KR 2026 homework part 2 - Redigeerimiste ajalugu

Riina: /* Gemini API */

2026-03-27T13:02:00Z

Gemini API

←Vanem redaktsioon		Redaktsioon: 27. märts 2026, kell 15:02
102. rida:		102. rida:
	analyze_image_with_gemini(PILDI_ASUKOHT, PROMPTI_ASUKOHT)		analyze_image_with_gemini(PILDI_ASUKOHT, PROMPTI_ASUKOHT)
	</pre>		</pre>

			=== Optional: logictools vs command line reasoner gkc ===

			Logictools is unable to eat very large datasets and the options to control it are limited. Also, experimenting only on the web may be cumbersome.

			Thus I'd recommend to download the full-powered version of the reasoner used in logictools from https://github.com/tammet/gkc : it is best to use the somewhat older release https://github.com/tammet/gkc/releases/tag/v0.6.0 which has the same codebase as logictools. Just take the provided windows, linux or macos binary: no need to compile yourself.

			A rather thorough tutorial of gkc with examples is README.md here: https://github.com/tammet/gkc/blob/master/Examples/README.md

	== A tiny example ==		== A tiny example ==

Riina: /* Initial ideas and suggestions */

2026-03-17T09:13:12Z

Initial ideas and suggestions

←Vanem redaktsioon		Redaktsioon: 17. märts 2026, kell 11:13
38. rida:		38. rida:

	When writing code, prefer doing it in a dialog with an LLM. Since the task is small, you can probably just use a chat window to describe the task, bring examples, get and debug the code. It is surely a bit better to use a proper coding tool like Claude code or VS Code plugin etc for the task, but it will be perfectly OK with just a chat window as well.		When writing code, prefer doing it in a dialog with an LLM. Since the task is small, you can probably just use a chat window to describe the task, bring examples, get and debug the code. It is surely a bit better to use a proper coding tool like Claude code or VS Code plugin etc for the task, but it will be perfectly OK with just a chat window as well.

			=== Gemini API ===

			Gemini documentation examples about how to handle inline images: https://ai.google.dev/gemini-api/docs/image-understanding

			You can generate your API key in here: https://aistudio.google.com/

			Below is a simple starter code generated by Gemini shown in practice session. Recommendation is to <b>not</b> use this code, but instead generate/write your own from scratch.
			<pre>
			#!/usr/bin/env python3

			import os
			from google import genai
			from PIL import Image

			def analyze_image_with_gemini(image_path, prompt_file_path):
			# 1. API võtme laadimine keskkonnamuutujast
			api_key = os.environ.get("GEMINI_API_KEY")
			if not api_key:
			print("Viga: GEMINI_API_KEY keskkonnamuutuja on puudu!")
			return

			# 2. Initsialiseerime uue teegi Kliendi
			client = genai.Client(api_key=api_key)

			try:
			# 3. Loeme prompti tekstifailist sisse
			with open(prompt_file_path, 'r', encoding='utf-8') as file:
			prompt_text = file.read()

			# 4. Avame pildifaili
			img = Image.open(image_path)

			print("Saadan päringu Gemini mudelile. Oota natuke...")

			# 5. Argumendid 'model' ja 'contents' peavad olema nimeliselt välja kirjutatud
			response = client.models.generate_content(
			model='gemini-3-flash-preview',
			contents=[prompt_text, img]
			)

			# 6. Prindime vastuse välja
			print("\n--- GEMINI VASTUS ---")
			print(response.text)
			print("---------------------\n")

			except FileNotFoundError as e:
			print(f"Viga: Faili ei leitud. Kontrolli radu! Detailid: {e}")
			except Exception as e:
			print(f"Päringu tegemisel tekkis ootamatu viga: {e}")

			# Koodi käivitamine
			if __name__ == "__main__":
			PILDI_ASUKOHT = "room.jpg" # Sinu toa pilt
			PROMPTI_ASUKOHT = "prompt.txt" # Sinu juhised

			# Loome dummy faili testimiseks, kui prompt.txt faili veel pole
			if not os.path.exists(PROMPTI_ASUKOHT):
			with open(PROMPTI_ASUKOHT, "w", encoding="utf-8") as f:
			f.write("Palun väljasta ainult loogikafaktid selle toa kohta.")
			print(f"Loodi näidis-prompt fail: {PROMPTI_ASUKOHT}")

			analyze_image_with_gemini(PILDI_ASUKOHT, PROMPTI_ASUKOHT)
			</pre>

	== A tiny example ==		== A tiny example ==

Tammet: /* API calling example */

2026-03-09T09:56:40Z

API calling example

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:56
145. rida:		145. rida:
	== API calling example ==		== API calling example ==

	Here is an example of calling the gemini API directly with text (not images). NB! This code does not run "as is": it assumes simple functions like llm_error(...), utils.debug_print(...) are available. It is recommended to use an LLM to generate your code.		Here is an example of calling the gemini API directly with text (not images). NB! This code does not run "as is": it assumes simple functions like llm_error(...), utils.debug_print(...), _gemini_supports_thinking(version) are available. It is recommended to use an LLM to generate your code. You can, for example, give LLM this code and ask to convert it to a directly runnable code where all the necessary utilities are replaced or implemented. Also, ask it to modify the code for sending images, either by upload or pointing to an url.

	<pre>		<pre>

Tammet: /* API calling example */

2026-03-09T09:54:53Z

API calling example

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:54
145. rida:		145. rida:
	== API calling example ==		== API calling example ==

	Here is an example of calling the gemini API directly. NB! This code does not run "as is": it assumes simple functions like llm_error(...), utils.debug_print(...) are available. It is recommended to use an LLM to generate your code.		Here is an example of calling the gemini API directly with text (not images). NB! This code does not run "as is": it assumes simple functions like llm_error(...), utils.debug_print(...) are available. It is recommended to use an LLM to generate your code.

	<pre>		<pre>

Tammet – 9. märts 2026, kell 09:54

2026-03-09T09:54:36Z

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:54
142. rida:		142. rida:

	Now, the system you have to build should take an image (or image url) as an argument, form a suitable API call and give back a directly usable logic-structure data, without any "This is a beautifully designed, ...." or "Would you like me ..." or *-starting bullets or backticks etc. You can achieve this is combination with suitable instructions in the prompt and simple programmatic cleaning of the resulting text.		Now, the system you have to build should take an image (or image url) as an argument, form a suitable API call and give back a directly usable logic-structure data, without any "This is a beautifully designed, ...." or "Would you like me ..." or *-starting bullets or backticks etc. You can achieve this is combination with suitable instructions in the prompt and simple programmatic cleaning of the resulting text.

			== API calling example ==

			Here is an example of calling the gemini API directly. NB! This code does not run "as is": it assumes simple functions like llm_error(...), utils.debug_print(...) are available. It is recommended to use an LLM to generate your code.

			<pre>

			def call_gemini(version, sentences, sysprompt, max_tokens):
			try:
			sf = open(gemini_secrets_file, "r")
			key = sf.read().strip()
			sf.close()
			except:
			return llm_error("Could not read Gemini API key file: " + str(gemini_secrets_file))

			baseurl = "/v1beta/models/" + version + ":generateContent"
			genconfig = {
			"maxOutputTokens": max_tokens,
			"temperature": temperature
			}
			if _gemini_supports_thinking(version):
			genconfig["thinkingConfig"] = {"thinkingLevel": "medium"}
			call = {
			"contents": [{"parts": [{"text": sentences}]}],
			"generationConfig": genconfig
			}
			if sysprompt:
			call["system_instruction"] = {"parts": [{"text": sysprompt}]}

			utils.debug_print("gemini call", call, flag=calldebug)
			calltxt = json.dumps(call)

			trycount = 0
			while True:
			host = "generativelanguage.googleapis.com"
			conn = http.client.HTTPSConnection(host, timeout=timeout)
			try:
			conn.request("POST", baseurl, calltxt,
			headers={"content-Type": "application/json", "x-goog-api-key": key})
			response = conn.getresponse()
			except KeyboardInterrupt:
			raise
			except:
			trycount += 1
			if conn: conn.close()
			if trycount > max_retries:
			return llm_error("Gemini connection failed after " + str(max_retries) + " retries")
			print("Gemini connection failure, retrying...")
			time.sleep(sleepseconds * trycount)
			continue
			if response.status != 200 or response.reason != "OK":
			message = ""
			try:
			data = json.loads(response.read())
			if "error" in data and "message" in data["error"]:
			message = ": " + data["error"]["message"]
			except:
			pass
			trycount += 1
			if conn: conn.close()
			if trycount > max_retries:
			return llm_error("Gemini API error " + str(response.status) + " " + str(response.reason) + message)
			print("Gemini API failure, retrying:", str(response.status), str(response.reason) + message)
			time.sleep(sleepseconds * trycount)
			else:
			break

			rawdata = response.read()
			conn.close()
			try:
			data = json.loads(rawdata)
			except KeyboardInterrupt:
			raise
			except:
			return llm_error("Gemini response is not valid JSON: " + str(rawdata))

			if "candidates" not in data:
			return llm_error("Gemini response has no candidates: " + str(rawdata))
			data = data["candidates"][0]
			if "content" not in data:
			return llm_error("Gemini response has no content: " + str(data))
			data = data["content"]
			if "parts" not in data:
			return llm_error("Gemini response has no parts: " + str(data))

			utils.debug_print("gemini response:", data, flag=debug)
			res = ""
			for el in data["parts"]:
			if "text" in el:
			res += el["text"].strip()
			return res

			</pre>

Tammet: /* A tiny example */

2026-03-09T09:50:05Z

A tiny example

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:50
140. rida:		140. rida:
	Would you like me to generate a similar logic-based description for a different room, or perhaps suggest some furniture pieces that would complement this specific aesthetic?		Would you like me to generate a similar logic-based description for a different room, or perhaps suggest some furniture pieces that would complement this specific aesthetic?
	</pre>		</pre>

			Now, the system you have to build should take an image (or image url) as an argument, form a suitable API call and give back a directly usable logic-structure data, without any "This is a beautifully designed, ...." or "Would you like me ..." or *-starting bullets or backticks etc. You can achieve this is combination with suitable instructions in the prompt and simple programmatic cleaning of the resulting text.

Tammet: /* A tiny example */

2026-03-09T09:47:23Z

A tiny example

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:47
98. rida:		98. rida:
	plant(plant2).		plant(plant2).
	</pre>		</pre>
	Gemini then answers me:		Gemini 3 Flash then answers me:
	<pre>		<pre>
	This is a beautifully designed, Japandi-style living room. It balances warm wood textures with minimalist, neutral tones.		This is a beautifully designed, Japandi-style living room. It balances warm wood textures with minimalist, neutral tones.

Tammet: /* A tiny example */

2026-03-09T09:46:08Z

A tiny example

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:46
41. rida:		41. rida:
	== A tiny example ==		== A tiny example ==

	This example is without an API and without image-output examples, just using the Gemini web interface:		This example is without an API and without image / expected output examples, just using the Gemini web interface:

	I attach this image to the question: https://turing.cs.ttu.ee/~tanel.tammet/room.jpg		I attach this image to the question: https://turing.cs.ttu.ee/~tanel.tammet/room.jpg

Tammet: /* A tiny example */

2026-03-09T09:45:54Z

A tiny example

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:45
41. rida:		41. rida:
	== A tiny example ==		== A tiny example ==

	This example is without an API, just using the Gemini web interface:		This example is without an API and without image-output examples, just using the Gemini web interface:

	I attach this image to the question: https://turing.cs.ttu.ee/~tanel.tammet/room.jpg		I attach this image to the question: https://turing.cs.ttu.ee/~tanel.tammet/room.jpg

Tammet – 9. märts 2026, kell 09:45

2026-03-09T09:45:17Z

←Vanem redaktsioon		Redaktsioon: 9. märts 2026, kell 11:45
3. rida:		3. rida:
	== Task ==		== Task ==

	You will have to write a small system where a VLM (~~visual~~ language model) describes the contents of an ordinary room, using the same schema and principles you used yourself for the the first lab. The main part of the work is prompt engineering for a VLM to do a sensibly good job.		You will have to write a small system where a VLM ([https://en.wikipedia.org/wiki/Vision-language_model vision language model]: most large commercial LLMs are actually VLMs) describes the contents of an ordinary room, using the same schema and principles you used yourself for the the first lab. The main part of the work is prompt engineering for a VLM to do a sensibly good job.

	Your system should be able to automatically generate a significant portion of the data you yourself wrote in the first lab by looking at an image, by looking at the same image. It should also be able to generate a noticeable amount of sensible structured data about an image for other, similar images of rooms.		Your system should be able to automatically generate a significant portion of the data you yourself wrote in the first lab by looking at an image, by looking at the same image. It should also be able to generate a noticeable amount of sensible structured data about an image for other, similar images of rooms.