LLM Zoomcamp 2025

Homework 1: Introduction Statistics

Distribution of scores and reported study time for this homework.

Submissions

426

Median total score

6

Average total score

6

Score distribution

All values are points.

Questions score

Min
1
Median
6.0
Max
6
Q1
5.0
Avg
5.2
Q3
6.0

Learning in public score

Min
-
Median
0.0
Max
7
Q1
0.0
Avg
0.5
Q3
0.0

Total score

Min
1
Median
6.0
Max
14
Q1
5.0
Avg
5.8
Q3
6.0

Time distribution

All values are hours reported by students.

Lectures

Min
0.0
Median
4.0
Max
72.0
Q1
2.0
Avg
5.8
Q3
6.0

Homework

Min
0.0
Median
2.0
Max
72.0
Q1
2.0
Avg
3.7
Q3
4.0

Question breakdown

Correctness and answer distribution per question.

1. Running Elastic

426 / 427 correct (99.8%)

Answer Count
dbcbbbd0bc4924cfeb28929dc05d82d662c527b7 177
42f05b9372a9a4a470db3b52817899b99a76ee73 127
0a58bc1dc7a4ae5412db66624aab968370bd44ce 15
73f7594ea00db50aa7e941e151a5b3985f01e364 13
"42f05b9372a9a4a470db3b52817899b99a76ee73" 8
"dbcbbbd0bc4924cfeb28929dc05d82d662c527b7" 6
"build_hash" : "dbcbbbd0bc4924cfeb28929dc05d82d662c527b7" 6
"build_hash" : "42f05b9372a9a4a470db3b52817899b99a76ee73" 4
112859b85d50de2a7e63f73c8fc70b99eea24291 3
da95df118650b55a500dcc181889ac35c6d8da7c 2
curl localhost:9200 2
!curl localhost:9200 2
8.4.3 2
df116ec6455476a07daafc3ded80e2bb1a3385ed 1
c6b8d8d951c631db715485edc1a74190cdce4189 1
version 8.17.6 doesn't exist (as requested by homework). I used most updated version 9.0.1: 73f7594ea00db50aa7e941e151a5b3985f01e364 1
'73f7594ea00db50aa7e941e151a5b3985f01e364' 1
c94b4700cda13820dad5aa74fae6db185ca5c304 1
8.17.6 1
{ "name" : "189deafa01d2", "cluster_name" : "docker-cluster", "cluster_uuid" : "tQiJnz5nTimKs-Lg0cnRZg", "version" : { "number" : "8.4.3", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "42f05b9372a9a4a470db3b52817899b99a76ee73", "build_date" : "2022-10-04T07:17:24.662462378Z", "build_snapshot" : false, "lucene_version" : "9.3.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
{ "name" : "db563346bc56", "cluster_name" : "docker-cluster", "cluster_uuid" : "Szzq0AtDQyGOR6jtjgzDzw", "version" : { "number" : "8.4.3", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "42f05b9372a9a4a470db3b52817899b99a76ee73", "build_date" : "2022-10-04T07:17:24.662462378Z", "build_snapshot" : false, "lucene_version" : "9.3.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
cbbbd0bc4924cfeb28929dc05d82d662c527b7 1
a47e00f30c727191147a46944b5a3e1572c68407 1
Issuing the "curl localhost:9200" I get the build hash : 42f05b9372a9a4a470db3b52817899b99a76ee73 1
es_client = Elasticsearch('http://localhost:9200/') es_client.info() 1
!curl http://localhost:9200 1
"73f7594ea00db50aa7e941e151a5b3985f01e364" (i used version 9.0.1 because of compatability issues) 1
b26557f585b7d95c71a5549e571a6bcd2667697d 1
Ans. dbcbbbd0bc4924cfeb28929dc05d82d662c527b7 1
es_client = Elasticsearch('http://localhost:9200') 1
{ "name" : "cd431ac30e2a", "cluster_name" : "docker-cluster", "cluster_uuid" : "GUYuxDtpT92dXg7VNVN8lA", "version" : { "number" : "8.17.6", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "dbcbbbd0bc4924cfeb28929dc05d82d662c527b7", "build_date" : "2025-04-30T14:07:12.231372970Z", "build_snapshot" : false, "lucene_version" : "9.12.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
"73f7594ea00db50aa7e941e151a5b3985f01e364" 1
version.build_hash value is 42f05b9372a9a4a470db3b52817899b99a76ee73 1
version.build_hash = 2e94dc48d5dbe407e2066eb6839c826fa2436e24 1
ObjectApiResponse({'name': '8edfe3cca075', 'cluster_name': 'docker-cluster', 'cluster_uuid': 'J5fG_xtaTiec5vx24XJ6cg', 'version': {'number': '8.4.3', 'build_flavor': 'default', 'build_type': 'docker', 'build_hash': '42f05b9372a9a4a470db3b52817899b99a76ee73', 'build_date': '2022-10-04T07:17:24.662462378Z', 'build_snapshot': False, 'lucene_version': '9.3.0', 'minimum_wire_compatibility_version': '7.17.0', 'minimum_index_compatibility_version': '7.0.0'}, 'tagline': 'You Know, for Search'}) 1
42f05b9372a9a4a470db3b52817899b99a76ee7 1
c1f6b0439a84f9c9b95aac4d930df0b09b4343a33ae0a8eb13192608de230785 1
version 8.4.3 1
Running elastic search 9.0.0 1
f65d44c502b15da3eb3a9ab41f1fcdb6ca3d5b6e 1
"build_hash" : "42f05b9372a9a4a470db3b52817899b99a76ee73", 1
8.15.3 1
9.0.2 1
1d5f5eaf892bad62b6e8263b2c2b709e8376f5f6 1
version.build.hash = "42f05b9372a9a4a470db3b52817899b99a76ee73" 1
~/zoomcamp/llm_zoomcamp % curl localhost:9200 { "name" : "262ab57e7628", "cluster_name" : "docker-cluster", "cluster_uuid" : "inf_rvdPQn6T0pFppBAPPA", "version" : { "number" : "8.17.6", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "dbcbbbd0bc4924cfeb28929dc05d82d662c527b7", "build_date" : "2025-04-30T14:07:12.231372970Z", "build_snapshot" : false, "lucene_version" : "9.12.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
version.build_hash value is "dbcbbbd0bc4924cfeb28929dc05d82d662c527b7" 1
dbcbbbd 1
1.2.0 1
docker run -d --name elasticsearch \ 1
{ "name" : "9b00f8f1e732", "cluster_name" : "docker-cluster", "cluster_uuid" : "li9JE_S9R8CXrQpWml7hiw", "version" : { "number" : "8.17.6", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "dbcbbbd0bc4924cfeb28929dc05d82d662c527b7", "build_date" : "2025-04-30T14:07:12.231372970Z", "build_snapshot" : false, "lucene_version" : "9.12.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
$ curl http://localhost:9200 { "name" : "d98eb13543c0", "cluster_name" : "docker-cluster", "cluster_uuid" : "ZjGTCkHwThybuTV84R7dDg", "version" : { "number" : "8.4.3", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "42f05b9372a9a4a470db3b52817899b99a76ee73", "build_date" : "2022-10-04T07:17:24.662462378Z", "build_snapshot" : false, "lucene_version" : "9.3.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
"build_hash" : "da95df118650b55a500dcc181889ac35c6d8da7c" 1
2f05b9372a9a4a470db3b52817899b99a76ee73 1
747663ddda3421467150de0e4301e8d4bc636b0c 1
5058a589ac76e63750372f8ca9b2c0182563383e 1
Done 1
docs_url = 'https://github.com/DataTalksClub/llm-zoomcamp/blob/main/01-intro/documents.json?raw=1' docs_response = requests.get(docs_url) documents_raw = docs_response.json() documents = [] for course in documents_raw: course_name = course['course'] for doc in course['documents']: doc['course'] = course_name documents.append(doc) 1
{ "name" : "eb363035b330", "cluster_name" : "docker-cluster", "cluster_uuid" : "FaccVoeSS5e6WMqIialyXQ", "version" : { "number" : "8.17.6", "build_flavor" : "default", "build_type" : "docker", "build_hash" : "dbcbbbd0bc4924cfeb28929dc05d82d662c527b7", "build_date" : "2025-04-30T14:07:12.231372970Z", "build_snapshot" : false, "lucene_version" : "9.12.0", "minimum_wire_compatibility_version" : "7.17.0", "minimum_index_compatibility_version" : "7.0.0" }, "tagline" : "You Know, for Search" } 1
docker run -it \ --rm \ --name elasticsearch \ -m 4GB \ -p 9200:9200 \ -p 9300:9300 \ -e "discovery.type=single-node" \ -e "xpack.security.enabled=false" \ docker.elastic.co/elasticsearch/elasticsearch:8.4.3 1
42f05b9372a9a4a470db3b52817899b99a76aee73 1
6cd9f9f5b7b9b3a6f7b7b7b7b7b7b7b7b7b7b7b7 1
48a287ab9497e852de30327444b0809e55d46466 1

2. Indexing the data

408 / 427 correct (95.6%)

1 insert 9 (2.1%)
2 index 409 (95.8%)
3 put 3 (0.7%)
4 add 3 (0.7%)

3. Searching

348 / 427 correct (81.5%)

1 84.50 30 (7.0%)
2 64.50 8 (1.9%)
3 44.50 349 (81.7%)
4 24.50 31 (7.3%)

4. Filtering

372 / 427 correct (87.1%)

1 How do I debug a docker container? 35 (8.2%)
2 How do I copy files from a different folder into docker container’s working directory? 373 (87.4%)
3 How do Lambda container images work? 8 (1.9%)
4 How can I annotate a graph? 3 (0.7%)

5. Building a prompt

333 / 427 correct (78.0%)

1 946 31 (7.3%)
2 1446 334 (78.2%)
3 1946 24 (5.6%)
4 2446 32 (7.5%)

6. Tokens

328 / 427 correct (76.8%)

1 120 13 (3.0%)
2 220 29 (6.8%)
3 320 329 (77.0%)
4 420 50 (11.7%)

Calculated: 23 June 2025, 12:14