added readme

README.md

@@ -1,3 +1,29 @@
 # CI using Athina Evals
 
-This repository demonstrates on how you can do a CI configuration for your RAG application using Athina Evals.
+This repository demonstrates on how you can do a CI configuration for your RAG application using Athina Evals.
+
+## Rag Application
+
+A sample Rag application is provided in the `src` directory. This is a simple rag application built using llama_index. We are going add evaluations for this application using Athina Evals.
+
+## Setting up the dependencies
+
+Install the necessary dependencies by running the following command:
+
+```bash
+pip install -r requirements.txt
+```
+
+additionally you need to install the `athina-evals` package by running the following command:
+
+```bash
+pip install athina-evals
+```
+
+## Running the evaluation script
+
+Then you can run the evaluation script by running the following command:
+
+```bash
+python -m evaluations/run_athina_evals.py
+```

evaluations/golden_dataset.jsonl

@@ -9,4 +9,4 @@
 {"query": "How has Y Combinator's alumni network impacted new entrepreneurs?", "expected_response": "Y Combinator's vast network of alumni and mentors provides ongoing support, advice, and networking opportunities to new entrepreneurs, significantly impacting their success and growth."}
 {"query": "What qualities does Y Combinator look for in the founding team of a startup?", "expected_response": "Y Combinator looks for qualities such as strength, cohesiveness, and the ability to execute rapidly in the founding team of a startup."}
 {"query": "What factors about a startup's product or service are important to Y Combinator?", "expected_response": "The novelty, market potential, and the problem it solves are important factors about a startup's product or service to Y Combinator."}
-{"query": "What does Y Combinator consider when evaluating the scalability of a business model?", "expected_response": "When evaluating scalability, Y Combinator considers whether the business model allows for rapid growth and expansion in the market."}
+{"query": "What does Y Combinator consider when evaluating the scalability of a business model?", "expected_response": "When evaluating scalability, Y Combinator considers whether the business model allows for rapid growth and expansion in the market."}

evaluations/run_athina_evals.py

@@ -22,9 +22,21 @@ def load_data():
             "expected_response": "Y Combinator takes a 7% equity stake in companies in return for $125,000 on a post-money SAFE, and a 1.5% equity stake in companies participating in the YC Fellowship Program in exchange for a $20,000 investment.",
         }
     ]
-
-    for item in raw_data:
-        item['context'], item['response'] = app.generate_response(item['query'])
+
+    # # or read from file
+    # with open('evaluations/golden_dataset.jsonl', 'r') as file:
+    #     raw_data = file.read()
+    #     raw_data = raw_data.split('\n')
+    #     data = []
+    #     for item in raw_data:
+    #         item = json.loads(item)
+    #         item['context'], item['response'] = app.generate_response(item['query'])
+    #         data.append(item)
+    #     global dataset
+    #     dataset = RagLoader().load_dict(data)
+    #     pd.DataFrame(dataset)
+    # for item in raw_data:
+    #     item['context'], item['response'] = app.generate_response(item['query'])
 
     global dataset
     dataset = RagLoader().load_dict(raw_data)