promptulate
v1.18.4
Anglais 中文
Protule est un cadre de développement d'applications d'agent AI fabriqué par Cogit Lab , qui offre aux développeurs un moyen extrêmement concis et efficace de créer des applications d'agent via un paradigme de développement pythonique. La philosophie centrale de l'interrompue est d'emprunter et d'intégrer la sagesse de la communauté open source, incorporant les moments forts de divers cadres de développement pour réduire la barrière à l'entrée et unifier le consensus parmi les développeurs. Avec Protule, vous pouvez manipuler des composants comme LLM, agent, outil, chiffon, etc., avec le code le plus succinct, car la plupart des tâches peuvent être facilement effectuées avec seulement quelques lignes de code.
pne.chat pour encapsuler toutes les fonctionnalités essentielles. Le diagramme suivant montre l'architecture centrale de promptulate :
Le concept principal de Protule est que nous espérons fournir un moyen simple, pythonique et efficace de créer des applications d'IA, ce qui signifie que vous n'avez pas besoin de passer beaucoup de temps à apprendre le cadre. Nous espérons utiliser pne.chat() pour faire la plupart des œuvres, et vous pouvez facilement créer n'importe quelle application AI avec seulement quelques lignes de code.
Ci-dessous,
pnesignifie Protule, qui est le surnom de protutuler. Lespetereprésentent respectivement le début et la fin de l'invite, etnreprésente 9, ce qui est un raccourci pour les neuf lettres entrepete
Protule intègre les capacités de Litellm, soutenant presque tous les types de grands modèles sur le marché, y compris, mais sans s'y limiter, les modèles suivants:
| Fournisseur | Achèvement | Streaming | Achèvement asynchrone | Streaming asynchrone | Asynchronisation asynchrone | Génération d'images asynchrones |
|---|---|---|---|---|---|---|
| Openai | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| azuré | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| AWS - Sagemaker | ✅ | ✅ | ✅ | ✅ | ✅ | |
| AWS - ombrat | ✅ | ✅ | ✅ | ✅ | ✅ | |
| Google - Vertex_ai [Gemini] | ✅ | ✅ | ✅ | ✅ | ||
| Google - Palm | ✅ | ✅ | ✅ | ✅ | ||
| Google AI Studio - Gemini | ✅ | ✅ | ||||
| Mistral AI API | ✅ | ✅ | ✅ | ✅ | ✅ | |
| Cloudflare AI Workers | ✅ | ✅ | ✅ | ✅ | ||
| adhérer | ✅ | ✅ | ✅ | ✅ | ✅ | |
| anthropique | ✅ | ✅ | ✅ | ✅ | ||
| étreinte | ✅ | ✅ | ✅ | ✅ | ✅ | |
| reproduire | ✅ | ✅ | ✅ | ✅ | ||
| ensemble_ai | ✅ | ✅ | ✅ | ✅ | ||
| ouverte | ✅ | ✅ | ✅ | ✅ | ||
| AI21 | ✅ | ✅ | ✅ | ✅ | ||
| bassier | ✅ | ✅ | ✅ | ✅ | ||
| vllm | ✅ | ✅ | ✅ | ✅ | ||
| nlp_cloud | ✅ | ✅ | ✅ | ✅ | ||
| Aleph Alpha | ✅ | ✅ | ✅ | ✅ | ||
| pétales | ✅ | ✅ | ✅ | ✅ | ||
| ollla | ✅ | ✅ | ✅ | ✅ | ||
| deepinfra | ✅ | ✅ | ✅ | ✅ | ||
| perplexité-ai | ✅ | ✅ | ✅ | ✅ | ||
| GROQ AI | ✅ | ✅ | ✅ | ✅ | ||
| tous les niveaux | ✅ | ✅ | ✅ | ✅ | ||
| Voyage AI | ✅ | |||||
| xinference [inférence Xorbits] | ✅ |
La prise en charge puissante du modèle de PNE vous permet de créer facilement tous les appels de modèle tiers.
Voyons maintenant comment gérer des modèles locaux Llama3 d'Olllama avec PNE.
import promptulate as pne
resp : str = pne . chat ( model = "ollama/llama2" , messages = [{ "content" : "Hello, how are you?" , "role" : "user" }])? 2024.5.14 OpenAI a lancé son nouveau modèle "OMNI", offrant une vitesse et une tarification améliorés par rapport à Turbo.
Vous pouvez en utiliser les capacités multimodales disponibles dans l'une de vos applications invite!
import promptulate as pne
messages = [
{
"role" : "user" ,
"content" : [
{ "type" : "text" , "text" : "What's in this image?" },
{
"type" : "image_url" ,
"image_url" : "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" ,
},
],
}
]
resp = pne . chat ( model = "gpt-4o" , messages = messages )
print ( resp ) Utilisez provider/model_name pour appeler le modèle, et vous pouvez facilement créer tous les appels de modèle tiers.
Pour plus de modèles, veuillez visiter la documentation Litellm.
Vous pouvez également voir comment utiliser pne.chat() dans la documentation de démarrage / officielle.
Créer un chatbot rationalisé par PNE
Construire Gradio Chatbot par PNE
Créer une application mathématique avec l'agent
GROQ, LLAMA3, rational pour créer une application
Construisez la carte des connaissances avec Streamlit et PNE
Créez un chatbot à l'aide de PNE + Streamlit pour discuter avec GitHub Repo
Créez une application mathématique avec Agent [Steamlit, Toolagent, Hooks].
Un cadre d'agent de robot mulitmodal de ROS2 et produir [agent]
Utilisez Streamlit et PNE pour comparer différents modèles un terrain de jeu. [Rational]
GCOP: Votre copilote Git AI, basé sur Protule
pip install -U pneRemarque: Votre version Python doit être de 3,8 ou plus.
Même si PNE fournit de nombreux modules, dans 90% des scénarios de développement d'applications LLM, vous n'avez qu'à utiliser la fonction pne.chat (), vous n'avez donc qu'à commencer par le chat pour comprendre l'utilisation de PNE, et lorsque vous devez utiliser des modules supplémentaires, vous pouvez en savoir plus sur les fonctionnalités et l'utilisation d'autres modules.
Vous pouvez utiliser pne.chat() pour discuter comme Openai. Document API de chat Openai: https://platform.openai.com/docs/api-reference/chat
import promptulate as pne
messages = [
{ "role" : "system" , "content" : "You are a helpful assistant." },
{ "role" : "user" , "content" : "Who are you?" },
]
response : str = pne . chat ( messages = messages , model = "gpt-4-turbo" )
print ( response ) De nombreuses bibliothèques tierces peuvent utiliser Openai SDK appelle leurs modèles, tels que Deepseek. Dans PNE, vous pouvez utiliser directement la fonction pne.chat() pour appeler ces modèles, il n'a pas besoin d'utiliser le SDK OpenAI et fournit des fonctionnalités améliorées pour simplifier la difficulté de développement. Utilisez le préfixe du fournisseur openai/xxx dans le modèle, et vous pouvez utiliser le modèle OpenAI pour passer des appels.
import os
import promptulate as pne
os . environ [ "DEEPSEEK_API_KEY" ] = "your api key"
messages = [
{ "role" : "system" , "content" : "You are a helpful assistant." },
{ "role" : "user" , "content" : "How are you?" },
]
response = pne . chat (
messages = messages ,
model = "openai/deepseek-chat" ,
)
print ( response )Le formatage de sortie robuste est une base fondamentale pour le développement d'applications LLM. Nous espérons que les LLM peuvent renvoyer des données stables. Avec PNE, vous pouvez facilement effectuer une sortie formatée. Dans l'exemple suivant, nous utilisons Basemodel de Pydontic pour encapsuler une structure de données qui doit être retournée.
from typing import List
import promptulate as pne
from pydantic import BaseModel , Field
class LLMResponse ( BaseModel ):
provinces : List [ str ] = Field ( description = "List of provinces' names" )
resp : LLMResponse = pne . chat ( "Please tell me all provinces in China." , output_schema = LLMResponse )
print ( resp )Sortir:
provinces=['Anhui', 'Fujian', 'Gansu', 'Guangdong', 'Guizhou', 'Hainan', 'Hebei', 'Heilongjiang', 'Henan', 'Hubei', 'Hunan', 'Jiangsu', 'Jiangxi', 'Jilin', 'Liaoning', 'Qinghai', 'Shaanxi', 'Shandong', 'Shanxi', 'Sichuan', 'Yunnan', 'Zhejiang', 'Taiwan', 'Guangxi', 'Nei Mongol', 'Ningxia', 'Xinjiang', 'Xizang', 'Beijing', 'Chongqing', 'Shanghai', 'Tianjin', 'Hong Kong', 'Macao']
De plus, influencé par le papier plan-et-résolution, PNE permet également aux développeurs de construire des agents capables de faire face à des problèmes complexes par la planification, le raisonnement et l'action. Les capacités de planification de l'agent peuvent être activées à l'aide du paramètre enable_plan .
Dans cet exemple, nous utilisons Tavily comme moteur de recherche, qui est un outil puissant pour rechercher des informations sur le Web. Pour utiliser Tavily, vous devez obtenir une clé API de Tavily.
import os
os . environ [ "TAVILY_API_KEY" ] = "your_tavily_api_key"
os . environ [ "OPENAI_API_KEY" ] = "your_openai_api_key"Dans ce cas, nous utilisons l'outil TavilySearchResults enveloppé par Langchain.
from langchain_community . tools . tavily_search import TavilySearchResults
tools = [ TavilySearchResults ( max_results = 5 )] import promptulate as pne
pne . chat ( "what is the hometown of the 2024 Australia open winner?" , model = "gpt-4-1106-preview" , enable_plan = True )Sortir:
[Agent] Assistant Agent start...
[User instruction] what is the hometown of the 2024 Australia open winner?
[Plan] {"goals": ["Find the hometown of the 2024 Australian Open winner"], "tasks": [{"task_id": 1, "description": "Identify the winner of the 2024 Australian Open."}, {"task_id": 2, "description": "Research the identified winner to find their place of birth or hometown."}, {"task_id": 3, "description": "Record the hometown of the 2024 Australian Open winner."}], "next_task_id": 1}
[Agent] Tool Agent start...
[User instruction] Identify the winner of the 2024 Australian Open.
[Thought] Since the current date is March 26, 2024, and the Australian Open typically takes place in January, the event has likely concluded for the year. To identify the winner, I should use the Tavily search tool to find the most recent information on the 2024 Australian Open winner.
[Action] tavily_search_results_json args: {'query': '2024 Australian Open winner'}
[Observation] [{'url': 'https://ausopen.com/articles/news/sinner-winner-italian-takes-first-major-ao-2024', 'content': 'The agile right-hander, who had claimed victory from a two-set deficit only once previously in his young career, is the second Italian man to achieve singles glory at a major, following Adriano Panatta in1976.With victories over Andrey Rublev, 10-time AO champion Novak Djokovic, and Medvedev, the Italian is the youngest player to defeat top 5 opponents in the final three matches of a major since Michael Stich did it at Wimbledon in 1991 – just weeks before Sinner was born.n He saved the only break he faced with an ace down the tee, and helped by scoreboard pressure, broke Medvedev by slamming a huge forehand to force an error from his more experienced rival, sealing the fourth set to take the final to a decider.n Sensing a shift in momentum as Medvedev served to close out the second at 5-3, Sinner set the RLA crowd alight with a pair of brilliant passing shots en route to creating a break point opportunity, which Medvedev snuffed out with trademark patience, drawing a forehand error from his opponent. “We are trying to get better every day, even during the tournament we try to get stronger, trying to understand every situation a little bit better, and I’m so glad to have you there supporting me, understanding me, which sometimes it’s not easy because I am a little bit young sometimes,” he said with a smile.n Medvedev, who held to love in his first three service games of the second set, piled pressure on the Italian, forcing the right-hander to produce his best tennis to save four break points in a nearly 12-minute second game.n'}, {'url': 'https://www.cbssports.com/tennis/news/australian-open-2024-jannik-sinner-claims-first-grand-slam-title-in-epic-comeback-win-over-daniil-medvedev/', 'content': '"nOur Latest Tennis StoriesnSinner makes epic comeback to win Australian OpennSinner, Sabalenka win Australian Open singles titlesn2024 Australian Open odds, Sinner vs. Medvedev picksnSabalenka defeats Zheng to win 2024 Australian Openn2024 Australian Open odds, Sabalenka vs. Zheng picksn2024 Australian Open odds, Medvedev vs. Zverev picksnAustralian Open odds: Djokovic vs. Sinner picks, betsnAustralian Open odds: Gauff vs. Sabalenka picks, betsnAustralian Open odds: Zheng vs. Yastremska picks, betsnNick Kyrgios reveals he's contemplating retirementn© 2004-2024 CBS Interactive. Jannik Sinner claims first Grand Slam title in epic comeback win over Daniil MedvedevnSinner, 22, rallied back from a two-set deficit to become the third ever Italian Grand Slam men's singles championnAfter almost four hours, Jannik Sinner climbed back from a two-set deficit to win his first ever Grand Slam title with an epic 3-6, 3-6, 6-4, 6-4, 6-3 comeback victory against Daniil Medvedev. Sinner became the first Italian man to win the Australian Open since 1976, and just the eighth man to successfully come back from two sets down in a major final.n He did not drop a single set until his meeting with Djokovic, and that win in itself was an accomplishment as Djokovic was riding a 33-match winning streak at the Australian Open and had never lost a semifinal in Melbourne.n @janniksin • @wwos • @espn • @eurosport • @wowowtennis pic.twitter.com/DTCIqWoUoRn"We are trying to get better everyday, and even during the tournament, trying to get stronger and understand the situation a little bit better," Sinner said.'}, {'url': 'https://www.bbc.com/sport/tennis/68120937', 'content': 'Live scores, results and order of playnAlerts: Get tennis news sent to your phonenRelated TopicsnTop StoriesnFA Cup: Blackburn Rovers v Wrexham - live text commentarynRussian skater Valieva given four-year ban for dopingnLinks to Barcelona are 'totally untrue' - ArtetanElsewhere on the BBCnThe truth behind the fake grooming scandalnFeaturing unseen police footage and interviews with the officers at the heart of the casenDid their father and uncle kill Nazi war criminals?n A real-life murder mystery following three brothers in their quest for the truthnWhat was it like to travel on the fastest plane?nTake a behind-the-scenes look at the supersonic story of the ConcordenToxic love, ruthless ambition and shocking betrayalnTell Me Lies follows a passionate college relationship with unimaginable consequences...n "nMarathon man Medvedev runs out of steamnMedvedev is the first player to lose two Grand Slam finals after winning the opening two setsnSo many players with the experience of a Grand Slam final have talked about how different the occasion can be, particularly if it is the first time, and potentially overwhelming.n Jannik Sinner beats Daniil Medvedev in Melbourne finalnJannik Sinner is the youngest player to win the Australian Open men's title since Novak Djokovic in 2008nJannik Sinner landed the Grand Slam title he has long promised with an extraordinary fightback to beat Daniil Medvedev in the Australian Open final.n "nSinner starts 2024 in inspired formnSinner won the first Australian Open men's final since 2005 which did not feature Roger Federer, Rafael Nadal or Novak DjokovicnSinner was brought to the forefront of conversation when discussing Grand Slam champions in 2024 following a stunning end to last season.n'}]
[Execute Result] {'thought': "The search results have provided consistent information about the winner of the 2024 Australian Open. Jannik Sinner is mentioned as the winner in multiple sources, which confirms the answer to the user's question.", 'action_name': 'finish', 'action_parameters': {'content': 'Jannik Sinner won the 2024 Australian Open.'}}
[Execute] Execute End.
[Revised Plan] {"goals": ["Find the hometown of the 2024 Australian Open winner"], "tasks": [{"task_id": 2, "description": "Research Jannik Sinner to find his place of birth or hometown."}, {"task_id": 3, "description": "Record the hometown of Jannik Sinner, the 2024 Australian Open winner."}], "next_task_id": 2}
[Agent] Tool Agent start...
[User instruction] Research Jannik Sinner to find his place of birth or hometown.
[Thought] To find Jannik Sinner's place of birth or hometown, I should use the search tool to find the most recent and accurate information.
[Action] tavily_search_results_json args: {'query': 'Jannik Sinner place of birth hometown'}
[Observation] [{'url': 'https://www.sportskeeda.com/tennis/jannik-sinner-nationality', 'content': "During the semifinal of the Cup, Sinner faced Djokovic for the third time in a row and became the first player to defeat him in a singles match. Jannik Sinner NationalitynJannik Sinner is an Italian national and was born in Innichen, a town located in the mainly German-speaking area of South Tyrol in northern Italy. A. Jannik Sinner won his maiden Masters 1000 title at the 2023 Canadian Open defeating Alex de Minaur in the straight sets of the final.n Apart from his glorious triumph at Melbourne Park in 2024, Jannik Sinner's best Grand Slam performance came at the 2023 Wimbledon, where he reached the semifinals. In 2020, Sinner became the youngest player since Novak Djokovic in 2006 to reach the quarter-finals of the French Open."}, {'url': 'https://en.wikipedia.org/wiki/Jannik_Sinner', 'content': "At the 2023 Australian Open, Sinner lost in the 4th round to eventual runner-up Stefanos Tsitsipas in 5 sets.[87]nSinner then won his seventh title at the Open Sud de France in Montpellier, becoming the first player to win a tour-level title in the season without having dropped a single set and the first since countryman Lorenzo Musetti won the title in Naples in October 2022.[88]nAt the ABN AMRO Open he defeated top seed and world No. 3 Stefanos Tsitsipas taking his revenge for the Australian Open loss, for his biggest win ever.[89] At the Cincinnati Masters, he lost in the third round to Félix Auger-Aliassime after being up a set, a break, and 2 match points.[76]nSeeded 11th at the US Open, he reached the fourth round after defeating Brandon Nakashima in four sets.[77] Next, he defeated Ilya Ivashka in a five set match lasting close to four hours to reach the quarterfinals for the first time at this Major.[78] At five hours and 26 minutes, it was the longest match of Sinner's career up until this point and the fifth-longest in the tournament history[100] as well as the second longest of the season after Andy Murray against Thanasi Kokkinakis at the Australian Open.[101]nHe reached back to back quarterfinals in Wimbledon after defeating Juan Manuel Cerundolo, Diego Schwartzman, Quentin Halys and Daniel Elahi Galan.[102] He then reached his first Major semifinal after defeating Roman Safiullin, before losing to Novak Djokovic in straight sets.[103] In the following round in the semifinals, he lost in straight sets to career rival and top seed Carlos Alcaraz who returned to world No. 1 following the tournament.[92] In Miami, he reached the quarterfinals of this tournament for a third straight year after defeating Grigor Dimitrov and Andrey Rublev, thus returning to the top 10 in the rankings at world No. In the final, he came from a two-set deficit to beat Daniil Medvedev to become the first Italian player, male or female, to win the Australian Open singles title, and the third man to win a Major (the second of which is in the Open Era), the first in 48 years.[8][122]"}, {'url': 'https://www.thesportreview.com/biography/jannik-sinner/', 'content': '• Date of birth: 16 August 2001n• Age: 22 years oldn• Place of birth: San Candido, Italyn• Nationality: Italiann• Height: 188cm / 6ft 2insn• Weight: 76kg / 167lbsn• Plays: Right-handedn• Turned Pro: 2018n• Career Prize Money: US$ 4,896,338n• Instagram: @janniksinnThe impressive 22-year-old turned professional back in 2018 and soon made an impact on the tour, breaking into the top 100 in the world rankings for the first time in 2019.n Jannik Sinner (Photo: Dubai Duty Free Tennis Championships)nSinner ended the season as number 78 in the world, becoming the youngest player since Rafael Nadal in 2003 to end the year in the top 80.n The Italian then ended the 2019 season in style, qualifying for the 2019 Next Gen ATP Finals and going on to win the tournament with a win over Alex de Minaur in the final.n Sinner then reached the main draw of a grand slam for the first time at the 2019 US Open, when he came through qualifying to reach the first round, where he lost to Stan Wawrinka.n Asked to acknowledge some of the key figures in his development, Sinner replied: “I think first of all, my family who always helped me and gave me the confidence to actually change my life when I was 13-and-a-half, 14 years old.n'}]
[Execute Result] {'thought': 'The search results have provided two different places of birth for Jannik Sinner: Innichen and San Candido. These are actually the same place, as San Candido is the Italian name and Innichen is the German name for the town. Since the user asked for the place of birth or hometown, I can now provide this information.', 'action_name': 'finish', 'action_parameters': {'content': 'Jannik Sinner was born in San Candido (Italian) / Innichen (German), Italy.'}}
[Execute] Execute End.
[Revised Plan] {"goals": ["Find the hometown of the 2024 Australian Open winner"], "tasks": [], "next_task_id": null}
[Agent Result] Jannik Sinner was born in San Candido (Italian) / Innichen (German), Italy.
[Agent] Agent End.
Dans le scénario du développement des agents, nous devons souvent diviser de nombreuses composantes atomiques des agents pour obtenir une meilleure personnalisation. L'EPN fournit des composants d'agent atomisées, comme le planificateur. L'exemple suivant montre l'utilisation d'un composant de planificateur distinct pour la planification des tâches.
import promptulate as pne
model = pne . LLMFactory . build ( "gpt-4-turbo" )
planner = pne . Planner ( model , system_prompt = "You are a planner" )
plans = planner . run ( "Plan a trip to Paris" )
print ( plans )Sortir:
('goals', ['Plan a trip to Paris'])
('tasks', [Task(task_id=1, description='Check passport validity', status=<TaskStatus.TODO: 'todo'>), Task(task_id=2, description='Determine travel dates', status=<TaskStatus.TODO: 'todo'>), Task(task_id=3, description='Research and book flights', status=<TaskStatus.TODO: 'todo'>), Task(task_id=4, description='Book accommodations', status=<TaskStatus.TODO: 'todo'>), Task(task_id=5, description='Plan itinerary for the trip', status=<TaskStatus.TODO: 'todo'>), Task(task_id=6, description='Investigate and purchase travel insurance', status=<TaskStatus.TODO: 'todo'>), Task(task_id=7, description='Set a budget for the trip', status=<TaskStatus.TODO: 'todo'>), Task(task_id=8, description='Pack luggage', status=<TaskStatus.TODO: 'todo'>), Task(task_id=9, description='Notify bank of international travel', status=<TaskStatus.TODO: 'todo'>), Task(task_id=10, description='Check weather forecast and pack accordingly', status=<TaskStatus.TODO: 'todo'>)])
('next_task_id', 1)
Pour des informations plus détaillées, veuillez consulter la mise en place / documentation officielle.
Les principes de conception du cadre PNE comprennent la modularité, l'extensibilité, l'interopérabilité, la robustesse, la maintenabilité, la sécurité, l'efficacité et la convivialité.
Suivant ces principes et appliquant les dernières technologies d'intelligence artificielle, pne vise à fournir un cadre puissant et flexible pour la création d'agents automatisés.
Pour plus d'informations, veuillez contacter: [email protected]
Voir quoi que ce soit Changelog, décrivez le canal télégramme
Nous apprécions votre intérêt à contribuer à notre initiative open source. Nous avons fourni un guide d'un développeur décrivant les étapes pour contribuer à produir. Veuillez vous référer à ce guide pour assurer une collaboration en douceur et des contributions réussies. De plus, vous pouvez voir le plan de développement actuel pour voir les dernières progrès de développement?
