diff --git a/pages/applications/pal.en.mdx b/pages/applications/pal.en.mdx index 260add7..2a891ec 100644 --- a/pages/applications/pal.en.mdx +++ b/pages/applications/pal.en.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # The answer formatted with %m/%d/%Y is today.strftime('%m/%d/%Y') # Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY? -# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/1/2002. +# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/12/2002. today = datetime(2002, 3, 12) # 24 hours later, later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -This will output the following: `02/27/1998` \ No newline at end of file +This will output the following: `02/27/1998` diff --git a/pages/applications/pal.es.mdx b/pages/applications/pal.es.mdx index dbba436..2121cc0 100644 --- a/pages/applications/pal.es.mdx +++ b/pages/applications/pal.es.mdx @@ -76,7 +76,7 @@ later = today + relativedelta(hours=24) # The answer formatted with %m/%d/%Y is today.strftime('%m/%d/%Y') # Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY? -# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/1/2002. +# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/12/2002. today = datetime(2002, 3, 12) # 24 hours later, later = today + relativedelta(hours=24) diff --git a/pages/applications/pal.fi.mdx b/pages/applications/pal.fi.mdx index 414fdb4..b89c2a0 100644 --- a/pages/applications/pal.fi.mdx +++ b/pages/applications/pal.fi.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # The answer formatted with %m/%d/%Y is today.strftime('%m/%d/%Y') # Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY? -# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/1/2002. +# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/12/2002. today = datetime(2002, 3, 12) # 24 hours later, later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -Lopputuloksena: `02/27/1998` \ No newline at end of file +Lopputuloksena: `02/27/1998` diff --git a/pages/applications/pal.fr.mdx b/pages/applications/pal.fr.mdx index 7c31baf..38e6db9 100644 --- a/pages/applications/pal.fr.mdx +++ b/pages/applications/pal.fr.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # La réponse formatée avec %m/%d/%Y est today.strftime('%m/%d/%Y') # Q: Jane pensait qu'aujourd'hui est le 11/03/2002, mais aujourd'hui est en fait le 12 mars, soit 1 jour plus tard. Quelle est la date 24 heures plus tard en MM/JJ/AAAA ? -# Si Jane pense qu'aujourd'hui est le 11/03/2002, mais qu'aujourd'hui est en fait le 12 mars, alors aujourd'hui est le 01/03/2002. +# Si Jane pense qu'aujourd'hui est le 11/03/2002, mais qu'aujourd'hui est en fait le 12 mars, alors aujourd'hui est le 12/03/2002. today = datetime(2002, 3, 12) # 24 heures plus tard, later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -Cela affichera ce qui suit : `27/02/1998` \ No newline at end of file +Cela affichera ce qui suit : `27/02/1998` diff --git a/pages/applications/pal.it.mdx b/pages/applications/pal.it.mdx index 0b6c7d6..aa09bf3 100644 --- a/pages/applications/pal.it.mdx +++ b/pages/applications/pal.it.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # La risposta formattata come %m/%d/%Y è today.strftime('%m/%d/%Y') # D: Jane pensava che oggi fosse il 3/11/2002, ma in realtà è il 12 marzo, cioè un giorno dopo. Qual è la data di 24 ore dopo in MM/DD/YYYY? -# Se Jane pensava che oggi fosse il 3/11/2002, ma in realtà è il 12 marzo, allora oggi è il 3/1/2002. +# Se Jane pensava che oggi fosse il 3/11/2002, ma in realtà è il 12 marzo, allora oggi è il 3/12/2002. today = datetime(2002, 3, 12) # 24 hours later, later = today + relativedelta(hours=24) diff --git a/pages/applications/pal.jp.mdx b/pages/applications/pal.jp.mdx index 201776e..67c461f 100644 --- a/pages/applications/pal.jp.mdx +++ b/pages/applications/pal.jp.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # %m/%d/%Yでフォーマットされた答えは today.strftime('%m/%d/%Y') # Q: Janeは今日が2002年3月11日だと思っていましたが、実際は3月12日であり、1日後です。24時間後の日付は何ですか?MM/DD/YYYYで答えてください。 -# Janeは今日が2002年3月11日だと思っていましたが、実際は3月12日である場合、今日は2002年3月1日です。 +# Janeは今日が2002年3月11日だと思っていましたが、実際は3月12日である場合、今日は2002年3月12日です。 today = datetime(2002, 3, 12) # 24時間後、 later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -これにより、`02/27/1998`が出力されます。 \ No newline at end of file +これにより、`02/27/1998`が出力されます。 diff --git a/pages/applications/pal.kr.mdx b/pages/applications/pal.kr.mdx index dabc4a3..df2e68f 100644 --- a/pages/applications/pal.kr.mdx +++ b/pages/applications/pal.kr.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # %m/%d/%Y의 형식으로 반환된 답은 today.strftime('%m/%d/%Y') # Q: Jane은 오늘이 2002년 3월 11일이라고 생각했지만 실제로는 3월 12일이고 하루 뒤야. 24시간 후의 날짜를 MM/DD/YYYY 형식으로 반환해줘. -# 제인은 오늘 날짜를 3/11/2002 라고 생각했고, 사실 오늘은 3월 12일이면 오늘 날짜는 3/1/2002 입니다. +# 제인은 오늘 날짜를 3/11/2002 라고 생각했고, 사실 오늘은 3월 12일이면 오늘 날짜는 3/12/2002 입니다. today = datetime(2002, 3, 12) # 24시간 후, later = today + relativedelta(hours=24) diff --git a/pages/applications/pal.pt.mdx b/pages/applications/pal.pt.mdx index 023ac50..04ba618 100644 --- a/pages/applications/pal.pt.mdx +++ b/pages/applications/pal.pt.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # A resposta formatada com %m/%d/%Y é today.strftime('%m/%d/%Y') # Q: Jane pensou que hoje é 11/03/2002, mas hoje é 12 de março, que é 1 dia depois. Qual é a data 24 horas depois em MM/DD/AAAA? -# Se Jane pensou que hoje é 11/03/2002, mas hoje é 12 de março, então hoje é 01/03/2002. +# Se Jane pensou que hoje é 11/03/2002, mas hoje é 12 de março, então hoje é 12/03/2002. today = datetime(2002, 3, 12) # 24 horas depois, later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -Isso produzirá o seguinte: `02/27/1998` \ No newline at end of file +Isso produzirá o seguinte: `02/27/1998` diff --git a/pages/applications/pal.ru.mdx b/pages/applications/pal.ru.mdx index a0ef797..bec1498 100644 --- a/pages/applications/pal.ru.mdx +++ b/pages/applications/pal.ru.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # The answer formatted with %m/%d/%Y is today.strftime('%m/%d/%Y') # Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY? -# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/1/2002. +# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/12/2002. today = datetime(2002, 3, 12) # 24 hours later, later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -Это выведет следующее: `02/27/1998` \ No newline at end of file +Это выведет следующее: `02/27/1998` diff --git a/pages/applications/pal.tr.mdx b/pages/applications/pal.tr.mdx index 5646d02..f4c8320 100644 --- a/pages/applications/pal.tr.mdx +++ b/pages/applications/pal.tr.mdx @@ -76,7 +76,7 @@ later = today + relativedelta(hours=24) # %m/%d/%Y ile biçimlendirilen yanıt: today.strftime('%m/%d/%Y') # S: Jane bugünün 11/3/2002 olduğunu düşündü, ama aslında bugün 12 Mart yani 1 gün sonra. AA/GG/YYYY cinsinden 24 saat sonraki tarih nedir? -# Jane bugünün 11/3/2002 olduğunu düşündüyse ama aslında bugün 12 Mart ise, o zaman bugün 1/3/2002'dir. +# Jane bugünün 11/3/2002 olduğunu düşündüyse ama aslında bugün 12 Mart ise, o zaman bugün 12/3/2002'dir. today = datetime(2002, 3, 12) # 24 saat sonra, later = today + relativedelta(hours=24) @@ -103,4 +103,4 @@ exec(llm_out) print(born) ``` -Aşağıdaki çıktıyı verecektir: `27/02/1998` \ No newline at end of file +Aşağıdaki çıktıyı verecektir: `27/02/1998` diff --git a/pages/applications/pal.zh.mdx b/pages/applications/pal.zh.mdx index 157e679..c56cd4e 100644 --- a/pages/applications/pal.zh.mdx +++ b/pages/applications/pal.zh.mdx @@ -75,7 +75,7 @@ later = today + relativedelta(hours=24) # The answer formatted with %m/%d/%Y is today.strftime('%m/%d/%Y') # Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY? -# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/1/2002. +# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/12/2002. today = datetime(2002, 3, 12) # 24 hours later, later = today + relativedelta(hours=24) @@ -102,4 +102,4 @@ exec(llm_out) print(born) ``` -这将输出以下内容:`02/27/1998` \ No newline at end of file +这将输出以下内容:`02/27/1998` diff --git a/pages/models/chatgpt.es.mdx b/pages/models/chatgpt.es.mdx index b00e642..1482221 100644 --- a/pages/models/chatgpt.es.mdx +++ b/pages/models/chatgpt.es.mdx @@ -90,7 +90,7 @@ import openai openai.ChatCompletion.create( model="gpt-3.5-turbo", messages=[ - {"role": "system", "content": "res un asistente de investigación de IA. Utilizas un tono técnico y científico."}, + {"role": "system", "content": "Eres un asistente de investigación de IA. Utilizas un tono técnico y científico."}, {"role": "user", "content": "Hola, ¿quién eres?"}, {"role": "assistant", "content": "¡Saludos! Soy un asistente de investigación de IA. ¿En qué puedo ayudarte hoy?"}, {"role": "user", "content": "¿Puedes contarme sobre la creación de los agujeros negros?"} diff --git a/pages/techniques/fewshot.jp.mdx b/pages/techniques/fewshot.jp.mdx index 24993cd..180a6a4 100644 --- a/pages/techniques/fewshot.jp.mdx +++ b/pages/techniques/fewshot.jp.mdx @@ -28,8 +28,8 @@ *プロンプト:* ``` -これは素晴らしい! // ポジティブ -これは酷い! // ネガティブ +これは素晴らしい! // ネガティブ +これは酷い! // ポジティブ あの映画は最高だった! // ポジティブ なんてひどい番組なんだ! // ``` diff --git a/pages/techniques/rag.it.mdx b/pages/techniques/rag.it.mdx index 8994330..eceeb92 100644 --- a/pages/techniques/rag.it.mdx +++ b/pages/techniques/rag.it.mdx @@ -1,3 +1,25 @@ # Retrieval Augmented Generation (RAG) -This page needs a translation! Feel free to contribute a translation by clicking the `Edit this page` button on the right side. \ No newline at end of file +import {Screenshot} from 'components/screenshot' +import RAG from '../../img/rag.png' + +I modelli di linguaggio di uso generale possono essere perfezionati per svolgere diversi compiti comuni come l'analisi del sentimento e il riconoscimento delle entità nominate. Questi compiti generalmente non richiedono ulteriori conoscenze di base. + +Per compiti più complessi e che richiedono molte conoscenze, è possibile costruire un sistema basato su un modello di linguaggio che accede a fonti di conoscenza esterne per completare i compiti. Questo consente una maggiore coerenza dei fatti, migliora l'affidabilità delle risposte generate e aiuta a mitigare il problema dell'"allucinazione". + +I ricercatori di Meta AI hanno introdotto un metodo chiamato [Generazione aumentata dal recupero (RAG)](https://ai.facebook.com/blog/retrieval-augmented-generation-streamlining-the-creation-of-intelligent-natural-language-processing-models/) per affrontare tali compiti che richiedono molte conoscenze. RAG combina un componente di recupero delle informazioni con un modello generatore di testo. RAG può essere perfezionato e la sua conoscenza interna può essere modificata in modo efficiente e senza la necessità di riaddestrare l'intero modello. + +RAG prende un input e recupera un insieme di documenti rilevanti/supportativi dati una fonte (ad esempio, Wikipedia). I documenti vengono concatenati come contesto con il prompt di input originale e inviati al generatore di testo che produce l'output finale. Questo rende RAG adattivo per situazioni in cui i fatti potrebbero evolvere nel tempo. Questo è molto utile poiché la conoscenza parametrica dei LLM è statica. RAG consente ai modelli di linguaggio di bypassare la ri-formazione, consentendo l'accesso alle informazioni più recenti per generare output affidabili attraverso la generazione basata sul recupero. + +Lewis et al., (2021) hanno proposto una ricetta generale per il perfezionamento di RAG. Un modello seq2seq pre-addestrato viene utilizzato come memoria parametrica e un indice vettoriale denso di Wikipedia viene utilizzato come memoria non parametrica (accessibile tramite un recupero pre-addestrato neurale). Di seguito è riportata una panoramica di come funziona l'approccio: + + +Fonte dell'immagine: [Lewis et al. (2021)](https://arxiv.org/pdf/2005.11401.pdf) + +RAG si comporta in modo forte su diversi benchmark come [Natural Questions](https://ai.google.com/research/NaturalQuestions), [WebQuestions](https://paperswithcode.com/dataset/webquestions), e CuratedTrec. RAG genera risposte che sono più fattuali, specifiche e diverse quando testate su domande MS-MARCO e Jeopardy. RAG migliora anche i risultati sulla verifica dei fatti FEVER. + +Questo mostra il potenziale di RAG come opzione valida per migliorare gli output dei modelli di linguaggio nei compiti che richiedono molte conoscenze. + +Più recentemente, questi approcci basati su recupero sono diventati più popolari e sono combinati con LLM popolari come ChatGPT per migliorare le capacità e la coerenza fattuale. + +Puoi trovare un [esempio semplice di come usare i recuperatori e i LLM per rispondere alle domande con le fonti](https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa_with_sources.html) dalla documentazione di LangChain. diff --git a/pages/tools.ca.mdx b/pages/tools.ca.mdx index 20d78b0..5867a84 100644 --- a/pages/tools.ca.mdx +++ b/pages/tools.ca.mdx @@ -37,6 +37,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.en.mdx b/pages/tools.en.mdx index d8e4854..0910b00 100644 --- a/pages/tools.en.mdx +++ b/pages/tools.en.mdx @@ -2,6 +2,7 @@ #### (Sorted by Name) - [AI Test Kitchen](https://aitestkitchen.withgoogle.com) +- [AnySolve](https://www.anysolve.ai) - [betterprompt](https://github.com/stjordanis/betterprompt) - [Chainlit](https://github.com/chainlit/chainlit) - [ChatGPT Prompt Generator](https://huggingface.co/spaces/merve/ChatGPT-prompt-generator) @@ -38,12 +39,14 @@ - [Prompt Engine](https://github.com/microsoft/prompt-engine) - [Prompt Generator for OpenAI's DALL-E 2](http://dalle2-prompt-generator.s3-website-us-west-2.amazonaws.com) - [Promptable](https://promptable.ai) +- [prompted.link](https://prompted.link) - [PromptInject](https://github.com/agencyenterprise/PromptInject) - [Prompts.ai](https://github.com/sevazhidkov/prompts-ai) - [Promptmetheus](https://promptmetheus.com) - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.es.mdx b/pages/tools.es.mdx index 9663a3f..63fa87c 100644 --- a/pages/tools.es.mdx +++ b/pages/tools.es.mdx @@ -36,6 +36,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools herramienta](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.fi.mdx b/pages/tools.fi.mdx index 35c08bd..7eb13b0 100644 --- a/pages/tools.fi.mdx +++ b/pages/tools.fi.mdx @@ -38,6 +38,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.fr.mdx b/pages/tools.fr.mdx index 66008a7..501dde4 100644 --- a/pages/tools.fr.mdx +++ b/pages/tools.fr.mdx @@ -36,6 +36,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.it.mdx b/pages/tools.it.mdx index fb8a758..b077913 100644 --- a/pages/tools.it.mdx +++ b/pages/tools.it.mdx @@ -36,6 +36,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.jp.mdx b/pages/tools.jp.mdx index 532d303..4ff4814 100644 --- a/pages/tools.jp.mdx +++ b/pages/tools.jp.mdx @@ -35,6 +35,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools 工具](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.kr.mdx b/pages/tools.kr.mdx index 1ae927c..b614a87 100644 --- a/pages/tools.kr.mdx +++ b/pages/tools.kr.mdx @@ -36,6 +36,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools 도구](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.pt.mdx b/pages/tools.pt.mdx index fa3669d..ec20c19 100644 --- a/pages/tools.pt.mdx +++ b/pages/tools.pt.mdx @@ -37,6 +37,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools narzędzie](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.ru.mdx b/pages/tools.ru.mdx index 25df0ed..06ca1b9 100644 --- a/pages/tools.ru.mdx +++ b/pages/tools.ru.mdx @@ -40,6 +40,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools инструмент](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.tr.mdx b/pages/tools.tr.mdx index 1cd83a8..53c8c1d 100644 --- a/pages/tools.tr.mdx +++ b/pages/tools.tr.mdx @@ -37,6 +37,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com) diff --git a/pages/tools.zh.mdx b/pages/tools.zh.mdx index 2e778ee..378ba6d 100644 --- a/pages/tools.zh.mdx +++ b/pages/tools.zh.mdx @@ -37,6 +37,7 @@ - [PromptPerfect](https://promptperfect.jina.ai/) - [Promptly](https://trypromptly.com/) - [PromptSource](https://github.com/bigscience-workshop/promptsource) +- [PromptTools 工具](https://github.com/hegelai/prompttools) - [Promptist](https://promptist.herokuapp.com/) - [Scale SpellBook](https://scale.com/spellbook) - [sharegpt](https://sharegpt.com)