├── .env.example ├── .gitignore ├── LICENSE ├── README.md ├── dimon ├── __init__.py └── main.py ├── examples └── golden_dataset_v1.csv └── setup.py /.env.example: -------------------------------------------------------------------------------- 1 | DATABASE_URL=https://elasticsearch.example.com:9200 2 | DATABASE_INDEX=your_index 3 | USERNAME=elastic 4 | PASSWORD=your_password_here 5 | DATASET_PATH=/path/to/your/dataset 6 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control 110 | .pdm.toml 111 | .pdm-python 112 | .pdm-build/ 113 | 114 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 115 | __pypackages__/ 116 | 117 | # Celery stuff 118 | celerybeat-schedule 119 | celerybeat.pid 120 | 121 | # SageMath parsed files 122 | *.sage.py 123 | 124 | # Environments 125 | .env 126 | .venv 127 | env/ 128 | venv/ 129 | ENV/ 130 | env.bak/ 131 | venv.bak/ 132 | 133 | # Spyder project settings 134 | .spyderproject 135 | .spyproject 136 | 137 | # Rope project settings 138 | .ropeproject 139 | 140 | # mkdocs documentation 141 | /site 142 | 143 | # mypy 144 | .mypy_cache/ 145 | .dmypy.json 146 | dmypy.json 147 | 148 | # Pyre type checker 149 | .pyre/ 150 | 151 | # pytype static type analyzer 152 | .pytype/ 153 | 154 | # Cython debug symbols 155 | cython_debug/ 156 | 157 | # PyCharm 158 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 159 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 160 | # and can be added to the global gitignore or merged into this file. For a more nuclear 161 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 162 | #.idea/ 163 | 164 | # macos finder 165 | .DS_Store 166 | 167 | # Generated default report files 168 | mrr_report.csv 169 | to_confirm_change.csv 170 | count.json -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # dimon: Your Canonical Answer Management Tool 2 | dimon is a command-line interface (CLI) tool for evaluating and managing golden dataset for evaluation your retrival mechnism. 3 | 4 | ## Installation 5 | You can install dimon directly from PyPI: 6 | 7 | ``` 8 | pip install dimon-cli 9 | ``` 10 | 11 | ## Prepare env file 12 | 13 | Create a file named `.env`, or copy it from `.env.example`. 14 | This file should contain the default configuration values for dimon. Here is an example of what the `.env` file might look like: 15 | 16 | ``` 17 | DATABASE_URL=http://localhost:9200 18 | DATABASE_INDEX=your_index 19 | USERNAME=elastic 20 | PASSWORD=your_password_here 21 | DATASET_PATH=/path/to/your/dataset 22 | ``` 23 | 24 | Replace the values with the actual ones. 25 | 26 | Note: Currently, the script only supports ElasticSearch as the vector database. Ensure that your ElasticSearch instance is correctly set up and accessible via the URL provided in the DATABASE_URL parameter. The DATABASE_INDEX should point to the specific index within ElasticSearch that you want to use for storing and querying vectors. 27 | 28 | 29 | ## The CLI tool provides three main commands: 30 | 31 | ### evaluate 32 | This command evaluates a specified model on a given dataset. It computes embeddings for each document in the corpus, retrieves the top-k most similar documents for each query, and calculates the Mean Reciprocal Rank (MRR) for evaluation. 33 | 34 | ``` 35 | dimon evaluate --database_url 'http://localhost:9200' --dataset 'golden_dataset.csv' 36 | ``` 37 | 38 | ### diff 39 | This command reads a report file, filters out entries with MRR below a certain threshold 40 | 41 | ``` 42 | dimon diff --file_name 'mrr_report.csv' --threshold 0.2 43 | ``` 44 | 45 | ### merge 46 | This command reads a report file, filters out entries marked as 'Accept', and simulates a merging process. 47 | 48 | ``` 49 | dimon merge --report_name 'to_confirmed_change.csv' 50 | ``` 51 | -------------------------------------------------------------------------------- /dimon/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InfuseAI/dimon/1a4b3b7d7c9a6cdd58d0e127b339f83e06f43155/dimon/__init__.py -------------------------------------------------------------------------------- /dimon/main.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import click 3 | import time 4 | import re 5 | import os 6 | import json 7 | import pandas as pd 8 | from dataclasses import dataclass 9 | 10 | from dotenv import load_dotenv 11 | from llama_index.core import StorageContext, VectorStoreIndex 12 | from llama_index.vector_stores.elasticsearch import ElasticsearchStore 13 | from llama_index.core import VectorStoreIndex, Settings 14 | from llama_index.embeddings.ollama import OllamaEmbedding 15 | from llama_index.llms.ollama import Ollama 16 | 17 | from rich.console import Console 18 | from rich.live import Live 19 | from rich.table import Table 20 | from rich.text import Text 21 | from rich.progress import Progress 22 | 23 | 24 | @dataclass 25 | class Entry: 26 | query_id: int 27 | question: str 28 | expected_id: str 29 | expected: str 30 | actual_id: str 31 | actual: str 32 | mrr: float 33 | 34 | @click.group() 35 | def cli(): 36 | pass 37 | 38 | load_dotenv() 39 | 40 | @cli.command() 41 | @click.option('--database_url', '-db', default=os.getenv('DATABASE_URL', 'h'), help='Database URL') 42 | @click.option('--database_index', '-index', default=os.getenv('DATABASE_INDEX', ''), help='Database index') 43 | @click.option('--username', '-u', default=os.getenv('USERNAME', ''), help='Username for the database') 44 | @click.option('--password', '-p', default=os.getenv('PASSWORD', ''), help='Password for the database') 45 | @click.option('--dataset', '-d', default=os.getenv('DATASET_PATH', ''), type=click.Path(exists=True), help='Path to the dataset') 46 | def evaluate(dataset, database_url, database_index, username, password, top_k=10, verbose=False): 47 | d = pd.read_csv(dataset) 48 | 49 | # Prepare to collect evaluation results 50 | eval_results = [] 51 | console = Console() 52 | # nomic embedding model 53 | Settings.embed_model = OllamaEmbedding(model_name="nomic-embed-text") 54 | 55 | # ollama 56 | Settings.llm = Ollama(model="llama3", request_timeout=360.0) 57 | vector_store = ElasticsearchStore( 58 | index_name=database_index, 59 | es_url=database_url, 60 | es_user=username, 61 | es_password=password, 62 | ) 63 | storage_context = StorageContext.from_defaults(vector_store=vector_store) 64 | index = VectorStoreIndex.from_vector_store( 65 | vector_store=vector_store, storage_context=storage_context 66 | ) 67 | retriever = index.as_retriever(similarity_top_k=top_k) 68 | 69 | # count 70 | counts = {} 71 | 72 | with Live(console=console, screen=True, auto_refresh=False) as live: 73 | counter = 0 # Add a counter 74 | display_interval = console.size.height - 4 # Number of queries to process before updating the display 75 | processes = [] 76 | # Iterate over each query in the dataset to evaluate retrieval performance 77 | for index, row in d.iterrows(): 78 | try: 79 | query_id = row['query_id'] 80 | query = row['query'] 81 | expected_id = row['expected_id'] 82 | expected_text = row['expected_text'] 83 | except ValueError: 84 | continue # Skip this iteration and move on to the next one 85 | 86 | # Retrieve the top_k most similar documents for the current query and extract the IDs of the retrieved documents 87 | nodes = retriever.retrieve(query) 88 | retrieved_ids = [result.node_id for result in nodes] 89 | retrieved_text = re.sub(r'\W+', ' ', nodes[0].text).strip() 90 | 91 | is_hit = expected_id in retrieved_ids # assume 1 relevant doc 92 | 93 | # Calculate the Mean Reciprocal Rank (RR) and append to results 94 | if is_hit: 95 | rank = retrieved_ids.index(expected_id) + 1 96 | mrr = 1 / rank 97 | 98 | for r in retrieved_ids[:3]: 99 | if not r in counts: 100 | counts[r] = 0 101 | counts[r] = counts[r] + 1 102 | else: 103 | mrr = 0 104 | eval_results.append(mrr) 105 | 106 | #Generate a process for the current query and add it to the list of processes 107 | process = _generate_entry(query_id, query, expected_id, expected_text, retrieved_ids[0], retrieved_text, mrr) 108 | processes.append(process) 109 | 110 | counter += 1 # Increment the counter 111 | if counter % display_interval == 0: # Only update the display every display_interval queries 112 | tmp = sorted(processes[counter - display_interval : counter], key=lambda p: p.mrr, reverse=True) 113 | live.update(_create_process_table(console, tmp), refresh=True) 114 | 115 | if eval_results: 116 | final_table = Table(style="bold") 117 | final_table.add_row("AVG MRR", "", "", "", f"{np.average(eval_results):.1f}") 118 | live.update(final_table) 119 | time.sleep(1) 120 | 121 | data = [vars(p) for p in processes] 122 | df = pd.DataFrame(data) 123 | # TODO: specify output file name 124 | mrr_report_filename = 'mrr_report.csv' 125 | df.to_csv(mrr_report_filename, index=False) 126 | vector_store.close() 127 | 128 | with open('count.json', 'w') as f: 129 | json.dump(counts, f) 130 | 131 | console.print(f'Average MRR: {np.average(eval_results):.2f}', style="magenta") 132 | console.print(f"MRR report has been saved to '{mrr_report_filename}'") 133 | 134 | # Return the average MRR across all queries as the final evaluation metric 135 | return np.average(eval_results) 136 | 137 | 138 | @cli.command() 139 | @click.option('--file_name', '-f', default='mrr_report.csv', required=True) 140 | @click.option('--threshold', '-t', default=0.7, required=True) 141 | def diff(file_name, threshold): 142 | df = pd.read_csv(file_name) 143 | df = df[df['mrr'] < threshold ] 144 | num = df.shape[0] 145 | df['Accept / Reject'] = '' 146 | df.to_csv('to_confirm_change.csv') 147 | console = Console() 148 | console.print(f"Filtered out {num} records with MRR less than the threshold, saved to 'to_confirm_change.csv'") 149 | 150 | @cli.command() 151 | @click.option('--report', '-r', default='to_confirm_change.csv') 152 | @click.option('--dataset', '-d', default=os.getenv('DATASET_PATH', ''), type=click.Path(exists=True), help='Path to the dataset') 153 | def merge(dataset, report): 154 | r = pd.read_csv(report) 155 | r = r[r['Accept / Reject'] == 'Accept'] 156 | d = pd.read_csv(dataset) 157 | 158 | # Merge the dataframes on 'query_id' 159 | merged = pd.merge(d, r[['query_id', 'actual_id', 'actual']], on='query_id', how='left') 160 | 161 | # Update 'expected_id' and 'expected_text' with 'actual_id' and 'actual' 162 | merged.loc[merged['actual_id'].notna(), 'expected_id'] = merged['actual_id'] 163 | merged.loc[merged['actual'].notna(), 'expected_text'] = merged['actual'] 164 | 165 | # Drop the 'actual_id' and 'actual' columns 166 | merged.drop(['actual_id', 'actual'], axis=1, inplace=True) 167 | 168 | # Update 'd' with 'merged' 169 | d = merged 170 | 171 | with Progress() as progress: 172 | 173 | task3 = progress.add_task("[cyan] Merging ...", total=merged.shape[0]) 174 | while not progress.finished: 175 | progress.update(task3, advance=0.9) 176 | #time.sleep(0.01) 177 | 178 | console = Console() 179 | console.print("Accepted answers have been merged into golden answers, saved to 'examples/merged_golden_dataset.csv'") 180 | d.to_csv('examples/merged_golden_dataset.csv', index=False) 181 | 182 | 183 | def _generate_entry(id: int, q: str, ei: str, e: str, ai: str, a: str, mrr: float) -> Entry: 184 | return Entry( 185 | query_id=id, 186 | question=q, 187 | expected_id=ei, 188 | expected=e, 189 | actual_id=ai, 190 | actual=a, 191 | mrr=mrr # Generate a random float between 0 and 1 192 | ) 193 | 194 | def _create_process_table(console, processes: list) -> Table: 195 | 196 | table = Table() 197 | table.add_column("ID", ratio=1) 198 | table.add_column("QUESTION", overflow="crop", no_wrap=True, ratio=2) 199 | table.add_column("EXPECTED",overflow="crop", no_wrap=True, ratio=2) 200 | table.add_column("ACTUAL", overflow="crop", no_wrap=True, ratio=2) 201 | table.add_column("MRR", style="dim", width=10, ratio=1) 202 | table.width = console.width * 2 // 3 203 | 204 | for process in processes: 205 | mrr_color = "green" if process.mrr > 0.7 else "yellow" if process.mrr > 0.3 else "red" 206 | mrr_text = Text(f"{process.mrr:.1f}", style=mrr_color) 207 | table.add_row( 208 | str(process.query_id), 209 | process.question, 210 | process.expected, 211 | process.actual, 212 | mrr_text, 213 | ) 214 | 215 | return table 216 | 217 | if __name__ == '__main__': 218 | evaluate() -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup( 4 | name='dimon-cli', 5 | version='0.1.0', 6 | py_modules=['dimon'], 7 | description='dimensional monitoring cli', 8 | long_description=open('README.md').read(), 9 | long_description_content_type='text/markdown', 10 | author='InfuseAI', 11 | url='https://github.com/InfuseAI/dimon', 12 | install_requires=[ 13 | 'Click', 14 | 'pandas', 15 | 'python-dotenv', 16 | 'llama-index', 17 | 'llama-index-vector-stores-elasticsearch', 18 | 'llama-index-llms-ollama', 19 | 'llama-index-embeddings-ollama', 20 | 'rich', 21 | ], 22 | entry_points={ 23 | 'console_scripts': ['dimon = dimon.main:cli'] 24 | }, 25 | ) --------------------------------------------------------------------------------