Ndlela Yo Aka Mafambelo Ya Ntirho Ya AI Ya Misava Ya Xiviri Hi AutoGen: Nkongomiso Wa Goza Hi Goza

Kutani, u tshame u tlanga hi Timodelo ta Ririmi Letikulu naswona u sungula ku hlanganisa Generative AI eka ti-app ta wena? Sweswo swa chavisa! Kambe a hi vekeni va xiviri. A hi minkarhi hinkwayo ti-LLM ti tikhomaka hi ndlela leyi hi lavaka leswaku ti tikhoma ha yona. Va fana ni vana vo biha va kondlo-a-ndzi-dyi lava nga ni mianakanyo ya vona vini! Hi ku hatlisa u swi xiya leswaku tinketana to olova ta xihatla a ti enelanga ntsena. Minkarhi yin’wana, hi lava swin’wana leswi engetelekeke. Minkarhi yin’wana, hi lava maendlelo ya ntirho ya ti-agent to tala! Hi kona laha yi nghenaka kona. AutoGen A hi tekeni xikombiso. Imagine u endla app yo tsala tinotsi (Swi le rivaleni leswaku misava a yi na swona swo enela. 😝). Kambe hey, hi lava ku endla nchumu wo hlawuleka. Hi lava ku teka noti yo olova, yo ka yi nga swekiwanga leyi mutirhisi a hi nyikaka yona ivi hi yi hundzula tsalwa leri lulamisiweke hi vuntshwa hi ku helela, leri heleleke hi nkatsakanyo, nhlokomhaka leyi nga hlawuriwa, na nxaxamelo wa mintirho leyi faneleke ku endliwa hi xiothomethi. Naswona hi lava ku endla hinkwaswo leswi handle ko tshoveka nyuku - kahle, eka vayimeri va wena va AI at least. Okay, sweswi, ndza swi tiva leswi u swi ehleketaka - “Xana leswi a swi fani na minongonoko ya rookie?” Eka sweswo, ndzi ri, u vula ntiyiso. Swi vula... kambe swi tano! Kambe u nga kanganyisiwi hi ku olova ka maendlelo ya ntirho. Vuswikoti lebyi u nga ta byi dyondza laha - ku fana na ku khoma vayimeri va AI, ku tirhisa vulawuri bya mafambelo ya ntirho, na ku lawula matimu ya mbulavurisano - swi ta ku pfuna ku yisa ntlangu wa wena wa AI eka xiyimo lexi landzelaka. So buckle up, hikuva hi ta dyondza ku endla ti AI workflows hi ku tirhisa AutoGen! https://youtu.be/-ls9QLoQfKc ya xitsonga Loko hi nga si sungula, xiya leswaku u nga kuma xihlanganisi xa khodi hinkwayo ya xihlovo eka . GitHub Ku Aka Mafambiselo ya Ntirho ya Xihlawuhlawu A hi sunguleni hi use-case yo sungula - “Ku tumbuluxa nkatsakanyo wa noti leyi landzeriwaka hi nhlokomhaka ya xiyimo”. Ku vula ntiyiso, a hi lavi ku tirhisa vayimeri laha hakunene. Kambe hey, hi fanele hi sungula kun’wana a swi tano ke? Goza 1: Ku tumbuluxa Base LLM Config ya hina Tiframework ta agent to fana na AutoGen minkarhi hinkwayo ti lava leswaku hi lulamisa ti parameter ta model. Hi vulavula hi modele na fallback model ku yi tirhisa, mahiselo, hambi ku ri swiyimiso swo fana na timeout na caching. Eka mhaka ya AutoGen, xiyimiso xexo xi languteka hi ndlela leyi: # build the gpt_configuration object base_llm_config = { "config_list": [ { "model": "Llama-3-8B-Instruct", "api_key": os.getenv("OPENAI_API_KEY"), "base_url": os.getenv("OPENAI_API_URL"), } ], "temperature": 0.0, "cache_seed": None, "timeout": 600, } Hilaha u nga swi vonaka hakona, ndzi fanboy leyikulu ya AI leyi pfulekeke naswona ndzi hlambanya hi Llama 3. U nga endla leswaku AutoGen yi kombetela eka hi ku lulamisa ntsena mimpimo ya na . Kutani, titwe u ntshunxekile ku tirhisa Groq, Together.ai, kumbe hambi ku ri vLLM ku rhurhela modele wa wena laha tikweni. Ndzi tirhisa . sevha yihi na yihi ya inference leyi fambisanaka na OpenAI api_key base_url Inferix Hakunene swa olova hi ndlela yoleyo! Ndzi lava ku tiva! Xana u nga tsakela nkongomiso lowu fanaka wa ku rhurhela ka AI loku pfulekeke? Ndzi tivise eka ti comments. Goza 2: Ku Tumbuluxa Vayimeri va Hina Ku sungula vayimeri va mbulavurisano eka AutoGen swi kongomile swinene; ntsena phakela base LLM config xikan’we na rungula ra sisiteme naswona u kahle ku famba. import autogen def get_note_summarizer(base_llm_config: dict): # A system message to define the role and job of our agent system_message = """You are a helpful AI assistant. The user will provide you a note. Generate a summary describing what the note is about. The summary must follow the provided "RULES". "RULES": - The summary should be not more than 3 short sentences. - Don't use bullet points. - The summary should be short and concise. - Identify and retain any "catchy" or memorable phrases from the original text - Identify and correct all grammatical errors. - Output the summary and nothing else.""" # Create and return our assistant agent return autogen.AssistantAgent( name="Note_Summarizer", # Lets give our agent a nice name llm_config=base_llm_config, # This is where we pass the llm configuration system_message=system_message, ) def get_title_generator(base_llm_config: dict): # A system message to define the role and job of our agent system_message = """You are a helpful AI assistant. The user will provide you a note along with a summary. Generate a title based on the user's input. The title must be witty and easy to read. The title should accurate present what the note is about. The title must strictly be less than 10 words. Make sure you keep the title short. Make sure you print the title and nothing else. """ # Create and return our assistant agent return autogen.AssistantAgent( name="Title_Generator", llm_config=base_llm_config, system_message=system_message, ) Xiphemu xa nkoka swinene xo tumbuluxa vayimeri i . Tinyike nkarhinyana u languta leyi ndzi yi tirhiseke ku lulamisa ti-agent ta mina. system_message system_message I swa nkoka ku tsundzuka leswaku ndlela leyi AI Agents eka AutoGen yi tirhaka ha yona i ku nghenelela eka . Ndlela leyi va hlamuselaka no yisa mbulavurisano emahlweni hi ku helela yi titshege hi leyi va hleriweke ha yona. Leyi i yin’wana ya tindhawu leti u nga ta heta nkarhi wo karhi leswaku u lulamisa swilo. mbulavurisano system_message Hi lava muyimeri un’we ntsena un’wana. Muyimeri wo tirha tanihi muyimeri eka hina vanhu. Muyimeri loyi a nga sungulaka mbulavurisano hi “noti” tanihi xitsundzuxo xa yona xo sungula. def get_user(): # A system message to define the role and job of our agent system_message = "A human admin. Supplies the initial prompt and nothing else." # Create and return our user agent return autogen.UserProxyAgent( name="Admin", system_message=system_message, human_input_mode="NEVER", # We don't want interrupts for human-in-loop scenarios code_execution_config=False, # We definitely don't want AI executing code. default_auto_reply=None, ) A ku na nchumu wo saseka lowu humelelaka laha. Xiya ntsena leswaku ndzi vekile parameter ya eka . Sweswo i swa nkoka. Ku veka leswi eka none swi tiyisisa leswaku mbulavurisano wu hela nkarhi wun’wana na wun’wana loko muyimeri wa mutirhisi a rhumeriwa rungula. default_auto_reply None Oops, ndzi rivele hi ku helela ku tumbuluxa ti agents teto. A hi endleni sweswo hi ku hatlisa hakunene. # Create our agents user = get_user() note_summarizer = get_note_summarizer(base_llm_config) title_generator = get_title_generator(base_llm_config) Goza 3: Seta Nhlanganiso wa Agent hi ku tirhisa GroupChat Xiphemu xo hetelela xa xiphiqo i ku endla leswaku vayimeri va hina va hlanganisa. Hi fanele ku kumisisa ntlhandlamano wa ku nghenelela ka vona na ku teka xiboho xa leswaku hi tihi vayimeri lava faneleke. Okay, sweswo swi tlula xiphemu xin’we. Kambe wa yi kuma yinhla! 🙈 Ntlhantlho wun’wana lowu nga kotekaka ku nga va ku tshika AI yi kuma ntlhandlamano lowu Vayimeri va hlanganyelaka eka wona. Leyi a hi mianakanyo yo biha. Entiyisweni, leyi i ndlela ya mina yo ya eka yona loko ndzi tirhana na swiphiqo leswi rharhanganeke laha muxaka wa maendlelo ya ntirho wu cinca-cincaka. Hambiswiritano, endlelo leri ri ni swiphiqo swa rona. Ntiyiso wu tlhela wu hlasela! Muyimeri loyi a nga na vutihlamuleri byo teka swiboho leswi hakanyingi u lava modele lowukulu, leswi endlaka leswaku ku va na ku hlwela ka le henhla na ku durha. Ku engetela kwalaho, ku ni khombo ra leswaku yi nga ha endla swiboho leswi hoxeke. Eka maendlelo ya ntirho ya deterministic, laha hi tivaka ntlhandlamano wa magoza ka ha ri emahlweni, ndzi tsakela ku khoma swirhabyani na ku kongomisa xikepe hi ndzexe. Nkateko wa kona, AutoGen yi seketela xiyimo lexi xa matirhiselo hi xitirhisiwa xo olova lexi vuriwaka . GroupChat from autogen import GroupChatManager from autogen.agentchat.groupchat import GroupChat from autogen.agentchat.agent import Agent def get_group_chat(agents, generate_title: bool = False): # Define the function which decides the agent selection order def speaker_selection_method(last_speaker: Agent, group_chat: GroupChat): # The admin will always forward the note to the summarizer if last_speaker.name == "Admin": return group_chat.agent_by_name("Note_Summarizer") # Forward the note to the title generator if the user wants a title if last_speaker.name == "Note_Summarizer" and generate_title: return group_chat.agent_by_name("Title_Generator") # Handle the default case - exit return None return GroupChat( agents=agents, messages=[], max_round=3, # There will only be 3 turns in this group chat. The group chat will exit automatically post that. speaker_selection_method=speaker_selection_method, ) Anakanya hi tani hi ntlawa wa WhatsApp laha ti agent hinkwato tinga chat no tirhisana. Setup leyi yi pfumelela ti agents ku aka eka ntirho wa un’wana na un’wana. Tlilasi ya xikan’we na tlilasi leyi fambisanaka leyi vuriwaka yi tirha ku fana na vafambisi va ntlawa, yi hlayisa marungula hinkwawo lawa muyimeri un’wana na un’wana a ma rhumelaka ku tiyisisa leswaku un’wana na un’wana u tshama eka xirhendzevutani na matimu ya mbulavurisano. GroupChat GroupChat GroupChatManager Eka xiphemu xa khodi lexi nga laha henhla, hi endlile leyi nga na custom . yi hi pfumelela ku boxa maendlelo ya hina ya ntirho ya ntolovelo. Hi lexi xifaniso xa xivono xa leswi fanaka. GroupChat speaker_selection_method speaker_selection_method Tanihi leswi kahle-kahle yi nga ntirho wa Python, hi nga endla xin’wana na xin’wana lexi hi xi lavaka ha yona! Leswi swi hi pfuna ku tumbuluxa maendlelo man’wana ya ntirho lama nga ni matimba hakunene. Hi xikombiso, hi nga: speaker_selection_method Hlanganisa vayimeri vambirhi ku tiyisisa ntirho wa un’wana na un’wana. Katsa muyimeri wa loko un’wana wa vayimeri va khale a humesa xihoxo. “Mutlhantlhisi wa swiphiqo” Ku hlohlotela ti webhook eka tisisiteme ta le handle ku va tivisa hi nhluvuko lowu endliweke. Anakanya hi swilo leswi nga kotekaka! 😜 Goza 4: Ku Swi Veka Hinkwaswo Ni Ku Sungula Bulo Goza ro hetelela i ku tumbuluxa xikombiso xa , ku xi phutsela endzeni ka na ku sungula mbulavurisano. GroupChat GroupChatManager # Create our group chat groupchat = get_group_chat([user, note_summarizer, title_generator], generate_title=True) manager = autogen.GroupChatManager(groupchat=groupchat, llm_config=base_llm_config) # Start the chat user.initiate_chat( manager, clear_history=True, message=note, ) Xiya: Mutirhisi u burisana na GroupChatManager GroupChatManager ku nga ri vayimeri ha un’we. A yi na xikombiso xa leswaku hi tihi vayimeri lava nga ta joyina mbulavurisano ku nyika nhlamulo yo hetelela. Sneaky, a swi tano ke? Vuyelo byi ta languteka hi ndlela leyi: Admin (to chat_manager): Note: Convo with editor: - discuss titles and thumbnails - discuss video editing tips tracker - Zeeshan presents the tracker - what trick helps with what - he decidedls if we can experiment with something new - make sure all all videos since how config management works in k8s are backed u - make list of YouTube thumbnail templates - make list of YouTube idea generation limits -------------------------------------------------------------------------------- Next speaker: Note_Summarizer Note_Summarizer (to chat_manager): The note is about a conversation with an editor regarding video production. They discussed titles and thumbnails, as well as a video editing tips tracker presented by Zeeshan, which highlights tricks for specific tasks. Additionally, they ensured that all videos on Kubernetes configuration management are backed up and created lists of YouTube thumbnail templates and idea generation limits. -------------------------------------------------------------------------------- Next speaker: Title_Generator Title_Generator (to chat_manager): "Video Production Chat: Titles, Thumbnails, and Editing Tips" -------------------------------------------------------------------------------- Ku Teka Vulawuri Bya Bulo Lexi landzelaka, hi ta nghena eka xiyimo xo hetelela xa matirhiselo: ku teka “noti” leyi nyikiweke, hi yi lulamisa hi vuntshwa leswaku yi va erivaleni ku antswa, ivi hi tumbuluxa nxaxamelo wa mintirho eka mutirhisi. Hi leyi ndlela leyi hi nga ta famba ha yona eka swona: Hi ta sungula hi ku kuma nxaxamelo wa tinhloko-mhaka leti katsiweke eka xiphephana. Nxaxamelo lowu i matimba lama susumetaka endlelo hinkwaro. Yi simeka swiyenge swa noti leyi fomatiweke nakambe naswona yi kumisisa mpimo wa vuxokoxoko bya mintirho ya hina leyi tumbuluxiweke. Ku ni xiphiqo xin’we ntsena lexitsongo. Muyimeri na a va na mhaka ngopfu na vuhumelerisi bya un'wana na un'wana. Va khathala ntsena hi vuhumelerisi bya . Paraphrazer Task_Creator Topic_Analyzer Kutani, hi lava ndlela yo hlayisa tinhlamulo ta vayimeri lava ti nga pfilunganyi matimu ya mbulavurisano, kutani swi ta va mpfilumpfilu lowu heleleke. Se hi teke vulawuri bya maendlelo ya ntirho; sweswi, i nkarhi wo va boss ya matimu ya mbulavurisano na yona! 😎 Goza 1: Ku tumbuluxa Vayimeri Swilo swo sungula ku sungula, hi fanele hi simeka vayimeri va hina. A ndzi nge mi borhi hi vuxokoxoko so hi leyi code: def get_topic_analyzer(base_llm_config: dict): # A system message to define the role and job of our agent system_message = """You are a helpful AI assistant. The user will provide you a note. Generate a list of topics discussed in that note. The output must obey the following "RULES": "RULES": - Output should only contain the important topics from the note. - There must be atleast one topic in output. - Don't reuse the same text from user's note. - Don't have more than 10 topics in output.""" # Create and return our assistant agent return autogen.AssistantAgent( name="Topic_Analyzer", llm_config=base_llm_config, system_message=system_message, ) def get_paraphrazer(base_llm_config: dict): # A system message to define the role and job of our agent system_message = """You are a helpful AI content editor. The user will provide you a note along with a summary. Rewrite that note and make sure you cover everything in the note. Do not include the title. The output must obey the following "RULES": "RULES": - Output must be in markdown. - Make sure you use each points provided in summary as headers. - Each header must start with `##`. - Headers are not bullet points. - Each header can optionally have a list of bullet points. Don't put bullet points if the header has no content. - Strictly use "-" to start bullet points. - Optionally make an additional header named "Addional Info" to cover points not included in the summary. Use "Addional Info" header for unclassified points. - Identify and correct spelling & grammatical mistakes.""" # Create and return our assistant agent return autogen.AssistantAgent( name="Paraphrazer", llm_config=base_llm_config, system_message=system_message, ) def get_tasks_creator(base_llm_config: dict): # A system message to define the role and job of our agent system_message = """You are a helpful AI personal assistant. The user will provide you a note along with a summary. Identify each task the user has to do as next steps. Make sure to cover all the action items mentioned in the note. The output must obey the following "RULES": "RULES": - Output must be an YAML object with a field named tasks. - Make sure each task object contains fields title and description. - Extract the title based on the tasks the user has to do as next steps. - Description will be in markdown format. Feel free to include additional formatting and numbered lists. - Strictly use "-" or "dashes" to start bullet points in the description field. - Output empty tasks array if no tasks were found. - Identify and correct spelling & grammatical mistakes. - Identify and fix any errors in the YAML object. - Output should strictly be in YAML with no ``` or any additional text.""" # Create and return our assistant agent return autogen.AssistantAgent( name="Task_Creator", llm_config=base_llm_config, system_message=system_message, ) Goza 2: Endla ya Custom GroupChat Nkateko-khombo. AutoGen a yi hi pfumeleli ku lawula matimu ya mbulavurisano hi ku kongoma. Kutani, hi fanele ku ya emahlweni hi engetela tlilasi hi ku tirhisiwa ka hina ka ntolovelo. GroupChat class CustomGroupChat(GroupChat): def __init__(self, agents): super().__init__(agents, messages=[], max_round=4) # This function get's invoked whenever we want to append a message to the conversation history. def append(self, message: Dict, speaker: Agent): # We want to skip messages from the Paraphrazer and the Task_Creator if speaker.name != "Paraphrazer" and speaker.name != "Task_Creator": super().append(message, speaker) # The `speaker_selection_method` now becomes a function we will override from the base class def select_speaker(self, last_speaker: Agent, selector: AssistantAgent): if last_speaker.name == "Admin": return self.agent_by_name("Topic_Analyzer") if last_speaker.name == "Topic_Analyzer": return self.agent_by_name("Paraphrazer") if last_speaker.name == "Paraphrazer": return self.agent_by_name("Task_Creator") # Return the user agent by default return self.agent_by_name("Admin") Hi tlula mintirho yimbirhi ku suka eka tlilasi ya xisekelo: GroupChat - Leswi swi lawula leswaku i marungula wahi lama engeteriwaka eka matimu ya mbulavurisano. append - Leyi i ndlela yin'wana yo boxa . select_speaker speaker_selection_method Kambe yima, eka ku nghena swinene eka khodi ya AutoGen, ndzi xiye leswaku yi endla leswaku muyimeri un’wana na un’wana a hlayisa matimu ya mbulavurisano na yena. U nga ndzi vutisi leswaku ha yini. Hakunene a ndzi swi tivi! GroupChatManager Kutani, a hi andziseni na yona ku lulamisa sweswo: GroupChatManager class CustomGroupChatManager(GroupChatManager): def __init__(self, groupchat, llm_config): super().__init__(groupchat=groupchat, llm_config=llm_config) # Don't forget to register your reply functions self.register_reply(Agent, CustomGroupChatManager.run_chat, config=groupchat, reset_config=GroupChat.reset) def run_chat( self, messages: Optional[List[Dict]] = None, sender: Optional[Agent] = None, config: Optional[GroupChat] = None, ) -> Union[str, Dict, None]: """Run a group chat.""" if messages is None: messages = self._oai_messages[sender] message = messages[-1] speaker = sender groupchat = config for i in range(groupchat.max_round): # set the name to speaker's name if the role is not function if message["role"] != "function": message["name"] = speaker.name groupchat.append(message, speaker) if self._is_termination_msg(message): # The conversation is over break # We do not want each agent to maintain their own conversation history history # broadcast the message to all agents except the speaker # for agent in groupchat.agents: # if agent != speaker: # self.send(message, agent, request_reply=False, silent=True) # Pro Tip: Feel free to "send" messages to the user agent if you want to access the messages outside of autogen for agent in groupchat.agents: if agent.name == "Admin": self.send(message, agent, request_reply=False, silent=True) if i == groupchat.max_round - 1: # the last round break try: # select the next speaker speaker = groupchat.select_speaker(speaker, self) # let the speaker speak # We'll now have to pass their entire conversation of messages on generate_reply # Commented OG code: reply = speaker.generate_reply(sender=self) reply = speaker.generate_reply(sender=self, messages=groupchat.messages) except KeyboardInterrupt: # let the admin agent speak if interrupted if groupchat.admin_name in groupchat.agent_names: # admin agent is one of the participants speaker = groupchat.agent_by_name(groupchat.admin_name) # We'll now have to pass their entire conversation of messages on generate_reply # Commented OG code: reply = speaker.generate_reply(sender=self) reply = speaker.generate_reply(sender=self, messages=groupchat.messages) else: # admin agent is not found in the participants raise if reply is None: break # The speaker sends the message without requesting a reply speaker.send(reply, self, request_reply=False) message = self.last_message(speaker) return True, None Ndzi endlile ku lulamisiwa kun’wana lokuntsongo eka ku tirhisiwa ko sungula. U fanele u kota ku landzelela mavonelo ku tiva swo tala. Kambe ku ni nchumu wun’we lowu ndzi lavaka ku wu kandziyisa hakunene. Vatirhi va tisisiteme leti hangalasiweke va swi tiva kahle leswaku vuswikoti lebyi byi ni matimba ku fikela kwihi! U nga ha tlula ndlela ya GroupChatManager ya “run_chat” ku nghenisa eka njhini ya wena ya mafambelo ya ntirho ku fana na Apache Airflow kumbe Temporal. Goza 3: Ku Swi Veka Hinkwaswo Ni Ku Sungula Bulo Hi veka leswi hinkwaswo ku fana na xikombiso lexi hundzeke hi hlalela n’wana loyi a purrr! 🐱 # Create our agents user = get_user() topic_analyzer = get_topic_analyzer(base_llm_config) paraphrazer = get_paraphrazer(base_llm_config) task_creator = get_tasks_creator(base_llm_config) # Create our group chat groupchat = CustomGroupChat(agents=[user, topic_analyzer, paraphrazer, task_creator]) manager = CustomGroupChatManager(groupchat=groupchat, llm_config=base_llm_config) # Start the chat user.initiate_chat( manager, clear_history=True, message=note, ) # Lets print the count of tasks just for fun chat_messages = user.chat_messages.get(manager) if chat_messages is not None: for message in chat_messages: if message.get("name") == "Task_Creator": taskList = yaml.safe_load(message.get("content")) # type: ignore l = len(taskList.get("tasks")) print(f"Got {l} tasks from Task_Creator.") Vuyelo byi ta languteka hi ndlela leyi: Admin (to chat_manager): Note: Convo with editor: - discuss titles and thumbnails - discuss video editing tips tracker - Zeeshan presents the tracker - what trick helps with what - he decidedls if we can experiment with something new - make sure all all videos since how config management works in k8s are backed u - make list of YouTube thumbnail templates - make list of YouTube idea generation limits -------------------------------------------------------------------------------- Topic_Analyzer (to chat_manager): Here is the list of topics discussed in the note: 1. Titles 2. Thumbnails 3. Video editing tips 4. Config management in Kubernetes (k8s) 5. YouTube thumbnail templates 6. YouTube idea generation limits -------------------------------------------------------------------------------- Paraphrazer (to chat_manager): Here is the rewritten note in markdown format: ## Titles - Discuss titles and thumbnails with the editor ## Video Editing Tips Tracker ### Zeeshan presents the tracker - What trick helps with what - He decides if we can experiment with something new ## Config Management in Kubernetes (k8s) - Make sure all videos since how config management works in k8s are backed up ## YouTube Thumbnail Templates - Make a list of YouTube thumbnail templates ## YouTube Idea Generation Limits - Make a list of YouTube idea generation limits ## Additional Info - Discuss video editing tips tracker with Zeeshan - Present the tracker and decide if we can experiment with something new -------------------------------------------------------------------------------- Task_Creator (to chat_manager): tasks: - title: Discuss Titles and Thumbnails description: >- - Discuss titles and thumbnails with the editor This task involves having a conversation with the editor to discuss the titles and thumbnails for the videos. - title: Discuss Video Editing Tips Tracker description: >- - Zeeshan presents the tracker - Discuss what trick helps with what - Decide if we can experiment with something new This task involves discussing the video editing tips tracker presented by Zeeshan, understanding what tricks help with what, and deciding if it's possible to experiment with something new. - title: Back up All Videos Since How Config Management Works in k8s description: >- - Make sure all videos since how config management works in k8s are backed up This task involves ensuring that all videos related to config management in Kubernetes (k8s) are backed up. - title: Create List of YouTube Thumbnail Templates description: >- - Make list of YouTube thumbnail templates This task involves creating a list of YouTube thumbnail templates. - title: Create List of YouTube Idea Generation Limits description: >- - Make list of YouTube idea generation limits This task involves creating a list of YouTube idea generation limits. -------------------------------------------------------------------------------- Got 5 tasks from Task_Creator. Yup. Mi amukeriwile eka nguva ya AI ku hi nyika va hoomans ntirho wo wu endla! (Xana hinkwaswo swi fambe kwihi? 🤷 ♂️) Mahetelelo Ku aka switirhisiwa leswi fambiwaka hi Generative AI swa tika. Kambe swi nga endliwa hi switirho leswi faneleke. Ku katsakanya: Vayimeri va AI va pfula vuswikoti lebyi byo hlamarisa byo modela swiphiqo leswi rharhanganeke tanihi mabulo. Loko swi endliwa kahle, swi nga pfuna ku endla leswaku switirhisiwa swa hina swa AI swi va ni . leswi tiyimiseleke leswi tshembekaka Switirhisiwa swo fana na swi hi nyika rimba leri nga na swifaniso swo olova swo aka ku aka Vayimeri va AI. AutoGen Tanihi magoza lama landzelaka, u nga kambela switirhisiwa leswi landzelaka ku nghena swinene emisaveni ya vayimeri va AI: GitHub repo ku ringeta hi wexe (Khodi) . Nkongomiso wa magoza hi magoza yo sungula hi AutoGen (Vhidiyo) . Ku tirhisa swivumbeko swa mbulavurisano hi ku tirhisa AutoGen (Docs) .