KR 2025 homework part 1 - Redigeerimiste ajalugu

Riina – 26. veebruar 2025, kell 15:25

2025-02-26T15:25:25Z

←Vanem redaktsioon		Redaktsioon: 26. veebruar 2025, kell 17:25
1. rida:		1. rida:
	You will have to write a small program to convert/filter data to a suitable format for experimenting with a logical reasoner, and then write ca 10 nontrivial rules for answering questions. ~~Add some facts using LLM~~.		You will have to write a small program to convert/filter data to a suitable format for experimenting with a logical reasoner, add some facts using LLM and then write ca 10 nontrivial rules for answering questions. Number of questions should be ca 5 depending on how complex the rules are. You probably use more then one rule to answer a question. You can also reuse rules to answer other questions.

	Finally, experiment with the reasoner on this data + rules and make a small presentation of your data, rules, successes and failures.		Finally, experiment with the reasoner on this data + rules and make a small presentation of your data, rules, successes and failures.
59. rida:		59. rida:
	* [https://together.ai together.ai] that allows you to use open source LLMs for a small fee. Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free. They used to have 25$ credit for new users, but this might not be the case anymore.		* [https://together.ai together.ai] that allows you to use open source LLMs for a small fee. Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free. They used to have 25$ credit for new users, but this might not be the case anymore.

	* [https://aistudio.google.com/ aistudio.google.com] Google AI Studio now also allows to create an API key (includes a free tier), that can be used to make request over Gemini API (see the documentation: https://ai.google.dev/gemini-api/docs) for more information.		* [https://aistudio.google.com/ aistudio.google.com] Google AI Studio now also allows to create an API key (includes a free tier), that can be used to make request over Gemini API (see the documentation: https://ai.google.dev/gemini-api/docs) for more information. See [[sample Gemini code and prompt]] used in practice session for inspiration. Note that you might not get the same results even when using the same model and prompt.

	* [https://ollama.com/ ollama.com] makes it easy to run free models on local computer. Smaller models run even without GPU.		* [https://ollama.com/ ollama.com] makes it easy to run free models on local computer. Smaller models run even without GPU.

Riina: /* LLM generated data */

2025-02-23T14:07:39Z

LLM generated data

←Vanem redaktsioon		Redaktsioon: 23. veebruar 2025, kell 16:07
58. rida:		58. rida:

	* [https://together.ai together.ai] that allows you to use open source LLMs for a small fee. Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free. They used to have 25$ credit for new users, but this might not be the case anymore.		* [https://together.ai together.ai] that allows you to use open source LLMs for a small fee. Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free. They used to have 25$ credit for new users, but this might not be the case anymore.

			* [https://aistudio.google.com/ aistudio.google.com] Google AI Studio now also allows to create an API key (includes a free tier), that can be used to make request over Gemini API (see the documentation: https://ai.google.dev/gemini-api/docs) for more information.

	* [https://ollama.com/ ollama.com] makes it easy to run free models on local computer. Smaller models run even without GPU.		* [https://ollama.com/ ollama.com] makes it easy to run free models on local computer. Smaller models run even without GPU.

Riina: /* LLM generated data */

2025-02-18T16:00:41Z

LLM generated data

←Vanem redaktsioon		Redaktsioon: 18. veebruar 2025, kell 18:00
54. rida:		54. rida:
	You can use any LLM chat or API. For API usage there are some almost free options.		You can use any LLM chat or API. For API usage there are some almost free options.

	* [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]). Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free.

	* [https://mistral.ai/ mistral.ai], you can try API for free (150.00€/month limit), in exchange your API requests may be used to improve their services.		* [https://mistral.ai/ mistral.ai] you can try API for free (150.00€/month limit), in exchange your API requests may be used to improve their services.

			* [https://together.ai together.ai] that allows you to use open source LLMs for a small fee. Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free. They used to have 25$ credit for new users, but this might not be the case anymore.

			* [https://ollama.com/ ollama.com] makes it easy to run free models on local computer. Smaller models run even without GPU.

			* [https://github.com/cheahjs/free-llm-api-resources List of additional resources that have free options]

	= Rules and questions =		= Rules and questions =

Riina: /* LLM generated data */

2025-02-18T14:35:13Z

LLM generated data

←Vanem redaktsioon		Redaktsioon: 18. veebruar 2025, kell 16:35
52. rida:		52. rida:
	You can either ask for facts formatted in RDF triples and convert them into logic. Or you can ask facts in logic. Experiment what works best!		You can either ask for facts formatted in RDF triples and convert them into logic. Or you can ask facts in logic. Experiment what works best!

	You can use any LLM chat or API. For API usage ~~we suggest using~~ [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]). Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free.		You can use any LLM chat or API. For API usage there are some almost free options.

			* [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]). Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free.

			* [https://mistral.ai/ mistral.ai], you can try API for free (150.00€/month limit), in exchange your API requests may be used to improve their services.

	= Rules and questions =		= Rules and questions =

Riina: /* Data */

2025-02-17T11:00:13Z

Data

←Vanem redaktsioon		Redaktsioon: 17. veebruar 2025, kell 13:00
13. rida:		13. rida:
	Riina took the large datasets from https://yago-knowledge.org/ and prepared relatively small selections (all about something Estonian) from this data. The link to the files is [https://cs.taltech.ee/staff/riina.maigre/iti8700/lab1/ here]. The data is presented as plain triplets, no fancy encoding (except namespaces) is involved.		Riina took the large datasets from https://yago-knowledge.org/ and prepared relatively small selections (all about something Estonian) from this data. The link to the files is [https://cs.taltech.ee/staff/riina.maigre/iti8700/lab1/ here]. The data is presented as plain triplets, no fancy encoding (except namespaces) is involved.

	This set of files also contains an estonian_taxonomy.txt file, which is a subset of yago-taxonomy.txt. Using ~~all or part~~ of estonian_taxonomy.txt file might help to write more complex rules.		This set of files also contains an estonian_taxonomy.txt file, which is a subset of yago-taxonomy.txt. Using some parts of estonian_taxonomy.txt file might help to write more complex rules.

	Suggested topics are tourism and entertainment/culture. But you can choose any other topic.		Suggested topics are tourism and entertainment/culture. But you can choose any other topic.

Riina: /* LLM generated data */

2025-02-12T12:51:28Z

LLM generated data

←Vanem redaktsioon		Redaktsioon: 12. veebruar 2025, kell 14:51
49. rida:		49. rida:

	Ideas for adding additional facts sightseeing objects, what is close to what etc for tourism and facts about actors or musicians etc for entertainment/culture.		Ideas for adding additional facts sightseeing objects, what is close to what etc for tourism and facts about actors or musicians etc for entertainment/culture.

			You can either ask for facts formatted in RDF triples and convert them into logic. Or you can ask facts in logic. Experiment what works best!

	You can use any LLM chat or API. For API usage we suggest using [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]). Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free.		You can use any LLM chat or API. For API usage we suggest using [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]). Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free.

Riina: /* Data */

2025-02-12T12:42:46Z

Data

←Vanem redaktsioon		Redaktsioon: 12. veebruar 2025, kell 14:42
15. rida:		15. rida:
	This set of files also contains an estonian_taxonomy.txt file, which is a subset of yago-taxonomy.txt. Using all or part of estonian_taxonomy.txt file might help to write more complex rules.		This set of files also contains an estonian_taxonomy.txt file, which is a subset of yago-taxonomy.txt. Using all or part of estonian_taxonomy.txt file might help to write more complex rules.

	Suggested topics are tourism and entertainment/culture.		Suggested topics are tourism and entertainment/culture. But you can choose any other topic.

	First, please download the files and explore them a bit. Then convert the files to the format our reasoner gk (or its web version http://logictools.org) can eat. Write a program for this! Trying to just replace/filter stuff using an editor will become very cumbersome soon.		First, please download the files and explore them a bit. Then convert the files to the format our reasoner gk (or its web version http://logictools.org) can eat. Write a program for this! Trying to just replace/filter stuff using an editor will become very cumbersome soon.

Riina: /* Data */

2025-02-12T12:36:57Z

Data

←Vanem redaktsioon		Redaktsioon: 12. veebruar 2025, kell 14:36
12. rida:		12. rida:

	Riina took the large datasets from https://yago-knowledge.org/ and prepared relatively small selections (all about something Estonian) from this data. The link to the files is [https://cs.taltech.ee/staff/riina.maigre/iti8700/lab1/ here]. The data is presented as plain triplets, no fancy encoding (except namespaces) is involved.		Riina took the large datasets from https://yago-knowledge.org/ and prepared relatively small selections (all about something Estonian) from this data. The link to the files is [https://cs.taltech.ee/staff/riina.maigre/iti8700/lab1/ here]. The data is presented as plain triplets, no fancy encoding (except namespaces) is involved.

			This set of files also contains an estonian_taxonomy.txt file, which is a subset of yago-taxonomy.txt. Using all or part of estonian_taxonomy.txt file might help to write more complex rules.

	Suggested topics are tourism and entertainment/culture.		Suggested topics are tourism and entertainment/culture.

Riina: /* Ideas for writing your own rules */

2025-02-12T12:30:59Z

Ideas for writing your own rules

←Vanem redaktsioon		Redaktsioon: 12. veebruar 2025, kell 14:30
122. rida:		122. rida:
	Some ideas, including somewhat crazy ones:		Some ideas, including somewhat crazy ones:

	* Categorizing objects into larger categories, using the transivity of rdf:type (you have to write your own rule for the transitivity)~~. You may also (strictly optional) convert yago-taxonomy.txt to rules and use this for larger categories~~.		* Categorizing objects into larger categories, using the transivity of rdf:type (you have to write your own rule for the transitivity).
	* What city/town/lake/island is inside what, according to located-in-estonia.txt. What can you derive from this, say, using transitivity of <i>inside</i>?		* What city/town/lake/island is inside what, according to located-in-estonia.txt. What can you derive from this, say, using transitivity of <i>inside</i>?
	* Who was born where and how could they potentially travel with the boat to a place another person was born :)		* Who was born where and how could they potentially travel with the boat to a place another person was born :)

Riina: /* LLM generated data */

2025-02-03T14:21:02Z

LLM generated data

←Vanem redaktsioon		Redaktsioon: 3. veebruar 2025, kell 16:21
48. rida:		48. rida:
	Ideas for adding additional facts sightseeing objects, what is close to what etc for tourism and facts about actors or musicians etc for entertainment/culture.		Ideas for adding additional facts sightseeing objects, what is close to what etc for tourism and facts about actors or musicians etc for entertainment/culture.

	You can use any LLM chat or API. For API usage we suggest using [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]).		You can use any LLM chat or API. For API usage we suggest using [https://together.ai together.ai], that allows you to use open source LLMs for a small fee. As a new user you will get 25$ credit, which will last for a long time using cheaper models (see [https://www.together.ai/pricing https://www.together.ai/pricing]). Two of their models are available for free: Llama-3.3-70B-Instruct-Turbo-Free and DeepSeek-R1-Distill-Llama-70B-free.


	= Rules and questions =		= Rules and questions =