, amathuluzi angenzeka azosetshenziswa Faka iKhalenda ukuhlola ukutholakala kwakho kanye ne-Web Search Tool yakho ukufinyelela kuwebhusayithi yokudlela futhi ubeke ukubhukelwa.
Ukwenza izinqunywa zezinqunywa ze-ejenti zokubhuka ai
Ama-Agents AI angafinyelela amathuluzi ahlukene ngokuya ngomsebenzi. Ithuluzi lingaba isitolo sedatha, njenge-database. Isibonelo, umenzeli wokusekela amakhasimende angafinyelela imininingwane ye-akhawunti yeKhasimende nomlando wokuthenga futhi anqume ukuthi uzothola nini lolo lwazi ukusiza ukuxazulula inkinga.
Ama-Agents ai asetshenziselwa ukuxazulula imisebenzi ehlukahlukene, futhi kunama-ejenti amaningi anamandla atholakalayo. Ama-ejenti amakhodi, ikakhulukazi ama-agentic ads afana nesikhombisi, iWindsurf, kanye ne-GitHub Copilot basiza onjiniyela babhale futhi balungisa iphutha ngokushesha futhi bakhe amaphrojekthi ngokushesha. Ama-ejenti wokufaka ama-CLI afana neClaude Code neCodex CLI angaxhumana nedeskithophu yomsebenzisi ne-terminal ukwenza imisebenzi yamakhodi. I-Chatgpt isekela ama-ejenti angenza izenzo ezinjengokubhuka ukubhuka egameni lomsebenzisi. Ama-ejenti ahlanganiswe nokusebenza kokuxhaswa kwamakhasimende ukuxhumanisa namakhasimende futhi axazulule izindaba zawo.
Ukushayela ucingo
Ukushayela ucingo kuyindlela yokuxhuma imodeli enkulu yolimi (LLM) kumathuluzi angaphandle afana nama-API noma imininingwane. Isetshenziswa ekwakheni ama-Agents ai ukuxhuma i-LLMS kumathuluzi. Ekusebenzeni kokusebenza, ithuluzi ngalinye lichazwa njengomsebenzi wekhodi (ngokwesibonelo, i-api yesimo sezulu ukulanda isibikezelo sakamuva) kanye ne-json schema ecacisa ukuthi i-LLM isebenze nini futhi kanjani.
Uhlobo lomsebenzi oluchazwe luncike emsebenzini we-ejenti yakhelwe ukwenza. Isibonelo, ku-ejenti yokuxhaswa kwamakhasimende singachaza umsebenzi ongawukhipha imininingwane emininingwane engahleliwe, efana nama-PDF aqukethe imininingwane ngemikhiqizo yebhizinisi.
Kulokhu okuthunyelwe ngizokhombisa ukuthi ngisebenzisa kanjani umsebenzi obizayo ekwakheni i-ejenti yokusesha yeWebhu elula usebenzisa i-GPT-5 njengemodeli enkulu yolimi.
Isakhiwo esiyisisekelo somenzeli we-Web Search
Umqondo oyinhloko ngemuva kwe-ejenti yokusesha yeWebhu:
- Chaza umsebenzi wekhodi ukuphatha usesho lwewebhu.
- Chaza imiyalo yangokwezifiso eqondisa imodeli enkulu yolimi ekunqumeni ukuthi ungayibiza nini umsebenzi wokusesha wewebhu osuselwa kumbuzo. Isibonelo, uma umbuzo ubuza ngesimo sezulu samanje, i-ejenti yokusesha yeWebhu izobona isidingo sokucinga i-Intanethi ukuthola imibiko yesimo sezulu yakamuva. Kodwa-ke, uma umbuzo ubuza ukuthi ubhale okokufundisa ngolimi oluhlelayo olufana noPython, okuthile okungakuphendula ngolwazi lwayo oluqeqeshelwe ngaphambili ngeke kushayele umsebenzi wokucinga wewebhu futhi uzophendula ngqo esikhundleni salokho.
Okudingekayo kuqala
Dala i-akhawunti ye-OpenAI futhi ukhiphe ukhiye we-API
1: Dala i-akhawunti ye-OpenAI uma ungenayo
2: khiqiza ukhiye we-API
Setha futhi usebenzise imvelo
python3 -m venv env
source env/bin/activateThumela ukhiye we-OpenAi API
export OPENAI_API_KEY="Your Openai API Key"Isethaphu ngesesho lokusesha ngewebhu
I-Tavily iyithuluzi elikhethekile lokusesha lewebhu labameli be-AI. Dala i-akhawunti ku-tavily.com, futhi uma iphrofayela yakho isethwe, kuzokhiqizwa ukhiye we-API ukuthi ungakopisha endaweni yakho. I-AccountA entsha yathola amakhredithi wamahhala ayi-1000 angasetshenziselwa ukusesha kwewebhu okungu-1000.
Thumela ukhiye we-tavily API
export TAVILY_API_KEY="Your Tavily API Key"Faka amaphakheji
pip3 install openai
pip3 install tavily-pythonUkwakha i-ejenti yokusesha iwebhu nge-Function Call Isinyathelo ngesinyathelo
Isinyathelo 1: Dala umsebenzi wokusesha wewebhu nge-tavily
Umsebenzi wokusesha weWebhu usetshenziswa usebenzisa i-tavily, ekhonza njengethuluzi lokusebenza kwe-ejenti yeWebhu.
from tavily import TavilyClient
import os
tavily = TavilyClient(api_key=os.getenv("TAVILY_API_KEY"))
def web_search(query: str, num_results: int = 10):
try:
result = tavily.search(
query=query,
search_depth="basic",
max_results=num_results,
include_answer=False,
include_raw_content=False,
include_images=False
)
results = result.get("results", [])
return {
"query": query,
"results": results,
"sources": [
{"title": r.get("title", ""), "url": r.get("url", "")}
for r in results
]
}
except Exception as e:
return {
"error": f"Search error: {e}",
"query": query,
"results": [],
"sources": [],
}Ukuwohloka kwekhodi yewebhu
Kuqalwa kabusha ngokhiye wayo we-API. Ku web_search Umsebenzi, izinyathelo ezilandelayo zenziwa:
- Umsebenzi wokusesha oshisayo ubizelwe ukusesha i-Intanethi futhi uthole imiphumela ephezulu eyi-10.
- Imiphumela yokusesha nemithombo yabo ehambelana nayo iyabuyiselwa.
Lokhu kukhishwa okubuyisiwe kuzosebenza njengomongo ofanele we-ejenti yokusesha yeWebhu: esizochaza kamuva kule ndatshana, ukuyola ulwazi olusha lwemibuzo (ukushukumisa) okudinga idatha yesikhathi sangempela.
Isinyathelo 2: Dala i-schema yamathuluzi
I-Tool Schema ichaza imiyalo yangokwezifiso yemodeli ye-AI lapho kufanele ilubize khona ithuluzi, kulokhu ithuluzi elizosetshenziswa emsebenzini wokusesha weWebhu. Iphinde icacise imibandela nezenzo okufanele zithathwe lapho imodeli ibiza ithuluzi. I-JSSO TOOL SCHEMA ichazwa ngezansi ngokususelwa ku-Opelai Tool Schema Hlela.
tool_schema = [
{
"type": "function",
"name": "web_search",
"description": """Execute a web search to fetch up to date information. Synthesize a concise,
self-contained answer from the content of the results of the visited pages.
Fetch pages, extract text, and provide the best available result while citing 1-3 sources (title + URL).
If sources conflict, surface the uncertainty and prefer the most recent evidence.
""",
"strict": True,
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Query to be searched on the web.",
},
},
"required": ["query"],
"additionalProperties": False
},
},
]
Izakhiwo zeSchema
- Uhlobo: Icacisa ukuthi uhlobo lwensimbi luwumsebenzi.
- Igama: igama lomsebenzi elizosetshenziselwa ukushaya amathuluzi, okuyilo I-Web_Search.
- Incazelo: Ichaza ukuthi yini imodeli ye-AI okufanele yenziwe lapho ibiza ithuluzi lokucinga leWebhu. Ifundisa imodeli ukusesha i-Intanethi usebenzisa I-Web_Search Umsebenzi wokulanda imininingwane esesikhathini futhi ukhiphe imininingwane efanelekile ukukhiqiza impendulo enhle kakhulu.
- Ngenhliziyo: Kuhlelwe iqiniso, le mpahla iyalela i-LLM ukuthi ilandele ngokuqinile imiyalo ye-schema yamathuluzi.
- Amapharamitha: Ichaza amapharamitha azodluliselwa ku I-Web_Search sebenza. Kulokhu, kunepharamitha eyodwa kuphela: khalaza emelela igama lokusesha ukuze abheke ku-inthanethi.
- Kuyadingeka: Iyalela i-LLM ukuthi umbuzo uyipharamitha eliyisibopho se I-Web_Search sebenza.
- I-ExtsProPeries: Ihlelelwe amanga, okusho ukuthi ithuluzi into yezimpikiswano ayikwazi ukufaka noma yimaphi amapharamitha ngaphandle kwaleyo echaziwe ngaphansi Amapharamitha.ProPerties.
Isinyathelo 3: Dala i-ejenti yokusesha yeWebhu usebenzisa ukubiza kwe-GPT-5 nokusebenza
Ekugcineni ngizokwakha umenzeli esingaxoxa naye, ongasesha iwebhu uma idinga imininingwane esesikhathini. Ngizosebenzisa GPT-5-MINIimodeli esheshayo nenembile evela ku-Opelai, kanye nomsebenzi obiza ukucela ithuluzi le-schema kanye Umsebenzi wokusesha wewebhu sekuchaziwe.
from datetime import datetime, timezone
import json
from openai import OpenAI
import os
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
# tracker for the last model's response id to maintain conversation's state
prev_response_id = None
# a list for storing tool's results from the function call
tool_results = []
while True:
# if the tool results is empty prompt message
if len(tool_results) == 0:
user_message = input("User: ")
""" commands for exiting chat """
if isinstance(user_message, str) and user_message.strip().lower() in {"exit", "q"}:
print("Exiting chat. Goodbye!")
break
else:
user_message = tool_results.copy()
# clear the tool results for the next call
tool_results = []
# obtain current's date to be passed into the model as an instruction to assist in decision making
today_date = datetime.now(timezone.utc).date().isoformat()
response = client.responses.create(
model = "gpt-5-mini",
input = user_message,
instructions=f"Current date is {today_date}.",
tools = tool_schema,
previous_response_id=prev_response_id,
text = {"verbosity": "low"},
reasoning={
"effort": "low",
},
store=True,
)
prev_response_id = response.id
# Handles model response's output
for output in response.output:
if output.type == "reasoning":
print("Assistant: ","Reasoning ....")
for reasoning_summary in output.summary:
print("Assistant: ",reasoning_summary)
elif output.type == "message":
for item in output.content:
print("Assistant: ",item.text)
elif output.type == "function_call":
# obtain function name
function_name = globals().get(output.name)
# loads function arguments
args = json.loads(output.arguments)
function_response = function_name(**args)
tool_results.append(
{
"type": "function_call_output",
"call_id": output.call_id,
"output": json.dumps(function_response)
}
)Isinyathelo ngesinyathelo sekhodi yokuphuka
from openai import OpenAI
import os
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
prev_response_id = None
tool_results = []- Iqale i-Opelai Model API nge ukhiye we-API.
- Iqale ukuguquguquka okubili I-Prev_response_id na- Amathuluzi_Rerults. I-Prev_response_id ugcina umkhondo wempendulo yemodeli yokugcina isimo sengxoxo, futhi Amathuluzi_Rerults uhlu olugcina okuphumayo olubuyiselwe ku I-Web_Search ucingo.
Ingxoxo isebenza ngaphakathi kwe uluphu. Umsebenzisi ungena umyalezo kanye nemodeli ebizwa nge-Tool Schema yamukela umyalezo, izizathu phezu kwayo, inquma ukuthi ungayibiza yini ithuluzi lokusesha leWebhu, bese ithuluzi lethuluzi lidluliselwa emuva kwimodeli. Imodeli ikhiqiza impendulo eyaziyo. Lokhu kuyaqhubeka kuze kube yilapho umsebenzisi ekhipha ingxoxo.
Ikhodi yokuhamba nge-loop
if len(tool_results) == 0:
user_message = input("User: ")
if isinstance(user_message, str) and user_message.strip().lower() in {"exit", "q"}:
print("Exiting chat. Goodbye!")
break
else:
user_message = tool_results.copy()
tool_results = []
today_date = datetime.now(timezone.utc).date().isoformat()
response = client.responses.create(
model = "gpt-5-mini",
input = user_message,
instructions=f"Current date is {today_date}.",
tools = tool_schema,
previous_response_id=prev_response_id,
text = {"verbosity": "low"},
reasoning={
"effort": "low",
},
store=True,
)
prev_response_id = response.id- Ihlola uma Amathuluzi_Rerults ayinalutho. Uma kunjalo, umsebenzisi uzokwaziswa ukuthi athayiphe umyalezo, ngenketho yokuyeka ukusebenzisa Phuma noma qhakaziza.
- Uma Amathuluzi_Rerults ayinalutho, Umsebenzisi_Message izosethwa kwi-Ithuluzi eliqoqiwe elizothunyelwa kumodeli. Amathuluzi_Rerults kusulwa ukugwema ukusetha okufanayo Imiphumela yethuluzi ku-loop iteration elandelayo.
- Usuku lwamanje (namuhla_date) Itholakala ukuthi isetshenziswe yimodeli ukwenza izinqumo zokwazi isikhathi.
- Iosha Iklayenti.Responses.create Ukukhiqiza impendulo yemodeli futhi kwamukela amapharamitha alandelayo:
- Imodeli: Setha ukuze GPT-5-MINI.
- Okokufaka: Yamukela umyalezo womsebenzisi.
- Imiyalo: Setha kusuku lwamanje (namuhla_date).
- Amathuluzi: Setha ku-schema yamathuluzi eyachazwa ngaphambili.
- I-Domert_response_id: isethwe ku-ID yempendulo edlule ngakho-ke imodeli ingakwazi ukugcina isimo sengxoxo.
- Umbhalo: I-Verbosity isethwe ku-Low ukuze ugcine impendulo yemodeli yokuphendula.
- Ukubonisana: I-GPT-5-MINI iyimodeli yokubonisana, setha umzamo wokucabanga ukuze unciphise impendulo esheshayo. Ngemisebenzi eyinkimbinkimbi esingayibeka phezulu.
- Isitolo: Itshela imodeli ukuthi igcine impendulo yamanje ukuze itholakale emuva kwesikhathi futhi isize ngokuqhubeka kwengxoxo.
- I-Prev_response_id
for output in response.output:
if output.type == "reasoning":
print("Assistant: ","Reasoning ....")
for reasoning_summary in output.summary:
print("Assistant: ",reasoning_summary)
elif output.type == "message":
for item in output.content:
print("Assistant: ",item.text)
elif output.type == "function_call":
# obtain function name
function_name = globals().get(output.name)
# loads function arguments
args = json.loads(output.arguments)
function_response = function_name(**args)
# append tool results list with the the function call's id and function's response
tool_results.append(
{
"type": "function_call_output",
"call_id": output.call_id,
"output": json.dumps(function_response)
}
)Lokhu kucubungula umphumela wokuphendula kwemodeli futhi kwenza okulandelayo;
- Uma uhlobo lokukhipha lubonisa, phrinta into ngayinye esifingwini sengqondo.
- Uma uhlobo lokukhipha lungumyalezo, luya ngokuqukethwe bese uphrinta into ngayinye yombhalo.
- Uma uhlobo lokukhipha luyinkokhelo yomsebenzi, thola igama lomsebenzi, ukuhlanganisa izimpikiswano zalo, bese uwadlulisela emsebenzini (I-Web_Search) ukukhiqiza impendulo. Kulokhu, impendulo yokusesha iwebhu iqukethe imininingwane esesikhathini efanelekile kumyalezo womsebenzisi. Ekugcineni Faka isicelo sempendulo ye-WUND CALL YOKWAKHA NOKUFUNDA I-ID Amathuluzi_Rerults. Lokhu kuvumela i-loop elandelayo ithumele ithuluzi liphumela emuva kwimodeli.
Ikhodi ephelele ye-ejenti yokusesha yeWebhu
from datetime import datetime, timezone
import json
from openai import OpenAI
import os
from tavily import TavilyClient
tavily = TavilyClient(api_key=os.getenv("TAVILY_API_KEY"))
def web_search(query: str, num_results: int = 10):
try:
result = tavily.search(
query=query,
search_depth="basic",
max_results=num_results,
include_answer=False,
include_raw_content=False,
include_images=False
)
results = result.get("results", [])
return {
"query": query,
"results": results,
"sources": [
{"title": r.get("title", ""), "url": r.get("url", "")}
for r in results
]
}
except Exception as e:
return {
"error": f"Search error: {e}",
"query": query,
"results": [],
"sources": [],
}
tool_schema = [
{
"type": "function",
"name": "web_search",
"description": """Execute a web search to fetch up to date information. Synthesize a concise,
self-contained answer from the content of the results of the visited pages.
Fetch pages, extract text, and provide the best available result while citing 1-3 sources (title + URL). "
If sources conflict, surface the uncertainty and prefer the most recent evidence.
""",
"strict": True,
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Query to be searched on the web.",
},
},
"required": ["query"],
"additionalProperties": False
},
},
]
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
# tracker for the last model's response id to maintain conversation's state
prev_response_id = None
# a list for storing tool's results from the function call
tool_results = []
while True:
# if the tool results is empty prompt message
if len(tool_results) == 0:
user_message = input("User: ")
""" commands for exiting chat """
if isinstance(user_message, str) and user_message.strip().lower() in {"exit", "q"}:
print("Exiting chat. Goodbye!")
break
else:
# set the user's messages to the tool results to be sent to the model
user_message = tool_results.copy()
# clear the tool results for the next call
tool_results = []
# obtain current's date to be passed into the model as an instruction to assist in decision making
today_date = datetime.now(timezone.utc).date().isoformat()
response = client.responses.create(
model = "gpt-5-mini",
input = user_message,
instructions=f"Current date is {today_date}.",
tools = tool_schema,
previous_response_id=prev_response_id,
text = {"verbosity": "low"},
reasoning={
"effort": "low",
},
store=True,
)
prev_response_id = response.id
# Handles model response's output
for output in response.output:
if output.type == "reasoning":
print("Assistant: ","Reasoning ....")
for reasoning_summary in output.summary:
print("Assistant: ",reasoning_summary)
elif output.type == "message":
for item in output.content:
print("Assistant: ",item.text)
# checks if the output type is a function call and append the function call's results to the tool results list
elif output.type == "function_call":
# obtain function name
function_name = globals().get(output.name)
# loads function arguments
args = json.loads(output.arguments)
function_response = function_name(**args)
# append tool results list with the the function call's id and function's response
tool_results.append(
{
"type": "function_call_output",
"call_id": output.call_id,
"output": json.dumps(function_response)
}
)Uma usebenzisa ikhodi, ungaxoxa kalula ne-ejenti ukubuza imibuzo edinga imininingwane yakamuva, efana nesimo sezulu samanje noma ukukhishwa komkhiqizo kwakamuva. Umenzeli uphendula ngolwazi olusha kanye nemithombo ehambisanayo evela kwi-Intanethi. Ngezansi kungukukhipha isampula kusuka ku-ukuphela.
User: What is the weather like in London today?
Assistant: Reasoning ....
Assistant: Reasoning ....
Assistant: Right now in London: overcast, about 18°C (64°F), humidity ~88%, light SW wind ~16 km/h, no precipitation reported. Source: WeatherAPI (current conditions) —
User: What is the latest iPhone model?
Assistant: Reasoning ....
Assistant: Reasoning ....
Assistant: The latest iPhone models are the iPhone 17 lineup (including iPhone 17, iPhone 17 Pro, iPhone 17 Pro Max) and the new iPhone Air — announced by Apple on Sept 9, 2025. Source: Apple Newsroom —
User: Multiply 500 by 12.
Assistant: Reasoning ....
Assistant: 6000
User: exit
Exiting chat. Goodbye!Ungabona imiphumela ngemithombo yabo ehambisanayo yewebhu. Uma uyicela ukwenza umsebenzi ongadingi imininingwane esesikhathini, njengokubala kwezibalo noma ikhodi yokubhala i-ejenti iphendula ngqo ngaphandle kokusesha kwewebhu.
Qaphela: I-ejenti yokusesha yeWebhu i-ejenti elula, ephathekayo eyodwa. Izinhlelo ze-Agentic ezithuthukile zihlela amathuluzi akhethekile amaningi futhi usebenzise imemori esebenza kahle ukugcina umongo, uhlelo, futhi uxazulule imisebenzi eyinkimbinkimbi.
Ukugcina
Kulesi siposo ngichaze ukuthi i-A Ejenti ye-AI isebenza kanjani nokuthi ingeza kanjani amakhono emodeli enkulu yolimi ukuze ahlangane nemvelo yawo, enza isenzo nokuxazulula imisebenzi ngokusebenzisa amathuluzi. Ngibuye ngachaza ukubiza umsebenzi nokuthi kunika amandla kanjani ama-LLM ukushaya amathuluzi. Ngikhombise ukuthi ungakha kanjani i-schema yamathuluzi yokubiza okuchaza ukuthi i-LLM kufanele ibize kanjani ithuluzi ukwenza isenzo. Ngichaze umsebenzi wokusesha weWebhu ngisebenzisa ukuthutha okuthe xaxa kusuka kuwebhu bese kukhombisa igxathu negxathu ukuthi ngiyokwakha kanjani i-ejenti yokusesha iwebhu ngisebenzisa ukubiza umsebenzi kanye ne-GPT-5-MINI njenge-LLM. Ekugcineni, sakha i-ejenti yokusesha yeWebhu ekwazi ukubuyisa imininingwane esesikhathini kwi-Intanethi ukuphendula imibuzo yomsebenzisi.
Bheka i-GitHub Repo yami, IGenai-Courses Lapho ngishicilele khona izifundo eziningi ezihlokweni ezahlukahlukene ze-AI ezikhiqizayo. Kubandakanya nesiqondisi ekwakheni i-agentic rag usebenzisa ukubiza umsebenzi.
Finyelela kimi nge:
I-imeyili: [email protected]
I-LinkedIn:
Ukunqubekela phambili
