diff --git a/.github/workflows/test-sdk-typescript.yml b/.github/workflows/test-sdk-typescript.yml index 6af11d2..438f4bb 100644 --- a/.github/workflows/test-sdk-typescript.yml +++ b/.github/workflows/test-sdk-typescript.yml @@ -6,12 +6,12 @@ on: - main paths: - 'sdks/typescript/**' - - 'evals/prompts/**' + - 'evals/**/*.txt' - '.github/workflows/test-sdk-typescript.yml' pull_request: paths: - 'sdks/typescript/**' - - 'evals/prompts/**' + - 'evals/**/*.txt' - '.github/workflows/test-sdk-typescript.yml' jobs: diff --git a/.release-please-manifest.json b/.release-please-manifest.json index 4e6872f..eb91c10 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,4 +1,4 @@ { "sdks/typescript": "0.4.0", - "evals/prompts": "1.4.0" + "evals": "1.4.0" } diff --git a/README.md b/README.md index 24f000b..ef9f02e 100644 --- a/README.md +++ b/README.md @@ -45,8 +45,8 @@ To use the evaluators, clone the repository and follow the instructions below. If you’d like to download or access our evaluators and datasets directly, follow the links below. * Evaluators literacy package - * [Prompts](./evals/prompts) - * [Notebooks](./evals) + * [Qualitative Text Complexity](./evals/literacy/qualitative-text-complexity/) + * [Examples (Python notebooks)](./evals/literacy/qualitative-text-complexity/examples/) * Datasets * [Learning Commons annotations of CLEAR for qualitative text complexity v1.0 2025-09-02.csv](https://aidt-evaluators-files-public-prod.s3.us-west-2.amazonaws.com/Learning+Commons+annotations+of+CLEAR+for+qualitative+text+complexity+v1.0+2025-09-02.csv) @@ -82,7 +82,7 @@ Remember to activate the virtual environment for each new shell session when wor The required packages are listed in the `requirements.txt` file. ```shell -pip install -r evals/requirements.txt +pip install -r evals/utils/requirements.txt ``` ### 3. Set your API keys @@ -132,7 +132,7 @@ Remember to activate the virtual environment for each new shell session when wor ### 2. Install dependencies ```cmd -pip install -r evals/requirements.txt +pip install -r evals/utils/requirements.txt ``` ### 3. Set your API keys @@ -171,7 +171,7 @@ jupyter lab Jupyter will open in your web browser (usually at `http://localhost:8888`). -2. Browse into the `evals` folder, then double click on the evaluator you want to try. +2. Browse into `evals/literacy/qualitative-text-complexity/examples/`, then double click on the evaluator you want to try. 3. You can now copy the text you want to evaluate into the last code cell of the notebook to run an evaluator on your text sample. If you prefer using an IDE with Python and Jupyter notebook support, such as VSCode with Microsoft's Python and Jupyter extensions, please refer to Microsoft's instructions for their installation and configuration.) diff --git a/evals/prompts/CHANGELOG.md b/evals/CHANGELOG.md similarity index 94% rename from evals/prompts/CHANGELOG.md rename to evals/CHANGELOG.md index e387868..631a360 100644 --- a/evals/prompts/CHANGELOG.md +++ b/evals/CHANGELOG.md @@ -1,10 +1,18 @@ -# Prompts Changelog +# Evals Changelog All notable changes to the evaluator prompt files will be documented here. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). --- + +## [Unreleased] + +### Changed +- Reorganized package from `evals/prompts` into `evals` with domain-based folder structure + +--- + ## [1.4.0] - 2026-03-20 ### Added diff --git a/evals/README.md b/evals/README.md index db1d969..923b0c8 100644 --- a/evals/README.md +++ b/evals/README.md @@ -1,41 +1,14 @@ -## **Evaluators** Code and Prompts +## Evals -## **Requirements** +Evaluator prompt definitions organized by domain and category. -Please follow the detailed instructions in the top-level [README](../README.md) to set up your environment. +See the [Quickstart](../README.md#quickstart) in the root README for setup and running instructions. -## **Quick Start** +## Structure -Use the provided Makefile to quickly set up your environment and install dependencies with `make` tool. - -### Install dependencies - -```shell -make install -``` - -### Set your API keys - -Set `GOOGLE_API_KEY` and `OPENAI_API_KEY` in the environment variable in your shell session, or add to `.env` file. - -```shell -export GOOGLE_API_KEY="..." -export OPENAI_API_KEY="..." -``` - -### Run the Evaluator Code - -You are now ready to run the evaluator examples. We recommend using a Jupyter Notebook for interactive exploration. - -Start Jupyter Notebook: -```shell -make jupyter -``` - -Jupyter will open in your web browser (usually at http://localhost:8888). - -1. In Jupyter file browser, double click on the evaluator you want to try. -2. Copy the text you want to evaluate into the last code cell of the notebook to try the evaluation of your text sample. -3. Use the toolbar to run all cells, or run each cell in sequence until the end. - - _If you prefer using an IDE with Python and Jupyter notebook support, such as VSCode with Microsoft's Python and Jupyter extensions, please refer to Microsoft's instructions for their installation and configuration._ +| Path | Description | +| :--- | :--- | +| [`literacy/`](./literacy/) | Literacy evaluators | +| [`literacy/qualitative-text-complexity/`](./literacy/qualitative-text-complexity/) | Qualitative text complexity evaluators (GLA, Sentence Structure, Vocabulary, Conventionality, SMK) | +| [`math/`](./math/) | Math evaluators (coming soon) | +| [`utils/`](./utils/) | Setup scripts and dependencies | diff --git a/evals/__init__.py b/evals/__init__.py deleted file mode 100644 index 1d7f23f..0000000 --- a/evals/__init__.py +++ /dev/null @@ -1,3 +0,0 @@ -""" - Evaluators literacy package -""" \ No newline at end of file diff --git a/evals/prompts/README.md b/evals/literacy/qualitative-text-complexity/README.md similarity index 100% rename from evals/prompts/README.md rename to evals/literacy/qualitative-text-complexity/README.md diff --git a/evals/prompts/conventionality/system.txt b/evals/literacy/qualitative-text-complexity/conventionality/system.txt similarity index 100% rename from evals/prompts/conventionality/system.txt rename to evals/literacy/qualitative-text-complexity/conventionality/system.txt diff --git a/evals/prompts/conventionality/user.txt b/evals/literacy/qualitative-text-complexity/conventionality/user.txt similarity index 100% rename from evals/prompts/conventionality/user.txt rename to evals/literacy/qualitative-text-complexity/conventionality/user.txt diff --git a/evals/conventionality_evaluator.ipynb b/evals/literacy/qualitative-text-complexity/examples/conventionality_evaluator.ipynb similarity index 99% rename from evals/conventionality_evaluator.ipynb rename to evals/literacy/qualitative-text-complexity/examples/conventionality_evaluator.ipynb index 87b9b99..f77fed5 100644 --- a/evals/conventionality_evaluator.ipynb +++ b/evals/literacy/qualitative-text-complexity/examples/conventionality_evaluator.ipynb @@ -72,7 +72,7 @@ "metadata": {}, "outputs": [], "source": [ - "from prompts import conventionality_prompts as prompts\n", + "import conventionality_prompts as prompts\n", "\n", "# Set your api key in your environment, .env file, or enter when prompted.\n", "# os.environ['GOOGLE_API_KEY'] = 'YOUR API KEY'\n", diff --git a/evals/prompts/conventionality_prompts.py b/evals/literacy/qualitative-text-complexity/examples/conventionality_prompts.py similarity index 100% rename from evals/prompts/conventionality_prompts.py rename to evals/literacy/qualitative-text-complexity/examples/conventionality_prompts.py diff --git a/evals/prompts/gla_prompts.py b/evals/literacy/qualitative-text-complexity/examples/gla_prompts.py similarity index 100% rename from evals/prompts/gla_prompts.py rename to evals/literacy/qualitative-text-complexity/examples/gla_prompts.py diff --git a/evals/grade_level_evaluator.ipynb b/evals/literacy/qualitative-text-complexity/examples/grade_level_evaluator.ipynb similarity index 99% rename from evals/grade_level_evaluator.ipynb rename to evals/literacy/qualitative-text-complexity/examples/grade_level_evaluator.ipynb index f4faafd..54a969d 100644 --- a/evals/grade_level_evaluator.ipynb +++ b/evals/literacy/qualitative-text-complexity/examples/grade_level_evaluator.ipynb @@ -126,7 +126,7 @@ "outputs": [], "source": [ "#This is the system prompt, user prompt and model output setting. Do not change this\n", - "from prompts.gla_prompts import gla_system_prompt, gla_user_prompt\n", + "from gla_prompts import gla_system_prompt, gla_user_prompt\n", "\n", "class OutputRanges(BaseModel):\n", " reasoning: str = Field(description=\"your reasoning for your answer in numbered bullet points for 4 steps with a 5th bullet point for synthesis.\")\n", diff --git a/evals/prompts/sent_str_prompts.py b/evals/literacy/qualitative-text-complexity/examples/sent_str_prompts.py similarity index 100% rename from evals/prompts/sent_str_prompts.py rename to evals/literacy/qualitative-text-complexity/examples/sent_str_prompts.py diff --git a/evals/sentence_structure_evaluator.ipynb b/evals/literacy/qualitative-text-complexity/examples/sentence_structure_evaluator.ipynb similarity index 99% rename from evals/sentence_structure_evaluator.ipynb rename to evals/literacy/qualitative-text-complexity/examples/sentence_structure_evaluator.ipynb index 0ecbb2b..66e5f98 100644 --- a/evals/sentence_structure_evaluator.ipynb +++ b/evals/literacy/qualitative-text-complexity/examples/sentence_structure_evaluator.ipynb @@ -115,7 +115,7 @@ }, "outputs": [], "source": [ - "from prompts import sent_str_prompts as prompts\n", + "import sent_str_prompts as prompts\n", "\n", "# Set your api key in your environment, .env file, or enter when prompted.\n", "# os.environ['OPENAI_API_KEY'] = 'YOUR API KEY'\n", diff --git a/evals/smk_evaluator.ipynb b/evals/literacy/qualitative-text-complexity/examples/smk_evaluator.ipynb similarity index 99% rename from evals/smk_evaluator.ipynb rename to evals/literacy/qualitative-text-complexity/examples/smk_evaluator.ipynb index 994da3a..3109b8f 100644 --- a/evals/smk_evaluator.ipynb +++ b/evals/literacy/qualitative-text-complexity/examples/smk_evaluator.ipynb @@ -67,7 +67,7 @@ "metadata": {}, "outputs": [], "source": [ - "from prompts import smk_prompts as prompts\n", + "import smk_prompts as prompts\n", "\n", "# Set your api key in your environment, .env file, or enter when prompted.\n", "# os.environ['GOOGLE_API_KEY'] = 'YOUR API KEY'\n", diff --git a/evals/prompts/smk_prompts.py b/evals/literacy/qualitative-text-complexity/examples/smk_prompts.py similarity index 100% rename from evals/prompts/smk_prompts.py rename to evals/literacy/qualitative-text-complexity/examples/smk_prompts.py diff --git a/evals/text_complexity_combo.ipynb b/evals/literacy/qualitative-text-complexity/examples/text_complexity_combo.ipynb similarity index 99% rename from evals/text_complexity_combo.ipynb rename to evals/literacy/qualitative-text-complexity/examples/text_complexity_combo.ipynb index 7bf28dd..975f42e 100644 --- a/evals/text_complexity_combo.ipynb +++ b/evals/literacy/qualitative-text-complexity/examples/text_complexity_combo.ipynb @@ -127,7 +127,7 @@ }, "outputs": [], "source": [ - "from prompts import vocab_prompts as v_prompts, sent_str_prompts as s_prompts, smk_prompts as smk_prompts, conventionality_prompts as conv_prompts\n", + "import vocab_prompts as v_prompts, sent_str_prompts as s_prompts, smk_prompts as smk_prompts, conventionality_prompts as conv_prompts\n", "\n", "# Set your api keys in your environment, .env file, or enter when prompted.\n", "# os.environ['GOOGLE_API_KEY'] = 'YOUR API KEY'\n", diff --git a/evals/prompts/vocab_prompts.py b/evals/literacy/qualitative-text-complexity/examples/vocab_prompts.py similarity index 100% rename from evals/prompts/vocab_prompts.py rename to evals/literacy/qualitative-text-complexity/examples/vocab_prompts.py diff --git a/evals/vocabulary_evaluator.ipynb b/evals/literacy/qualitative-text-complexity/examples/vocabulary_evaluator.ipynb similarity index 99% rename from evals/vocabulary_evaluator.ipynb rename to evals/literacy/qualitative-text-complexity/examples/vocabulary_evaluator.ipynb index 892ecdf..c77e080 100644 --- a/evals/vocabulary_evaluator.ipynb +++ b/evals/literacy/qualitative-text-complexity/examples/vocabulary_evaluator.ipynb @@ -120,7 +120,7 @@ }, "outputs": [], "source": [ - "from prompts import vocab_prompts as prompts\n", + "import vocab_prompts as prompts\n", "\n", "# Set your api keys in your environment, .env file, or enter when prompted.\n", "# os.environ['GOOGLE_API_KEY'] = 'YOUR API KEY'\n", diff --git a/evals/prompts/grade-level-appropriateness/system.txt b/evals/literacy/qualitative-text-complexity/grade-level-appropriateness/system.txt similarity index 100% rename from evals/prompts/grade-level-appropriateness/system.txt rename to evals/literacy/qualitative-text-complexity/grade-level-appropriateness/system.txt diff --git a/evals/prompts/grade-level-appropriateness/user.txt b/evals/literacy/qualitative-text-complexity/grade-level-appropriateness/user.txt similarity index 100% rename from evals/prompts/grade-level-appropriateness/user.txt rename to evals/literacy/qualitative-text-complexity/grade-level-appropriateness/user.txt diff --git a/evals/prompts/sentence-structure/analysis-system.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/analysis-system.txt similarity index 100% rename from evals/prompts/sentence-structure/analysis-system.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/analysis-system.txt diff --git a/evals/prompts/sentence-structure/analysis-user.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/analysis-user.txt similarity index 100% rename from evals/prompts/sentence-structure/analysis-user.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/analysis-user.txt diff --git a/evals/prompts/sentence-structure/complexity-system.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/complexity-system.txt similarity index 100% rename from evals/prompts/sentence-structure/complexity-system.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/complexity-system.txt diff --git a/evals/prompts/sentence-structure/complexity-user.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/complexity-user.txt similarity index 100% rename from evals/prompts/sentence-structure/complexity-user.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/complexity-user.txt diff --git a/evals/prompts/sentence-structure/rubric-grade-3.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grade-3.txt similarity index 100% rename from evals/prompts/sentence-structure/rubric-grade-3.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grade-3.txt diff --git a/evals/prompts/sentence-structure/rubric-grade-4.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grade-4.txt similarity index 100% rename from evals/prompts/sentence-structure/rubric-grade-4.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grade-4.txt diff --git a/evals/prompts/sentence-structure/rubric-grades-5-12.txt b/evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grades-5-12.txt similarity index 100% rename from evals/prompts/sentence-structure/rubric-grades-5-12.txt rename to evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grades-5-12.txt diff --git a/evals/prompts/subject-matter-knowledge/system.txt b/evals/literacy/qualitative-text-complexity/subject-matter-knowledge/system.txt similarity index 100% rename from evals/prompts/subject-matter-knowledge/system.txt rename to evals/literacy/qualitative-text-complexity/subject-matter-knowledge/system.txt diff --git a/evals/prompts/subject-matter-knowledge/user.txt b/evals/literacy/qualitative-text-complexity/subject-matter-knowledge/user.txt similarity index 100% rename from evals/prompts/subject-matter-knowledge/user.txt rename to evals/literacy/qualitative-text-complexity/subject-matter-knowledge/user.txt diff --git a/evals/prompts/vocabulary/background-knowledge.txt b/evals/literacy/qualitative-text-complexity/vocabulary/background-knowledge.txt similarity index 100% rename from evals/prompts/vocabulary/background-knowledge.txt rename to evals/literacy/qualitative-text-complexity/vocabulary/background-knowledge.txt diff --git a/evals/prompts/vocabulary/grades-3-4-system.txt b/evals/literacy/qualitative-text-complexity/vocabulary/grades-3-4-system.txt similarity index 100% rename from evals/prompts/vocabulary/grades-3-4-system.txt rename to evals/literacy/qualitative-text-complexity/vocabulary/grades-3-4-system.txt diff --git a/evals/prompts/vocabulary/grades-3-4-user.txt b/evals/literacy/qualitative-text-complexity/vocabulary/grades-3-4-user.txt similarity index 100% rename from evals/prompts/vocabulary/grades-3-4-user.txt rename to evals/literacy/qualitative-text-complexity/vocabulary/grades-3-4-user.txt diff --git a/evals/prompts/vocabulary/other-grades-system.txt b/evals/literacy/qualitative-text-complexity/vocabulary/other-grades-system.txt similarity index 100% rename from evals/prompts/vocabulary/other-grades-system.txt rename to evals/literacy/qualitative-text-complexity/vocabulary/other-grades-system.txt diff --git a/evals/prompts/vocabulary/other-grades-user.txt b/evals/literacy/qualitative-text-complexity/vocabulary/other-grades-user.txt similarity index 100% rename from evals/prompts/vocabulary/other-grades-user.txt rename to evals/literacy/qualitative-text-complexity/vocabulary/other-grades-user.txt diff --git a/evals/math/README.md b/evals/math/README.md new file mode 100644 index 0000000..956e36f --- /dev/null +++ b/evals/math/README.md @@ -0,0 +1,3 @@ +# Math Evaluators + +Coming soon. diff --git a/evals/prompts/__init__.py b/evals/prompts/__init__.py deleted file mode 100644 index 7d83a19..0000000 --- a/evals/prompts/__init__.py +++ /dev/null @@ -1,3 +0,0 @@ -""" - Evaluators literacy package: Prompts -""" \ No newline at end of file diff --git a/evals/.env.example b/evals/utils/.env.example similarity index 100% rename from evals/.env.example rename to evals/utils/.env.example diff --git a/evals/Makefile b/evals/utils/Makefile similarity index 100% rename from evals/Makefile rename to evals/utils/Makefile diff --git a/evals/install.sh b/evals/utils/install.sh similarity index 100% rename from evals/install.sh rename to evals/utils/install.sh diff --git a/evals/requirements.txt b/evals/utils/requirements.txt similarity index 100% rename from evals/requirements.txt rename to evals/utils/requirements.txt diff --git a/evals/run.sh b/evals/utils/run.sh similarity index 100% rename from evals/run.sh rename to evals/utils/run.sh diff --git a/release-please-config.json b/release-please-config.json index 805cbb8..369d128 100644 --- a/release-please-config.json +++ b/release-please-config.json @@ -1,5 +1,6 @@ { "include-v-in-tag": true, + "last-release-sha": "b17cfb728723d27277fcc4a986d95c6189010cd4", "pull-request-title-pattern": "chore${scope}: release${component} ${version}", "changelog-sections": [ { @@ -54,10 +55,10 @@ "changelog-path": "CHANGELOG.md", "component": "sdks-typescript" }, - "evals/prompts": { + "evals": { "release-type": "simple", "changelog-path": "CHANGELOG.md", - "component": "evals-prompts" + "component": "evals" } } } diff --git a/sdks/typescript/src/prompts/conventionality/index.ts b/sdks/typescript/src/prompts/conventionality/index.ts index 71af2bb..14223f5 100644 --- a/sdks/typescript/src/prompts/conventionality/index.ts +++ b/sdks/typescript/src/prompts/conventionality/index.ts @@ -1,5 +1,5 @@ -import SYSTEM_PROMPT from '../../../../../evals/prompts/conventionality/system.txt'; -import USER_PROMPT_TEMPLATE from '../../../../../evals/prompts/conventionality/user.txt'; +import SYSTEM_PROMPT from '../../../../../evals/literacy/qualitative-text-complexity/conventionality/system.txt'; +import USER_PROMPT_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/conventionality/user.txt'; /** * Get the Conventionality evaluator system prompt diff --git a/sdks/typescript/src/prompts/grade-level-appropriateness/index.ts b/sdks/typescript/src/prompts/grade-level-appropriateness/index.ts index 4192b62..36c1161 100644 --- a/sdks/typescript/src/prompts/grade-level-appropriateness/index.ts +++ b/sdks/typescript/src/prompts/grade-level-appropriateness/index.ts @@ -1,5 +1,5 @@ -import SYSTEM_PROMPT_TEMPLATE from '../../../../../evals/prompts/grade-level-appropriateness/system.txt'; -import USER_PROMPT_TEMPLATE from '../../../../../evals/prompts/grade-level-appropriateness/user.txt'; +import SYSTEM_PROMPT_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/grade-level-appropriateness/system.txt'; +import USER_PROMPT_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/grade-level-appropriateness/user.txt'; /** * Get the system prompt for grade level appropriateness evaluation diff --git a/sdks/typescript/src/prompts/sentence-structure/analysis.ts b/sdks/typescript/src/prompts/sentence-structure/analysis.ts index f5e8c7f..0aa4e4e 100644 --- a/sdks/typescript/src/prompts/sentence-structure/analysis.ts +++ b/sdks/typescript/src/prompts/sentence-structure/analysis.ts @@ -1,5 +1,5 @@ -import SYSTEM_PROMPT_ANALYSIS_TEMPLATE from '../../../../../evals/prompts/sentence-structure/analysis-system.txt'; -import USER_PROMPT_ANALYSIS_TEMPLATE from '../../../../../evals/prompts/sentence-structure/analysis-user.txt'; +import SYSTEM_PROMPT_ANALYSIS_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/analysis-system.txt'; +import USER_PROMPT_ANALYSIS_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/analysis-user.txt'; /** * Get the system prompt for sentence grammatical analysis diff --git a/sdks/typescript/src/prompts/sentence-structure/complexity.ts b/sdks/typescript/src/prompts/sentence-structure/complexity.ts index fd90505..65119de 100644 --- a/sdks/typescript/src/prompts/sentence-structure/complexity.ts +++ b/sdks/typescript/src/prompts/sentence-structure/complexity.ts @@ -1,8 +1,8 @@ -import SYSTEM_PROMPT_COMPLEXITY_TEMPLATE from '../../../../../evals/prompts/sentence-structure/complexity-system.txt'; -import USER_PROMPT_COMPLEXITY_TEMPLATE from '../../../../../evals/prompts/sentence-structure/complexity-user.txt'; -import RUBRIC_GRADE_3 from '../../../../../evals/prompts/sentence-structure/rubric-grade-3.txt'; -import RUBRIC_GRADE_4 from '../../../../../evals/prompts/sentence-structure/rubric-grade-4.txt'; -import RUBRIC_GRADES_5_12 from '../../../../../evals/prompts/sentence-structure/rubric-grades-5-12.txt'; +import SYSTEM_PROMPT_COMPLEXITY_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/complexity-system.txt'; +import USER_PROMPT_COMPLEXITY_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/complexity-user.txt'; +import RUBRIC_GRADE_3 from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grade-3.txt'; +import RUBRIC_GRADE_4 from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grade-4.txt'; +import RUBRIC_GRADES_5_12 from '../../../../../evals/literacy/qualitative-text-complexity/sentence-structure/rubric-grades-5-12.txt'; /** * Get the system prompt for sentence structure complexity evaluation diff --git a/sdks/typescript/src/prompts/subject-matter-knowledge/index.ts b/sdks/typescript/src/prompts/subject-matter-knowledge/index.ts index 923d53a..c4b5bab 100644 --- a/sdks/typescript/src/prompts/subject-matter-knowledge/index.ts +++ b/sdks/typescript/src/prompts/subject-matter-knowledge/index.ts @@ -1,5 +1,5 @@ -import SYSTEM_PROMPT from '../../../../../evals/prompts/subject-matter-knowledge/system.txt'; -import USER_PROMPT_TEMPLATE from '../../../../../evals/prompts/subject-matter-knowledge/user.txt'; +import SYSTEM_PROMPT from '../../../../../evals/literacy/qualitative-text-complexity/subject-matter-knowledge/system.txt'; +import USER_PROMPT_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/subject-matter-knowledge/user.txt'; /** * Get the SMK evaluator system prompt diff --git a/sdks/typescript/src/prompts/vocabulary/background-knowledge.ts b/sdks/typescript/src/prompts/vocabulary/background-knowledge.ts index 52309f1..715af3c 100644 --- a/sdks/typescript/src/prompts/vocabulary/background-knowledge.ts +++ b/sdks/typescript/src/prompts/vocabulary/background-knowledge.ts @@ -1,4 +1,4 @@ -import BACKGROUND_KNOWLEDGE_TEMPLATE from '../../../../../evals/prompts/vocabulary/background-knowledge.txt'; +import BACKGROUND_KNOWLEDGE_TEMPLATE from '../../../../../evals/literacy/qualitative-text-complexity/vocabulary/background-knowledge.txt'; /** * Generate the background knowledge prompt for a given text and grade level diff --git a/sdks/typescript/src/prompts/vocabulary/system.ts b/sdks/typescript/src/prompts/vocabulary/system.ts index 81dde16..a92b10b 100644 --- a/sdks/typescript/src/prompts/vocabulary/system.ts +++ b/sdks/typescript/src/prompts/vocabulary/system.ts @@ -1,5 +1,5 @@ -import SYSTEM_PROMPT_GRADES_3_4 from '../../../../../evals/prompts/vocabulary/grades-3-4-system.txt'; -import SYSTEM_PROMPT_OTHER_GRADES from '../../../../../evals/prompts/vocabulary/other-grades-system.txt'; +import SYSTEM_PROMPT_GRADES_3_4 from '../../../../../evals/literacy/qualitative-text-complexity/vocabulary/grades-3-4-system.txt'; +import SYSTEM_PROMPT_OTHER_GRADES from '../../../../../evals/literacy/qualitative-text-complexity/vocabulary/other-grades-system.txt'; /** * Get the appropriate system prompt based on grade level diff --git a/sdks/typescript/src/prompts/vocabulary/user.ts b/sdks/typescript/src/prompts/vocabulary/user.ts index 75e56b0..786345a 100644 --- a/sdks/typescript/src/prompts/vocabulary/user.ts +++ b/sdks/typescript/src/prompts/vocabulary/user.ts @@ -1,5 +1,5 @@ -import USER_PROMPT_TEMPLATE_GRADES_3_4 from '../../../../../evals/prompts/vocabulary/grades-3-4-user.txt'; -import USER_PROMPT_TEMPLATE_OTHER_GRADES from '../../../../../evals/prompts/vocabulary/other-grades-user.txt'; +import USER_PROMPT_TEMPLATE_GRADES_3_4 from '../../../../../evals/literacy/qualitative-text-complexity/vocabulary/grades-3-4-user.txt'; +import USER_PROMPT_TEMPLATE_OTHER_GRADES from '../../../../../evals/literacy/qualitative-text-complexity/vocabulary/other-grades-user.txt'; /** * Generate the user prompt for vocabulary complexity evaluation diff --git a/sdks/typescript/tests/README.md b/sdks/typescript/tests/README.md index 0f06c3e..669c178 100644 --- a/sdks/typescript/tests/README.md +++ b/sdks/typescript/tests/README.md @@ -194,7 +194,7 @@ interface TestResult { ## Test Strategy ### Local Development -Tests run against `src/` with prompts copied from `../../evals/prompts/`: +Tests run against `src/` with prompts copied from `../../evals/literacy/qualitative-text-complexity/`: ```bash npm run test:unit npm run test:integration