Kola

kola

Building Better React & Next.js Apps: Mistakes, Tips, and Best Practices

Physical Properties of KIC 9851944: Conclusion, Data Availability, Acknowledgments, and References

This paper is available on arxiv under CC BY-SA 4.0 DEED license. Authors: (1) Tomáš Jakl, Czech Academy of Sciences and Czech Technical University; (2) Dan Marsden, School of Computer Science University of Nottingham; (3) Nihil Shah, Department of Computer Science University of Oxford. Table of Links Abstract & Introduction Prelimenaries FVM Theorems for Positive Existential Fragments FVM Theorems for Counting Logic FVM Theorems for The Full Logic Abstract FVM Theorems for Products Adding Equality and Other Enrichment Conclusions, Acknowledgments & References Appendix A FVM theorems for coproducts Appendix B Proofs Omitted from Section III Appendix C Proofs Omitted from Section IV Appendix D Proofs Omitted from Section V Appendix E Proofs Omitted from Section VI Appendix F Proofs Omitted from Section VII VIII. CONCLUSION We presented a categorical approach to the composition method, and specifically Feferman–Vaught–Mostowski theorems. We exploit game comonads to encapsulate the logics and their model comparison games. Surprising connections to classical constructions in category theory, and especially the monad theory of bilinear maps emerged from this approach, cf. Section V-A. For finite model theorists, our work provides a novel highlevel account of many FVM theorems, abstracting away from individual logics and constructions. Furthermore, concrete instances of these theorems are verified purely semantically, by finding a suitable collection homomorphisms forming a Kleisli law satisfying (S2’), instead of the usual delicate verification that strategies of model comparison games compose. For game comonads, we provide a much needed tool that enables us to handle logical relationships between structures as they are transformed or viewed in terms of different logics. The FVM results in this paper, combined with judicious use of the techniques described in Section VII can be pushed significantly further. FVM theorems and the compositional method are of particular significance in the setting of monadic second-order (MSO) logic [49]. Exploiting the results we have presented for the composition method, a follow up paper will give a comonadic semantics for MSO, and develop a semantic account of Courcelle’s algorithmic meta-theorems [5]. The original theorem of Feferman–Vaught [3] is very flexible, including incorporating structure on the indices of families of models to be combined by an operation, as well as the models themselves. This aspect is currently outside the scope of our comonadic methods. An ad-hoc adaptation of our approach also gives a proof of the FVM theorem for free amalgamations, but this does not follow directly from our theorems. Developing these extensions is left to future work. The present work bears some resemblance to Turi and Plotkin’s bialgebraic semantics [50], a categorical model of structural operational semantics (SOS) [51]. Turi and Plotkin noticed that the SOS rules assigning behaviour to syntax could be abstracted as a certain distributive law λ. An algebra encodes the composition operations of the syntax, and a coalgebra the behaviour. If this pair is suitably compatible with λ, forming a so-called λ-bialgebra, then crucially bisimulation is a congruence with respect to the composition operations. Both bialgebraic semantics and our work presented in this paper give a categorical account of well-behaved composition operations, with the interaction between composition and observable behaviour mediated by some form of distributive law. There are also essential differences: bialgebraic semantics typically focuses on assigning behaviour to syntax, whereas FVM theorems encompass operations on models. Our FVM theorems are parametric in a choice of logic or observable behaviour, while the notion of bisimulation in bialgebraic semantics is fixed by the coalgebra signature functor. The natural presence of positive existential and counting quantifier variants of FVM theorems, and the incorporation of resource parameters, do not seem to have a direct analogue in bialgebraic semantics. The similarities are intriguing, and exploring the relationship between bialgebraic semantics and our approach to FVM theorems is left to future work. We would like to thank Clemens Berger for suggesting the connection with parametric adjoints and Nathanael Arkor for his suggestions on terminology. We are also grateful to the members of the EPSRC project “Resources and co-resources” for their feedback. Acknowledgements: REFERENCES [1] L. Libkin, Elements of finite model theory. Springer, 2004, vol. 41. [2] A. Mostowski, “On direct products of theories,” The Journal of Symbolic Logic, vol. 17, no. 1, pp. 1–31, 1952. [3] S. Feferman and R. L. Vaught, “The first-order properties of algebraic systems,” Fundamenta Mathematicae, vol. 47, 1959. [4] J. A. Makowsky, “Algorithmic uses of the Feferman–Vaught theorem,” Annals of Pure and Applied Logic, vol. 126, no. 1-3, pp. 159–213, 2004. [5] B. Courcelle and J. Engelfriet, Graph structure and monadic secondorder logic: a language-theoretic approach. Cambridge University Press, 2012, vol. 138. [6] A. Ehrenfeucht, “An application of games to the completeness problem for formalized theories,” Fundamenta mathematicae, vol. 49, no. 129- 141, p. 13, 1960. [7] R. Fraïssé, “Sur quelques classifications des relations, basées sur des isomorphismes restreints,” Publications Scientifiques de l’Université d’Alger. Série A (mathématiques), vol. 2, pp. 273–295, 1955. [8] P. G. Kolaitis and M. Y. Vardi, “Infinitary logics and 0–1 laws,” Information and computation, vol. 98, no. 2, pp. 258–294, 1992. [9] M. Hennessy and R. Milner, “On observing nondeterminism and concurrency,” in International Colloquium on Automata, Languages, and Programming. Springer, 1980, pp. 299–309. [10] S. Abramsky, A. Dawar, and P. Wang, “The pebbling comonad in finite model theory,” in 32nd Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2017, Reykjavik, Iceland, June 20-23, 2017. IEEE Computer Society, 2017, pp. 1–12. [11] S. Abramsky and N. Shah, “Relating structure and power: Comonadic semantics for computational resources,” Journal of Logic and Computation, vol. 31, no. 6, pp. 1390–1428, 2021. [12] E. Moggi, “Computational lambda-calculus and monads,” in Proceedings of the Fourth Annual Symposium on Logic in Computer Science (LICS ’89), Pacific Grove, California, USA, June 5-8, 1989. IEEE Computer Society, 1989, pp. 14–23. [13] ——, “Notions of computation and monads,” Information and Computation, vol. 93, no. 1, pp. 55–92, 1991. [14] E. G. Manes, Algebraic theories. Springer Science, 1976, vol. 26. [15] S. Abramsky and D. Marsden, “Comonadic semantics for guarded fragments,” in 36th Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2021, Rome, Italy, June 29 - July 2, 2021. IEEE, 2021, pp. 1–13. [16] A. Ó. Conghaile and A. Dawar, “Game comonads & generalised quantifiers,” in 29th EACSL Annual Conference on Computer Science Logic, CSL 2021, January 25-28, 2021, Ljubljana, Slovenia (Virtual Conference), ser. LIPIcs, C. Baier and J. Goubault-Larrecq, Eds., vol. 183. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2021, pp. 16:1–16:17. [17] Y. Montacute and N. Shah, “The pebble-relation comonad in finite model theory,” in LICS ’22: 37th Annual ACM/IEEE Symposium on Logic in Computer Science, Haifa, Israel, August 2 - 5, 2022, C. Baier and D. Fisman, Eds. ACM, 2022, pp. 13:1–13:11. [Online]. Available: https://doi.org/10.1145/3531130.3533335 [18] T. Paine, “A pebbling comonad for finite rank and variable logic, and an application to the equirank-variable homomorphism preservation theorem,” in Proceedings of the 36th Conference on the Mathematical Foundations of Programming Semantics, MFPS 2020, Online, October 1, 2020, ser. Electronic Notes in Theoretical Computer Science, P. Johann, Ed., vol. 352. Elsevier, 2020, pp. 191–209. [19] A. Dawar, T. Jakl, and L. Reggio, “Lovász-type theorems and game comonads,” in 36th Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2021, Rome, Italy, June 29 - July 2, 2021. IEEE, 2021, pp. 1–13. [20] S. Abramsky and D. Marsden, “Comonadic semantics for hybrid logic,” in 47th International Symposium on Mathematical Foundations of Computer Science, MFCS 2022, August 22-26, 2022, Vienna, Austria, ser. LIPIcs, S. Szeider, R. Ganian, and A. Silva, Eds., vol. 241. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2022, pp. 7:1–7:14. [21] L. Reggio, “Polyadic sets and homomorphism counting,” Advances in Mathematics, vol. 410, p. 108712, 2022. [22] S. Abramsky, “Structure and power: an emerging landscape,” Fundam. Informaticae, vol. 186, no. 1-4, pp. 1–26, 2022. [23] S. Abramsky and L. Reggio, “Arboreal categories and resources,” in 48th International Colloquium on Automata, Languages, and Programming, ICALP 2021, July 12-16, 2021, Glasgow, Scotland (Virtual Conference), ser. LIPIcs, N. Bansal, E. Merelli, and J. Worrell, Eds., vol. 198. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2021, pp. 115:1–115:20. [24] H. Ebbinghaus and J. Flum, Finite model theory, ser. Perspectives in Mathematical Logic. Springer, 1995. [25] E. G. Manes and P. Mulry, “Monad compositions I: general constructions and recursive distributive laws,” Theory and Applications of Categories, vol. 18, no. 7, pp. 172–208, 2007. [26] A. Kock, “Bilinearity and cartesian closed monads,” Mathematica Scandinavica, vol. 29, no. 2, pp. 161–174, 1971. [27] T. Jakl, D. Marsden, and N. Shah, “Generalizations of bilinear maps,” 2022, technical report, arXiv preprint. [Online]. Available: https://arxiv.org/abs/2205.05382 [28] A. Dawar, S. Severini, and O. Zapata, “Pebble games and cospectral graphs,” Electronic Notes in Discrete Mathematics, vol. 61, pp. 323– 329, 2017. [29] S. Abramsky and N. Tzevelekos, “Introduction to categories and categorical logic,” in New structures for physics. Springer, 2010, pp. 3–94. [30] S. Awodey, Category theory. Oxford University Press, 2010. [31] C. Stirling, Modal and temporal properties of processes. Springer Science & Business Media, 2001. [32] A. W. Roscoe, Understanding concurrent systems. Springer Science & Business Media, 2010. [33] H. Kleisli, “Every standard construction is induced by a pair of adjoint functors,” Proceedings of the American Mathematical Society, vol. 16, no. 3, pp. 544–546, 1965. [34] B. Jacobs, “Semantics of weakening and contraction,” Annals of Pure and Applied Logic, vol. 69, no. 1, pp. 73–106, 1994. [35] S. Abramsky, T. Jakl, and T. Paine, “Discrete density comonads and graph parameters,” in Coalgebraic Methods in Computer Science - 16th IFIP WG 1.3 International Workshop, CMCS 2022, Colocated with ETAPS 2022, Munich, Germany, April 2-3, 2022, Proceedings, ser. Lecture Notes in Computer Science, H. H. Hansen and F. Zanasi, Eds., vol. 13225. Springer, 2022, pp. 23–44. [Online]. Available: https://doi.org/10.1007/978-3-031-10736-8_2 [36] P. T. Johnstone, “Adjoint lifting theorems for categories of algebras,” Bulletin of the London Mathematical Society, vol. 7, no. 3, pp. 294– 297, 1975. [37] A. Kock, “Closed categories generated by commutative monads,” Journal of the Australian Mathematical Society, vol. 12, no. 4, pp. 405–424, 1971. [38] G. Seal, “Tensors, monads and actions,” Theory and Applications of Categories, vol. 28, no. 15, pp. 403–434, 2013. [39] F. E. Linton, “Coequalizers in categories of algebras,” in Seminar on triples and categorical homology theory. Springer, 1969, pp. 75–90. [40] R. Street, “The petit topos of globular sets,” Journal of Pure and Applied Algebra, vol. 154, no. 1-3, pp. 299–315, 2000. [41] M. Weber, “Generic morphisms, parametric representations and weakly cartesian monads,” Theory and Applications of Categories, vol. 13, no. 14, pp. 191–234, 2004. [42] ——, “Familial 2-functors and parametric right adjoints,” Theory and Applications of Categories, vol. 18, no. 22, pp. 665–732, 2007. [43] C. Berger, P.-A. Mellies, and M. Weber, “Monads with arities and their associated theories,” Journal of Pure and Applied Algebra, vol. 216, no. 8-9, pp. 2029–2048, 2012. [44] T. Altenkirch, J. Chapman, and T. Uustalu, “Monads need not be endofunctors,” in International Conference on Foundations of Software Science and Computational Structures. Springer, 2010, pp. 297–311. [45] P. J. Freyd and G. M. Kelly, “Categories of continuous functors, I,” Journal of Pure and Applied Algebra, vol. 2, no. 3, pp. 169–191, 1972. [46] B. Bednarczyk and M. Urbanczyk, “Comonadic semantics for description logics games,” in Proceedings of the 35th International Workshop on Description Logics (DL 2022) co-located with Federated Logic Conference (FLoC 2022), Haifa, Israel, August 7th to 10th, 2022, ser. CEUR Workshop Proceedings, O. Arieli, M. Homola, J. C. Jung, and M. Mugnier, Eds., vol. 3263. CEUR-WS.org, 2022. [Online]. Available: http://ceur-ws.org/Vol-3263/paper-5.pdf [47] M. Bojanczyk, “Separator logic and star-free expressions ´ for graphs,” 2021, arXiv preprint. [Online]. Available: https://arxiv.org/abs/2107.13953 [48] N. Schirrmacher, S. Siebertz, and A. Vigny, “First-Order Logic with Connectivity Operators,” in 30th EACSL Annual Conference on Computer Science Logic (CSL 2022), ser. Leibniz International Proceedings in Informatics (LIPIcs), F. Manea and A. Simpson, Eds., vol. 216. Dagstuhl, Germany: Schloss Dagstuhl – LeibnizZentrum für Informatik, 2022, pp. 34:1–34:17. [Online]. Available: https://drops.dagstuhl.de/opus/volltexte/2022/15754 [49] Y. Gurevich, “Monadic second-order theories,” in Model-theoretic logics, J. Barwise and S. Feferman, Eds. Cambridge University Press, 1985, pp. 479–506. [50] D. Turi and G. Plotkin, “Towards a mathematical operational semantics,” in Proceedings of Twelfth Annual IEEE Symposium on Logic in Computer Science. IEEE, 1997, pp. 280–291. [51] G.D.Plotkin, “A structural approach to operational semantics,” Aarhus University, Tech. Rep. DAIMI FN-19, 1981. [52] J. Adámek, J. Adamek, J. Rosicky et al., Locally presentable and accessible categories. Cambridge University Press, 1994, vol. 189.

A Categorical Account of
Composition Methods in Logic: Conclusions, Acknowledgments & References

Back in 2020, 's brand was worth a whopping , while PepsiCo's brand was valued at $70.9 billion. The time-honored competition between Pepsi and Coca-Cola is legendary in marketing, still influencing the drink market, global marketing, peoples’ choice of product, and brand loyalty. For over a century, this battle has evolved from a taste test to today’s online advertisement. This article delves into the creativity and strategies Pepsi and Coca-Cola implore to win customers worldwide; in this article, we will examine their battles, advertisement strategies, and how they adjust to changing customer tastes to keep their storied rivalry living. Coca-Cola $84.86 billion Background In , Coca-Cola first came to life. It all began when Dr. John S. Pemberton, a pharmacist, created a soft drink that had a unique taste meant to be sold at soda fountains. Frank Robinson his bookkeeper named the drink “Coca-Cola” and also crafted the logo in his handwriting; Coca-Cola was publicized as a stress-relieving drink. 1886, in Atlanta, Georgia On the other hand, in , Pepsi originally called “Brad’s Drink” was created by Caleb Bradham a pharmacist from New Bern, North Carolina. Brad’s Drink was later renamed Pepsi-cola in 1893, this change of name was inspired by the digestive aid; pepsin, and kola nuts which were used in the recipe. Pepsi was promoted as a tasty and healthy digestion-aiding beverage. 1893 \When Coca-Cola started its marketing journey, emphasis was laid on how refreshing and satisfactory it was. The brand was ahead of the game as it was the first to use branded merchandise, by distributing items like calendars and clocks with their logos on it to promote their brand. In 1916 Coca-Cola decided to switch up its marketing tactics with the introduction of the popular bottle shape; this made it different, and more recognizable in different places. In 1927 they created the largest soda fountain in the world. At first, Pepsi started by promoting its health benefits, strategically placing itself as a digestive aid. During the great depression that occurred in the 1930s, Pepsi became popular for selling double the amount of soda for the same price as Coca-Cola ( that is, 12 ounces of the beverage for the same price as 6 ounces of Coca-Cola) this became their unique selling point.             Pepsi came up with another approach in the 1960s which was the “Pepsi Generation” campaign,  they tried connecting with younger people; this act was the starting point of the famous Cola wars with Coca-Cola. Key Marketing Battles In the famous taste battle between Pepsi and Coke, the numbers show who's winning. In 2020, Coke had a big chunk of the market, with . This tells us a lot about what people like and how loyal they are to these brands. 43.7%, while Pepsi had 24.1% The Cola Wars represents one of the most notable marketing showdowns in marketing history, embodied by the Pepsi generation campaign. It all began in the year 1975 when Pepsi organized a blind taste test to see which product people liked better, Pepsi or Coca-Cola. This made Pepsi very famous, Coca-Cola could not just watch but felt the need to do something. In 1985, Coca-Cola responded by changing its recipe to “ ”, this move had no positive outcome; eventually they brought back their original recipe and called it “Coca-Cola Classic”. It was a valuable learning experience for both companies. New Coke Right from time, backing up a product with a famous person has always been a powerful marketing tool, companies believe that having a celebrity support a particular product will make people have more interest in it. Pepsi and Coca-Cola have thoroughly utilized these tactics, and prominent figures like Michael Jackson and Britney Spears have endorsed Pepsi. On the one hand, Coca-Cola has endorsed icons like Selena Gomez, Marilyn Monroe, and others recently. These endorsements, not only boost the brand’s visibility; it also contribute to shaping its identity by connecting it with the irresistible appeal and charisma of celebrities that support them. Lately, staying healthy has been a priority for a lot of people, companies like Pepsi and Coca-Cola have taken note of this, and they have adapted to this trend by expanding their options, adding healthier choices like juice, water, and drinks that contain fewer calories; their advertisements are also changing emphasizing the nutritional value of these products. This change highlights how important it is for companies to keep the needs of people in mind. Comparative Analysis of Marketing Strategies At first, Marketing was usually all about reaching large groups of people based on age, gender, and income. However, today’s marketing is about targeting specific individuals and customizing messages just for them. Companies now make use of data analytics to figure out people’s interests and behaviors, and then send messages that resonate. Change like this reflects an understanding that in a diverse world, a generic approach will not be effective because people's preferences cannot be the same in a globalized market. Over time, advertising has changed. At the start we used to see ads on traditional platforms like TV and newspapers, now we see them on the internet and social media; every form of advertisement has its benefits. TV ads reach a large group of people while online advertisements reach specific individuals only. Social media has changed marketing a lot, companies can now reach their customers right away and get feedback; the best part is with online advertisement we can measure how well it works through metrics like clicks and shares. With this, companies can identify areas for improvement and adjust their ads to get good results. Brands' messaging and positioning have gone through massive change too, in the past, Brands only emphasized their products’ features and benefits. But now through storytelling, they create an emotional connection with people; they do not want to be just providers of goods and services alone, they want to be like friends who share the same dreams, values, and worries. This is about building strong bonds with people and fostering dedication even in a saturated market. Iconic Campaigns and Their Impact In the 1980s, Pepsi came up with a brilliant idea called the “ ” It was a blind taste test where people did not know which of the sodas they were drinking, Pepsi or Coca-Cola. This was a daring move that boosted Pepsi's sales and positioned it as a confident, unconventional, youth-oriented brand. Another remarkable campaign was “The Choice of a New Generation”, this campaign featured celebrities of that time making Pepsi much cooler for younger people. Pepsi Challenge On the other hand, Coca-Cola has a natural talent for creating campaigns that make us feel warm and connected. Remember the ” ” campaign? Which featured bottles with customized names, it made buying a soda feel so personal and fun. It strengthened  Coca-Cola as a brand that was about bringing people together. Who can forget those Christmas trucks? “ ” ads always marked the start of a festive season, making us feel very excited; Coca-Cola sure knows how to spread happiness and celebration. Share a Coke The holidays are coming The way people see Pepsi and Coca-Cola was influenced by these advertising efforts. Pepsi is known as a brand that is cool and daring, having a desire to challenge existing ways of doing things and exploring new possibilities. Coca-Cola, conversely has positioned itself as a classic symbol that brings people together, making moments happier and more enjoyable. The Role of Innovation in Marketing When a new product is launched it captures people's attention, and brings excitement; using initiative marketing techniques like sneak pics and collaborating with famous people makes the whole experience very exciting. The packaging of a product is not just about aesthetics; it is about making sure they are easy to use, suitable for the environment, and gives a pleasant experience when it is being unboxed.  Coca-Cola bottles with people's names on them or Amazon user-friendly packaging can be taken as an example; it shows how packaging can make a brand look unique and influence consumers' preferences. The way brands connect with people has changed through digital marketing, they now make use of social media platforms, super cool digital encounters, and customized emails making the connection with consumers more personal and fun. Nike uses AR to launch their sneakers, and Spotify makes playlists just for you;  using new technologies to make memorable experiences that people love, makes customers stay loyal to the brand. Global Reach and Localization Strategies Coca-Cola and Pepsi are experts at adjusting their marketing tactics to fit different global markets. They don't just translate words they also change colors, themes, and messaging to match different local cultures. Coca-Cola's “ ” campaign was themed universally around joy and being together; local celebrities were featured and things in cultural reference to different cultures were also used to make the connection feel more personal for the people there. Open Happiness Understanding and respecting cultural differences is crucial. Coca-Cola and Pepsi have learned this aspect; Pepsi's journey to India is a good example, during Pepsi's expansion into India they didn't just advertise their product but also engaged in a big part of the Indian culture which was cricket. This way, they became an integral part of Indian recreation activities. Coca-Cola's strategy in China shows that adapting to local culture can be successful, They incorporated Chinese symbols and partnered with popular artists to be well-known to Chinese people. Conversely, Pepsi had issues with the Philippines because of a branding mistake that did not respect their local custom. This highlights the challenges that follow global marketing. The Current State of Battle Pepsi has relied heavily on entertainment, teaming up with notable stars and important occasions to win young people over. Focusing on digital platforms and social media engagements allowed them to create interactive and viral content that gets people talking and sharing online. On the other hand, Coca-Cola focuses on that give people a feeling of joy, togetherness, and shared experience; their “open happiness” and Share a Coke” can be used as an example, it has been successful in promoting a positive brand image across different regions. emotional branding with campaigns Regardless of the competition, Coca-Cola maintains a lead worldwide because its brand is loved by people wherever you go. However, Pepsi is making major progress in certain markets by offering healthier snacks and drinks people want currently. Both Pepsi and Coca-Cola have dedicated fans though customers are leaning toward healthier, low-sugar, and eco-friendly alternatives. In the future, Pepsi and Coca-Cola are striving to be more than just companies that make drinks. Coca-Cola is working hard to be eco-friendly by reducing its emissions and making its packaging easier to reutilize. Meanwhile, Pepsi is also big on sustainability but is investing in digital technology to make sure customers have a wonderful experience with their brand. Final Thoughts The Pepsi vs. Coca-Cola clashes teach us an invaluable lesson about outperforming in marketing. These brands have been struggling for ages, changing their strategies constantly to stay relevant; from creative ads to digital excitement. They have adjusted to what people care about, their rivalry is not just about the products, it is all about the fluid nature of marketing. Watching them, we learn how brands can continue to develop and connect with customers,  now and in the years to come.

Pepsi vs Coca-Cola: A Marketing Battle for the Ages

Startups of The Year 2023 Winners: North America 

In this blog post, I will share how to use LangChain, a flexible framework for building AI-driven applications, to extract and generate structured JSON data with GPT and Langchain. I'll provide code snippets and concise instructions to help you set up and run the project. You can find the code for this tutorial on GitHub: . link About LangChain LangChain is a framework designed to speed up the development of . It provides a suite of components for crafting prompt templates, connecting to diverse data sources, and interacting seamlessly with various tools. It simplifies prompt engineering, data input and output, and tool interaction so we can focus on core logic. It is available in and JavaScript. AI-driven applications Python LangChain contains tools that make getting structured (as in JSON format) output out of LLMs easy. Let's use them to our advantage. Installing and Setup I am assuming you have one of the latest versions of Python. I've used 3.11. Visit the LangChain website if you need more details. First, create a new project, i.e.: Create a new directory for your project and navigate to it in your terminal. Run pip install langchain openai Create an file. index.py Then, let's configure the API keys. Other dependencies are included. # configure credentials (easiest)
export OPENAI_API_KEY=XXX This is just for demonstrative use. In production, use your secret management way of choice. Let's import the required dependencies on top of our Python file. import os
from langchain.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
from langchain.chat_models import ChatOpenAI

from langchain.output_parsers import PydanticOutputParser
from pydantic import BaseModel, Field
from typing import List Generating data Let's start with generating some fake data to see the possibilities of parsing. Sample use case: JSON output formatting for fake identity generation. Output schema definition First, we need to tell the library what we want to get. LangChain supports defining expected schema using a popular library, Pydantic: # Define a new Pydantic model with field descriptions and tailored for Twitter.
class TwitterUser(BaseModel):
    name: str = Field(description="Full name of the user.")
    handle: str = Field(description="Twitter handle of the user, without the '@'.")
    age: int = Field(description="Age of the user.")
    hobbies: List[str] = Field(description="List of hobbies of the user.")
    email: str = Field(description="Email address of the user.")
    bio: str = Field(description="Bio or short description about the user.")
    location: str = Field(description="Location or region where the user resides.")
    is_blue_badge: bool = Field(
        description="Boolean indicating if the user has a verified blue badge."
    )
    joined: str = Field(description="Date the user joined Twitter.")
    gender: str = Field(description="Gender of the user.")
    appearance: str = Field(description="Physical description of the user.")
    avatar_prompt: str = Field(
        description="Prompt for generating a photorealistic avatar image. The image should capture the essence of the user's appearance description, ideally in a setting that aligns with their interests or bio. Use professional equipment to ensure high quality and fine details."
    )
    banner_prompt: str = Field(
        description="Prompt for generating a banner image. This image should represent the user's hobbies, interests, or the essence of their bio. It should be high-resolution and captivating, suitable for a Twitter profile banner."
    ) Prompt template To use the auto-generated template, we need to create a LangChain construct called PromptTemplate. In this case, we're going to use variation appropriate for a cheap chat model like . It will contain format instructions from the parser: GPT 3.5 # Instantiate the parser with the new model.
parser = PydanticOutputParser(pydantic_object=TwitterUser)

# Update the prompt to match the new query and desired format.
prompt = ChatPromptTemplate(
    messages=[
        HumanMessagePromptTemplate.from_template(
            "answer the users question as best as possible.\n{format_instructions}\n{question}"
        )
    ],
    input_variables=["question"],
    partial_variables={
        "format_instructions": parser.get_format_instructions(),
    },
) Try it out To execute the structured output, call the OpenAI model with the input: chat_model = ChatOpenAI(
    model="gpt-3.5-turbo",
    openai_api_key=os.getenv("OPENAI_API_KEY"),
    max_tokens=1000
)

# Generate the input using the updated prompt.
user_query = (
    "Generate a detailed Twitter profile of a random realistic user with a diverse background, "
    "from any country in the world, original name, including prompts for images. Come up with "
    "real name, never use most popular placeholders like john smith and john doe."
)
_input = prompt.format_prompt(question=user_query)

output = chat_model(_input.to_messages())
parsed = parser.parse(output.content)
print(output.content)
print(parsed) Here's what will be sent to the AI model. This will most likely change in the future LangChain versions. Answer the user query.
The output should be formatted as a JSON instance that conforms to the JSON schema below.

As an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}
the object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.

Here is the output schema:

{"properties": {"name": {"description": "Full name of the user.", "title": "Name", "type": "string"}, "handle": {"description": "Twitter handle of the user, without the '@'.", "title": "Handle", "type": "string"}, "age": {"description": "Age of the user.", "title": "Age", "type": "integer"}, "hobbies": {"description": "List of hobbies of the user.", "items": {"type": "string"}, "title": "Hobbies", "type": "array"}, "email": {"description": "Email address of the user.", "title": "Email", "type": "string"}, "bio": {"description": "Bio or short description about the user.", "title": "Bio", "type": "string"}, "location": {"description": "Location or region where the user resides.", "title": "Location", "type": "string"}, "is_blue_badge": {"description": "Boolean indicating if the user has a verified blue badge.", "title": "Is Blue Badge", "type": "boolean"}, "joined": {"description": "Date the user joined Twitter.", "title": "Joined", "type": "string"}, "gender": {"description": "Gender of the user.", "title": "Gender", "type": "string"}, "appearance": {"description": "Physical description of the user.", "title": "Appearance", "type": "string"}, "avatar_prompt": {"description": "Prompt for generating a photorealistic avatar image. The image should capture the essence of the user's appearance description, ideally in a setting that aligns with their interests or bio. Use professional equipment to ensure high quality and fine details.", "title": "Avatar Prompt", "type": "string"}, "banner_prompt": {"description": "Prompt for generating a banner image. This image should represent the user's hobbies, interests, or the essence of their bio. It should be high-resolution and captivating, suitable for a Twitter profile banner.", "title": "Banner Prompt", "type": "string"}}, "required": ["name", "handle", "age", "hobbies", "email", "bio", "location", "is_blue_badge", "joined", "gender", "appearance", "avatar_prompt", "banner_prompt"]}

Generate a detailed Twitter profile of a random realistic user with a diverse background, from any country in the world, original name, including prompts for images. Come up with real name, never use most popular placeholders like john smith and john doe. The output from the model will look like this: {
    "name": "Daniela Kolarova",
    "handle": "PragueReveries",
    "age": 29,
    "hobbies": ["classical piano", "literature", "yoga"],
    "email": "daniela.kolarova@czmail.cz",
    "bio": "Finding harmony through keys, books, and breaths. Embracing Prague's spellbinding tales.",
    "location": "Prague, Czech Republic",
    "is_blue_badge": True,
    "joined": "2014-05-01",
    "gender": "female",
    "appearance": "Caucasian, long wavy auburn hair, green eyes, 5'6\"",
    "avatar_prompt": "Photorealistic image of a caucasian woman with green eyes, playing a grand piano. Use Olympus PEN-F with a 38mm lens.",
    "banner_prompt": "High-resolution depiction of Prague's rooftops, cozy libraries, and serene yoga studios. Samsung Galaxy S20 II.",
} As you can see, we got just what we needed. We can generate whole identities with complex descriptions matching other parts of the persona. Error handling You may wonder if is safe in any way. using LLM in a production application If, for example, the output was missing a name, we would get this error: Got: 1 validation error for TwitterUser
name
  none is not an allowed value (type=type_error.none.not_allowed) Luckily, LangChain is focused on problems just like this. In case the output needs fixing, use the OutputFixingParser. It will try and fix errors in case your LLM outputs something that does not match your requirements. from langchain.output_parsers import OutputFixingParser
from langchain.schema import OutputParserException

try:
    parsed = parser.parse(output.content)
except OutputParserException as e:
    new_parser = OutputFixingParser.from_llm(
        parser=parser,
        llm=ChatOpenAI()
    )
    parsed = new_parser.parse(output.content) Under the hood, LangChain is calling our LLM again to fix the output. Extracting Data from Files To load and extract data from files using LangChain, you can follow these steps. In this example, we're going to load the PDF file. Conveniently, LangChain has utilities just for this purpose. We need one extra dependency. pip install pypdf We're going to load a short bio of Elon Musk and extract the information we've previously generated. Download the PDF file here: . google drive from langchain.document_loaders import PyPDFLoader

loader = PyPDFLoader("elon.pdf")
document = loader.load() We need to modify the prompt template to indicate extraction, not generation. document_query = "Create a profile based on this description: " + document[0].page_content

_input = prompt.format_prompt(question=document_query)
output = chat_model(_input.to_messages())
parsed = parser.parse(output.content)

print(parsed) Thanks to these modifications, we get the following output: {
  "name": "Elon Musk",
  "handle": "elonmusk",
  "age": 51,
  "hobbies": ["space exploration", "electric vehicles", "artificial intelligence", "sustainable energy", "tunnel construction", "neural interfaces", "Mars colonization", "hyperloop transportation"],
  "email": "elonmusk@gmail.com",
  "bio": "Entrepreneur, inventor, and CEO. Revolutionizing transportation and energy.",
  "location": "Pretoria, South Africa",
  "is_blue_badge": false,
  "joined": "2008-06-02",
  "gender": "male",
  "appearance": "normal build, short-cropped hair, trimmed beard",
  "avatar_prompt": "Generate a photorealistic avatar image capturing Elon Musk's appearance. The image should align with his interests and bio.",
  "banner_prompt": "Generate a high-resolution banner image representing Elon Musk's various fields of interest."
} By following these steps, we've extracted structured JSON data from a PDF file! This approach is versatile and can be adapted to suit your specific use case. Conclusion In conclusion, by leveraging , we can reduce the complexity of our LLM apps and introduce useful error handling. LangChain, GPTs, and Python You can find the code for this tutorial on GitHub: . link Subscribe to my profile by filling in your email address on the left, and be up-to-date with my articles! Don't forget to follow me on Twitter @ and subscribe to my blog for more tips and insights! horosin_ newsletter If you don't have Twitter, you can also follow me on . LinkedIn Also published . here

Unlocking Structured JSON Data with LangChain and GPT: A Step-by-Step Tutorial

A wide array of useful digital tools is available without cost, for anyone. Passionate developers and volunteers make this possible in the environment of open-source software, but there’s not much they gain in exchange for it. These projects are often struggling to find funding to keep afloat, and that’s where the Kivach platform in Obyte may help. is a pioneering open-source cascading donations platform designed to empower individuals and organizations to fundraise for various causes efficiently and transparently. It operates on the principle of "cascading donations," Kivach where donations received on GitHub can be distributed across multiple projects or recipients. This is because those recipients can donate a part or a total of the coins to any other open-source project(s) they want on GitHub, automatically. So, the donations can flow as a cascade across multiple repositories and collaborators. Kivach offers a user-friendly interface, allowing users to allocate funds in cryptocurrencies to specific initiatives, fostering a community-driven approach to philanthropy. All that the contributors need is an Obyte wallet, some crypto funds, and the name of the GitHub repository. Let’s explore some of them to donate! GIMP (GNU Image Manipulation Program) GIMP (from General Image Manipulation Program) was released in 1998 by Spencer Kimball and Peter Mattis. , rivaling commercial software like Adobe Photoshop. Its capabilities include image retouching, photo enhancement, and even support for advanced techniques like layers, masks, and filters. It’s a robust open-source software used for graphic design and image editing This tool supports various file formats, including PSD, and offers extensive customization options with a plethora of plugins and extensions. It's a favorite among graphic designers, photographers, illustrators, and hobbyists alike, offering professional-grade tools for free. Currently, it’s mainly maintained by the developers “Jehan” and Øyvind Kolås. Jehan is the main developer, and he’s creating (and raising funds for) an animation movie named , along with the artist Aryeom. ZeMarmot Of course, they to keep working on the project. They appear as . Remember that it’s important to tell them about the donation, though, so they can claim it with their own —a pre-existing one or a new one. accept donations To avoid Patreon fees, you can donate through Kivach with cryptocurrencies. Gnome/Gimp Obyte wallet Blender (3D Modeling) This is a versatile and open-source 3D computer graphics software used for a wide range of applications, including 3D modeling, animation, rendering, compositing, and more. Released initially in January 1994 as an in-house application by the Dutch animation studio NeoGeo, Blender became open-source in 2002, allowing users worldwide to contribute to its development. Blender's development is led by the Blender Foundation, a non-profit organization that oversees the project's direction and ensures its commitment to open-source principles. It has a global community of developers, artists, and enthusiasts who continually refine and enhance the software. Blender has gained immense popularity for its professional-grade features, i ncluding support for character animation, physics simulations, and a powerful node-based compositor. To support Blender financially, users can support the , where donations can be made to directly fund the software's development. Contributions are used to pay developers, support infrastructure, and ensure Blender's continued growth and improvement. They accept Bitcoin (BTC), Bitcoin Cash (BCH), Ethereum (ETH), and Litecoin (LTC). In Kivach, they’re available as . Blender Development Fund blender/blender Kdenlive (Video Editor) This is an open-source video editing software that offers a comprehensive and user-friendly platform for video editing and post-production. It was first released in 2002 by Jason Wood and has since evolved into Kdenlive is known for its intuitive interface and robust feature set, including support for multiple video and audio tracks, transitions, effects, and a wide range of video formats. a powerful video editing tool for Linux and other Unix-like operating systems. Its development is driven by a community of passionate contributors and developers who work collaboratively to enhance its functionality and performance. The project is part of the larger KDE Community, which promotes several open-source software projects, including . the image editor Krita To support Kdenlive financially and contribute to its ongoing development, users have the option to make donations through . Typically, Kdenlive accepts donations in traditional money, but its repository is available on Kivach too as . This way, you can use some of your crypto to support them. \ various channels KDE/Kdenlive Xfce (Desktop Environment) Xfce is a lightweight and open-source desktop environment designed for Unix-like operating systems, known for its efficiency and speed. It was initially released in 1996 by Olivier Fourdan and has since evolved into a mature and user-friendly desktop environment. Xfce provides users with a simple yet customizable interface, making it a popular choice for users who prefer a responsive and resource-efficient desktop environment. Xfce's development is primarily driven by a community of dedicated contributors and developers who work collaboratively to maintain and enhance the software. The Xfce project is known for its commitment to providing a stable and user-focused desktop experience while using fewer system resources compared to more resource-intensive desktop environments. To support the development of Xfce and help its ongoing improvement, users can make donations to the project. and ensuring that Xfce continues to provide a lightweight and efficient desktop environment for users who value performance and customization. Donors can send them funds via Open Collective, which a 15% fee for fiscal hosts. These contributions are essential for covering development costs, infrastructure maintenance, may take Of course, it’s also possible to send them crypto funds via Kivach, without high fees. They appear as . xfce-mirror/xfce4-terminal Tor (Privacy Browser) Well, if you don’t know this one, you likely have been living under a rock. First things first: It’s free and open-source software that enhances online privacy and security by routing internet traffic through a global network of volunteer-operated servers. It was initially developed in the mid-2000s by the United States Naval Research Laboratory and has since evolved into a global community-driven project. no, Tor (short for The Onion Router), isn’t solely to access the Darknet. The Tor network conceals a user's IP address, making it challenging for anyone to trace their online activities, providing anonymity and bypassing online censorship. , a non-profit organization (NGO), leads the development and maintenance of the Tor software and network. The Tor Project To support Tor financially and contribute to its mission of providing online privacy tools for everyone, individuals can make donations to the Tor Project. Their website provides various options for donating, including one-time and recurring donations, as well as options for corporate or institutional support. They accept Bitcoin, Bitcoin Cash, Dash, Dogecoin, Ether, Litecoin, Monero, Stellar, and Zcash. In Kivach, you can find them as . Besides, in case you don’t know, You can activate its use to obscure your transactions just by adjusting the proper switch in the section “Settings (Global Preferences)”. torproject/tor the Obyte wallet is integrated with this privacy browser to protect your personal data. Now, you can explore Kivach and GitHub yourself to support more essential open-source projects. Your cryptocurrency contributions can fuel innovation and ensure these tools remain accessible to all. Do you know any other interesting open-source projects that may need help? Please comment on them below, on our , or via , so we can cover them in future articles for potential donors to know! Telegram channel Discord Featured Vector Image by . Freepik

5 Open-source Projects You Can Support With Kivach — and Cryptocurrencies

5 proyectos de código abierto que puedes respaldar con Kivach y criptomonedas

5 projets open source que vous pouvez soutenir avec Kivach – et les crypto-monnaies

5 ओपन-सोर्स प्रोजेक्ट जिन्हें आप किवाच और क्रिप्टोकरेंसी के साथ समर्थन कर सकते हैं

Kivach と暗号通貨でサポートできる 5 つのオープンソース プロジェクト

5 projetos de código aberto que você pode apoiar com Kivach – e criptomoedas

5 dự án nguồn mở bạn có thể hỗ trợ với Kivach — và tiền điện tử

您可以使用 Kivach 和加密货币支持的 5 个开源项目

Fine-tuning is now available for one of the key models offered by OpenAI. Up to this point, we were only able to fine-tune older model variants with performance subpar to . Maximizing the performance of OpenAI's models without draining your budget is now achievable. the likes of GPT-3.5 and GPT-4 Why fine-tune? Better responses Training with more examples than in few-shot-learning approaches (giving a few examples in the prompt) Shorter prompts - lower costs and latency OpenAI also lists the following benefits: improved steerability, reliable output formatting, and custom tone. You can find all of the code from this article on GitHub: . The code is experimental and several-use-only; don't expect it to be polished. link Please remember that for JSON output, it may be better to use function-calling functionality. That said, this tutorial should show you how to fine-tune in general. Sample use case: JSON output formatting for fake identity generation Using large language models for tasks like JSON output formatting often results in lengthy and costly prompts. Let's explore this challenge with a sample use case. I am a big fan of using large language models (LLMs) like GPT-4 for language processing. Many people use the popular library Langchain for this use case ( ), while others use native function calling features ( ). Both of these use additional tokens and are error-prone. and I wrote about it I made a short demo Let's look at a particular example. Let's assume we often need to generate people's identities in structured formats to seed our demo databases, populate dashboards at development stages, etc. Let's take the Twitter/X user profile and try to generate its parts. {
    "name": "John Doe",
    "handle": "jdoe",
    "age": 30,
    "hobbies": ["programming", "gaming", "reading"],
    "email": "john.doe@gmail.com",
    "bio": "Avid Python programmer and gamer",
    "location": "USA",
    "is_blue_badge": True,
    "joined": "2019-01-01",
    "gender": "male",
    "appearance": "white, brown hair, brown eyes, 6'0",
    "avatar_prompt": "A photorealistic image of a man, white, brown hair, brown eyes, against a blurred backdrop od a home scenery. Use a Hasselblad camera with a 85mm lens at F 1.2 aperture setting and soft sunlight falling on the subject to capture the subject’s creativity.",
    "banner_prompt": "High resolution photo of a desk with a laptop, a gamepad and a book. Canon DSLR."
} The prompt to achieve that with a high degree of success is very long, especially using Langchain templates. Have a look: That is 923 tokens for the input, and the output takes 236. Generating a thousand would cost us $41.85 with GPT-4. With GPT 3.5, we could do it for $1.85. If the promise of fine-tuning can be met and we get performance closer to GPT-4 with shorter prompts, we will save tons of money. Most of the use cases require more data. What we can try to do is to reduce the prompt by fine-tuning to the following: As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt. Generate details of a random Twitter profile. With this prompt and fine-tuned model, we would pay $4.388. 10x less than GPT-4 but almost 3x GPT-3.5. The fine-running costs in this tutorial amount to around $0.4. Let's see how this works out. I have no automatic way of comparing the quality of the generated results, but if you know of any research, please let everyone know in the comments. The code to generate this prompt can be found in the project repository. Preparing the synthetic training data Make sure you have the latest version of the by running . OpenAI package pip install -U -r requirements.txt You also need to include your OpenAPI key in the environment variable. . export OPENAI_API_KEY="sk-XXXXX" Let's use GPT-4 to prepare 50 examples as per minimum OpenAI requirements. It will cost us around $2.4. We're leveraging the power of GPT-4 for high-quality examples to train our model. import openai
import json

prompt = "COMPLICATED LONG PROMPT"

SAMPLE_COUNT = 50

examples = []

for i in range(SAMPLE_COUNT):
    chat_completion = openai.ChatCompletion.create(
        model="gpt-4", messages=[{"role": "user", "content": prompt}]
    )
    print(chat_completion.choices[0].message.content)
    examples.append(json.loads(chat_completion.choices[0].message.content))

with open("training_examples.json", "w") as outfile:
    outfile.write(json.dumps(examples)) Now, armed with 50 strong examples from GPT-4, we can fine-tune our 3.5 model. Data formatting OpenAI suggests using the system message for the input data. It uses a system prompt as a recommended way of passing general instructions. Let's construct our template message. {
    "messages": [
        {
            "role": "system",
            "content": "As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt."
        },
        {
            "role": "user",
            "content": "Generate details of a random Twitter profile."
        },
        {
            "role": "assistant",
            "content": f"{profile_details}"
} We also need to prepare a file with each JSON object in a new line and run it through a . validator provided by OpenAI transform_data.py import json

# Load the data from the json file
with open('training_examples.json', 'r') as f:
    profiles = json.load(f)

# Output file to save the formatted messages
with open('mydata.jsonl', 'w') as out_file:
    for profile in profiles:
        profile_details = json.dumps(profile)

        # Create the desired format
        formatted_message = {
            "messages": [
                {
                    "role": "system",
                    "content": "As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt."
                },
                {
                    "role": "user",
                    "content": "Generate details of a random Twitter profile."
                },
                {
                    "role": "assistant",
                    "content": profile_details
                }
            ]
        }

        # Write the formatted message to the output file, each on a new line
        out_file.write(json.dumps(formatted_message) + "\n") Now, let's run the formatting script (in the repository called . openai_formatting.py python openai_formatting.py You should get the following message. 0 examples may be over the 4096 token limit, they will be truncated during fine-tuning
Dataset has ~14194 tokens that will be charged for during training
By default, you'll train for 3 epochs on this dataset
By default, you'll be charged for ~42582 tokens
See pricing page to estimate total costs In our case, fine-tuning will cost $0.34. Fine-tuning the model I have compiled all the necessary calls into one file. The script uploads the file with our data, waits for it to process, and then starts the finetuning process. Be careful; running it will incur costs! finetune.py import os
import openai
import time

openai.api_key = os.getenv("OPENAI_API_KEY")

file_upload = openai.File.create(file=open("mydata.jsonl", "rb"), purpose="fine-tune")
print("Uploaded file id", file_upload.id)

while True:
    print("Waiting for file to process...")
    file_handle = openai.File.retrieve(id=file_upload.id)
    if len(file_handle) and file_handle.status == "processed":
        print("File processed")
        break
    time.sleep(3)


job = openai.FineTuningJob.create(training_file=file_upload.id, model="gpt-3.5-turbo")

while True:
    print("Waiting for fine-tuning to complete...")
    job_handle = openai.FineTuningJob.retrieve(id=job.id)
    if job_handle.status == "succeeded":
        print("Fine-tuning complete")
        print("Fine-tuned model info", job_handle)
        print("Model id", job_handle.fine_tuned_model)
        break
    time.sleep(3) Run it by typing . python finetune.py If you don't want to wait, stop the script and wait to receive an email from OpenAI. Both the message in the terminal and the email will include the model ID! Now, let's test it! Testing the model Let's prepare the test file. Replace model_id with yours. run_model.py import os
import openai

openai.api_key = os.getenv("OPENAI_API_KEY")

model_id = "ft:gpt-3.5-turbo:my-org:custom_suffix:id"

completion = openai.ChatCompletion.create(
    model=model_id,
    messages=[
        {
            "role": "system",
            "content": "As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt.",
        },
        {"role": "user", "content": "Generate details of a random Twitter profile."},
    ],
)

print(completion.choices[0].message) python run_model.py And we should receive an output similar to this! {
    "name": "Daniela Kolarova",
    "handle": "PragueReveries",
    "age": 29,
    "hobbies": ["classical piano", "literature", "yoga"],
    "email": "daniela.kolarova@czmail.cz",
    "bio": "Finding harmony through keys, books, and breaths. Embracing Prague's spellbinding tales.",
    "location": "Prague, Czech Republic",
    "is_blue_badge": True,
    "joined": "2014-05-01",
    "gender": "female",
    "appearance": "Caucasian, long wavy auburn hair, green eyes, 5'6\"",
    "avatar_prompt": "Photorealistic image of a caucasian woman with green eyes, playing a grand piano. Use Olympus PEN-F with a 38mm lens.",
    "banner_prompt": "High-resolution depiction of Prague's rooftops, cozy libraries, and serene yoga studios. Samsung Galaxy S20 II.",
} As you can see, we've achieved our goal of generating high-quality data fitting complex instructions with shorter prompts. We didn't measure the quality, so make sure in your use case, this makes sense and is cost-effective. Conclusion Fine-tuning has opened up an avenue to achieve more specific and consistent outputs from OpenAI's models. As demonstrated with the Twitter profile generation example, fine-tuning meets the promise of achieving specific outputs with short prompts. While fine-tuning offers precision, it demands carefully crafted training data to ensure the model doesn't just memorize examples. This process involves initial investments in terms of time and money (luckily, we can generate fine-tuning data with more capable models). Moreover, the quality of outputs should be continuously assessed to ensure they meet the required standards. For businesses or projects that rely heavily on the performance of LLMs like GPT-4, fine-tuning presents a viable option to optimize performance and cost. As with any technology, it's crucial to stay updated with the best practices and latest developments in the field. OpenAI continues to evolve its offering, and adopting a flexible approach ensures that you can leverage the best capabilities of these models for your specific needs. You can find the code for this tutorial on GitHub: . link Subscribe to my profile by filling in your email address on the left, and be up-to-date with my articles! Don't forget to follow me on Twitter @ and subscribe to my blog for more tips and insights! horosin_ newsletter If you don't have Twitter, you can also follow me on . LinkedIn Also published . here

Fine-Tuning GPT-3.5: A Practical Python Example

To keep everyone safe and healthy, the decision to start working from home came to our management team within minutes. I remember the day SupportYourApp decided to switch to the WFH mode. The Covid-19 pandemic was starting to pick up steam, and businesses around the globe were going remote by the dozen every day. Since then, SupportYourApp grew from 500 people to 1200+ professionals who work from all around the world. Fully working from one office is not an option for all members of our team. Yet, global businesses have started a battle to return their employees to their offices. — the company’s CEO said he expected to see all 60 thousand Goldman Sachs' employees back at the office. “I do think for a business like ours which is an innovative, collaborative apprenticeship culture, (remote working) is not ideal for us, and it’s not a new normal,”. So far, only 10 thousand people have returned to their desks. Goldman Sachs — Netflix’s CEO says working remotely is not good for collaboration and is, in his opinion, a ‘pure negative’. Netflix — for almost a year, Google has been trying to incentivize its workers to . The employees were promised free food and other perks that would make office hours even more comfortable . When this motivation failed, the company’s Chief People Officer, Fiona Cicconi, said non-appearance in the office for three days a week will influence their performance review. Google come back to the office than they already were — Salesforce decided to go the other way and said the company would donate $10 to charity per each day an employee will show up to the office between June 12 and June 23. Salesforce What is businesses’ pro-office motivation? Productivity It is widely thought that a team member who works from home spends most of their time not working, watching Netflix, walking around, and only pretending to be productive. This issue can be resolved simply — make sure every team member sends their manager a productivity report at the end of every day, and start utilizing collaboration and progress tools like Asana or Trello. In general, the notion that people are less productive when they work from home is incorrect, as of workers say they are more productive when working remotely. 30% also report doing more work in less time, and 24% say they do more work in the same amount of time. 77% Control As leaders and managers, we want to make sure we can control and monitor the way our teams perform. We want to know what stage every project is on at almost any given moment, and we want to be sure everyone is doing what they are supposed to. We have to remember — micromanagement is not a good approach to management, especially with a growing team. For any C-suite leader, it is better to delegate some leadership tasks to other management members and focus on strategic goals and tasks. Can control really ensure a superb team performance? Not really. Through my tenure as a CEO, I tried several approaches to team management. At the beginning, I tried to be a friend to everyone on my team. That didn’t work, and I soon adopted a dictatorial style — I wanted to know everything that was happening at SupportYourApp, and I was trying to be strict with everyone. Did my team’s productivity improve? It was already good, and I cannot say that anyone’s strict control would make any difference, no matter whether my team works in our offices or remotely. Collaboration & Communication How can a leader ensure collaboration? There are several steps to doing that: Handpick every member of the team to ensure everyone is a perfect fit. Adopt collaboration software like Trello, Microsoft Teams, Slack, Kolab, and so on. Ensure regular communication both inside and outside the office. Encourage brainstorming sessions to make sure everyone’s free to share their ideas. As a manager, trust your team and listen to their ideas — this will not only ensure collaboration, but will actually vitalize creativity. Can an office encourage collaboration? When you have a question, it is easier to just turn your head and ask a teammate for help. But let’s be honest — businesses around the world have been in a remote mode for more than 3 years. We have online communication and collaboration all set up. It is especially true for international teams that cannot gather in one space on a regular basis, or even ever. Pro-office motivation: does it work? Measures taken by Google, Salesforce, Netflix, and many other companies show — most teams are not keen to come back to their offices even for a hybrid schedule. They want to have the possibility to choose where to work and when to come back and work with their teams face-to-face. With that said, will the office culture survive in the post-pandemic world? It will. The office will evolve and become a hub where colleagues can meet, work on projects that require top security measures, and feel their teams having their backs. The main task for a leader is to find a proper approach and proper encouragement. So, as always in the modern world, everything is about balance.

Pro-Office Motivation: Does it Actually Work?

প্রো-অফিস প্রেরণা: এটি আসলে কাজ করে?

Pro-Office-Motivation: Funktioniert das tatsächlich?

Motivación a favor de la oficina: ¿realmente funciona?

Motivation Pro-Office : ça marche vraiment ?

प्रो-ऑफिस प्रेरणा: क्या यह वास्तव में काम करता है?

プロオフィスのモチベーション: それは実際に機能しますか?

Stories, News & Mentions about KOLA

Kola’s Stories on HackerNoon