Add RAGAS initial version

agent/tools/ragasCall.ts

@@ -0,0 +1,22 @@
+import axios from "axios";
+
+export async function evaluateWithRagas({
+  question,
+  answer,
+  contexts,
+}: {
+  question: string;
+  answer: string;
+  contexts: string[];
+}) {
+  const res = await axios.post("http://localhost:8001/evaluate", {
+    question,
+    answer,
+    contexts,
+  });
+
+  return res.data;
+}
+
+// let res = await evaluateWithRagas({question: "Who was Bill Nye", answer: "Bill Nye was a Scientist", contexts: ["Bill nye was a Scientist"]});
+// console.log(res)

supporting/RAGAS_Service/.gitignore

@@ -0,0 +1,216 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

supporting/RAGAS_Service/ragas_service.py

@@ -0,0 +1,53 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from ragas import evaluate
+from ragas.metrics import faithfulness, answer_relevancy, context_precision
+from datasets import Dataset
+from pathlib import Path
+from dotenv import load_dotenv
+import os
+import math
+
+app = FastAPI()
+
+ENV_PATH = Path("../../agent/.env")
+
+load_dotenv(dotenv_path=ENV_PATH)
+
+def sanitize(obj):
+    if isinstance(obj, float) and math.isnan(obj):
+        return None
+    if isinstance(obj, dict):
+        return {k: sanitize(v) for k, v in obj.items()}
+    if isinstance(obj, list):
+        return [sanitize(v) for v in obj]
+    return obj
+
+if not os.getenv("OPENAI_API_KEY"):
+    raise RuntimeError("OPENAI_API_KEY not found")
+
+class EvalRequest(BaseModel):
+    question: str
+    answer: str
+    contexts: list[str]
+
+@app.post("/evaluate")
+def evaluate_rag(req: EvalRequest):
+    dataset = Dataset.from_dict({
+        "question": [req.question],
+        "answer": [req.answer],
+        "contexts": [req.contexts],
+        # "ground_truth": []
+    })
+
+    result = evaluate(
+        dataset,
+        metrics=[
+            faithfulness, 
+            answer_relevancy, 
+            context_precision
+        ],
+    )
+
+    raw = result.to_pandas().to_dict(orient="records")[0]
+    return sanitize(raw)

supporting/RAGAS_Service/requirements.txt

@@ -0,0 +1,19 @@
+# Web API
+fastapi
+uvicorn[standard]
+
+# RAGAS
+ragas
+datasets
+
+# LLM + embeddings
+openai
+tiktoken
+
+# Utils
+pydantic
+numpy
+pandas
+
+# Environment
+python-dotenv