Questions score
- Min
- 4
- Median
- 6.0
- Max
- 6
- Q1
- 6.0
- Avg
- 5.9
- Q3
- 6.0
LLM Zoomcamp 2024
Homework 5: Ingestion pipeline Statistics
Distribution of scores and reported study time for this homework.
Submissions
174
Median total score
6
Average total score
7
Score distribution
All values are points.
Learning in public score
- Min
- -
- Median
- 0.0
- Max
- 7
- Q1
- 0.0
- Avg
- 0.8
- Q3
- 0.0
Total score
- Min
- 4
- Median
- 6.0
- Max
- 14
- Q1
- 6.0
- Avg
- 6.9
- Q3
- 7.0
Time distribution
All values are hours reported by students.
Lectures
- Min
- 0.2
- Median
- 2.0
- Max
- 15.0
- Q1
- 1.0
- Avg
- 2.7
- Q3
- 3.0
Homework
- Min
- 0.0
- Median
- 3.0
- Max
- 20.0
- Q1
- 2.0
- Avg
- 4.4
- Q3
- 6.0
Question breakdown
Correctness and answer distribution per question.
1. Mage version
174 / 174 correct (100.0%)
| Answer | Count |
|---|---|
| v0.9.72 | 102 |
| 0.9.72 | 64 |
| 0.9.73 | 2 |
| v0.9.73 | 2 |
| v0.9.72 | image.version: "td--create_blocks_tmp4" | 1 |
| 0.9.7.2 | 1 |
2. Number of documents
170 / 174 correct (97.7%)
1
1
170 (97.7%)
2
2
1 (0.6%)
3
3
1 (0.6%)
4
4
1 (0.6%)
3. Chunking: number of questions
167 / 174 correct (96.0%)
1
66
0 (0.0%)
2
76
0 (0.0%)
3
86
167 (96.0%)
4
96
4 (2.3%)
4. Export: last processed document
174 / 174 correct (100.0%)
| Answer | Count |
|---|---|
| 6fc3236a | 51 |
| a976d6e7 | 32 |
| fa136280 | 23 |
| d8c4c7bb | 17 |
| 88cff058 | 3 |
| 3d6f30b1 | 2 |
| 424a2ae1 | 1 |
| index_name: documents_20240814_4531, id_document:fa136280 | 1 |
| 6bac821d | 1 |
| document id: a976d6e7 index name: documents_20240817_4450 | 1 |
| 2b15bf75 | 1 |
| fd8cf892 | 1 |
| last_document_id: '6fc3236a' && index name: documents_20240819_101956 | 1 |
| 6fc3236a (documents_20240813_1009) | 1 |
| documents_20240819_0627 | 1 |
| id = a976d6e7, index_name = documents_20240819_4351 | 1 |
| documents_20240820_4538 | 1 |
| document_id: d8c4c7bb | index_name: documents_20240819_2747 | 1 |
| 19 | 1 |
| document_id': 'a976d6e7', index name: documents_20240819_1027 | 1 |
| index_name: documents_20240818_4321 Connecting to Elasticsearch at ... ... 'document_id': 'a976d6e7'} | 1 |
| a976d67 | 1 |
| 831740ff | 1 |
| 0bd5fc78 | 1 |
| document_id: fa136280, index name: documents_20240819_4530 | 1 |
| documents_20240819_5805 | 1 |
| 1 | 1 |
| R= 6fc3236a | 1 |
| my_index_20240820_174208 | 1 |
| documents_20240820_2525 | 1 |
| 21f657ce | 1 |
| Index name: documents_20240825_2119, Last document indexed: d8c4c7bb | 1 |
| cBMLgZEBFajW2syKZI84 | 1 |
| llm_faq_v1:workshops__x:question | 1 |
| index_name: documents_20240818_4321 | 1 |
| {'text': 'Yes, but if you want to receive a certificate, you need to submit your project while we’re still accepting submissions.', 'section': 'General course-related questions', 'question': 'I just discovered the course. Can I still join?'} | 1 |
| ad7a2019 | 1 |
| {'text': 'Prior to using Ollama models in llm-zoomcamp tasks, you need to have ollama installed on your pc and the relevant LLM model downloaded with ollama from https://www.ollama.com\nTo download ollama for Ubuntu:\n``` curl -fsSL https://ollama.com/install.sh | sh ```\nTo download ollama for Mac and Windows, follow the guide on this link:\nhttps://ollama.com/download/\nOllama a number of open-source LLMs like:\nLlama3\nPhi3\nMistral and Mixtral\nGemma\nQwen\nYou can explore more models on https://ollama.com/library/\nTo download a model in Ollama, simply open command prompt and type:\n``` ollama run model_name ```\ne.g.\n``` ollama run phi3 ```\nIt will automatically download the model and you can use it same way as above for later time.\nTo use Ollama models for inference and llm-zoomcamp tasks, use the following function:\nimport ollama\ndef llm(prompt):\nresponse = ollama.chat(\nmodel="llama3",\nmessages=[{"role": "user", "content": prompt}]\n)\nreturn response[\'message\'][\'content\']\nFor example, we can use it in the following way:\nprompt = "When does the llm-zoomcamp course start?"\nanswer = llm(prompt)\nprint(answer)', 'section': 'Module 1: Introduction', 'question': 'OpenSource: How can I use Ollama open-source models locally on my pc without using any API?', 'course': 'llm-zoomcamp', 'document_id': 'a976d6e7'} | 1 |
5. Testing the retrieval: document id
174 / 174 correct (100.0%)
| Answer | Count |
|---|---|
| bf024675 | 103 |
| a705279d | 5 |
| CwNVY5EB3lQqJkEzx1pJ | 5 |
| tCtKY5EB8-OPqGIazkNH | 5 |
| 1fb710f3 | 3 |
| 7f502aa2 | 1 |
| 2eb1e9a7 | 1 |
| c48b90b6 | 1 |
| 367281d9 | 1 |
| NbmcaJEBwhMKiLSCpGG_ | 1 |
| 8Fe9aZEBD4y5RrGeHC82 | 1 |
| 28 | 1 |
| 'document_id': 'bf024675' | 1 |
| 'bf024675' | 1 |
| sfg5a5EBYm7XgtL9aU0 | 1 |
| 1183a5e3 | 1 |
| 3EV3bJEB9knvViczL5qY | 1 |
| 2 | 1 |
| i35zcJEB2TUQIgZvkGht | 1 |
| documents_20240821_2955 | 1 |
| _UWHcpEBYxc-ogipsmHQ | 1 |
| 4vDbcZEB5JcrJ9W4cy9g | 1 |
| Zl2_dJEBb56zewSe8BNL | 1 |
| llm_faq_v1:general_course_related_questions:when_will_the_course_be_offered_next_ | 1 |
| a5301a1f | 1 |
| 6cf805ca | 1 |
6. Reindexing: document id
174 / 174 correct (100.0%)
| Answer | Count |
|---|---|
| b6fa77f3 | 84 |
| bf024675 | 18 |
| a705279d | 5 |
| HYN4Y5EB_QV3m7mGYk1o | 5 |
| YCtNY5EB8-OPqGIal0RD | 5 |
| b2834cdf | 3 |
| 2f030489 | 2 |
| d3b7d9dc | 1 |
| 9b997fdf | 1 |
| 5c0c7942 | 1 |
| Summer 2026 | 1 |
| d6385bf8 | 1 |
| N7nPaJEBwhMKiLSC8WJe | 1 |
| TFfcaZEBD4y5RrGedTH5 | 1 |
| N/A | 1 |
| 'document_id': 'b6fa77f3' | 1 |
| 'b6fa77f3' | 1 |
| B_g8a5EBYm7XgtL9FU5a | 1 |
| b90b2d4c | 1 |
| 3EV3bJEB9knvViczL5qY | 1 |
| 1112 | 1 |
| 4X4acZEB2TUQIgZvL2hN | 1 |
| documents_20240821_3753 | 1 |
| _0WMcpEBYxc-ogipWWLi | 1 |
| OPBFcpEB5JcrJ9W4-zBI | 1 |
| vl3gdJEBb56zewSeZRTc | 1 |
| C72keJEBNldql2DdSrhw | 1 |
| llm_faq_v1:general_course_related_questions:when_is_the_next_cohort_ | 1 |
| 9816f1ae | 1 |
Calculated: 11 October 2024, 08:34