add ability to find a particular evaluation by title or url

Author: Solveit

README.md

@@ -3,52 +3,50 @@
 
 <!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
 
-Why my `nbs/sidebar.yml` file is erased when running `nbdev_prepare`?
-
-Here is my settings.ini:
-
-![pasted_image_139aef0e-db47-4fc7-92b5-0d761129545c.png](index_files/figure-commonmark/37de56d3-1-139aef0e-db47-4fc7-92b5-0d761129545c.png)
-
-##### 🤖Reply🤖<!-- SOLVEIT_SEPARATOR_7f3a9b2c -->
-
-Looking at your `settings.ini`, I can see the issue. You have:
-
-    custom_sidebar = True
-
-When `custom_sidebar = True`, nbdev expects you to manually maintain
-your `sidebar.yml` and won’t overwrite it. However, if the file doesn’t
-exist or gets erased, nbdev might be regenerating it.
+[![PyPI](https://img.shields.io/pypi/v/evaluatr.png)](https://pypi.org/project/evaluatr/)
+[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue.png)](https://franckalbinet.github.io/evaluatr/)
 
-The problem is likely that you also have:
+## What is Evaluatr?
 
-    doc_host = https://francklabinet.github.io
-    doc_baseurl = /evaluatr/
+`Evaluatr` is an AI-powered system that automates mapping evaluation
+reports against structured frameworks while maintaining interpretability
+and human oversight. Initially developed for [IOM (International
+Organization for Migration)](https://www.iom.int) evaluation reports and
+the [Strategic Results Framework (SRF)](https://srf.iom.int), it
+transforms a traditionally manual, time-intensive process into an
+efficient, transparent workflow.
 
-But your repository structure might not match what nbdev expects. Try
-this:
+The system maps evaluation reports against hierarchical frameworks like
+the SRF (objectives, enablers, cross-cutting priorities, outcomes,
+outputs, indicators) and connects to broader frameworks like the
+[Sustainable Development Goals (SDGs)](https://sdgs.un.org) for
+interoperability.
 
-1.  Set `custom_sidebar = False` temporarily to let nbdev generate the
-    sidebar
-2.  Run `nbdev_prepare`
-3.  Once generated, modify the sidebar as needed
-4.  Then set `custom_sidebar = True` again
+Beyond automation, `Evaluatr` prioritizes **interpretability and
+human-AI collaboration**—enabling evaluators to understand the mapping
+process, audit AI decisions, perform error analysis, and build training
+datasets over time, ensuring the system aligns with organizational needs
+through actionable, transparent, auditable methodology.
 
-Alternatively, if you want to keep `custom_sidebar = True`, make sure
-your `nbs/sidebar.yml` file exists and has valid YAML content before
-running `nbdev_prepare`. Even a minimal valid structure like:
+## The Challenge We Solve
 
-``` yaml
-website:
-  sidebar:
-    contents:
-      - index.ipynb
-```
+IOM evaluators possess deep expertise in mapping evaluation reports
+against frameworks like the Strategic Results Framework (SRF), but face
+significant operational challenges when processing reports that often
+exceed 150 pages of diverse content across multiple projects and
+contexts.
 
-Would you like me to help you create a proper `sidebar.yml` structure?
+The core challenges are:
 
-[![PyPI](https://img.shields.io/pypi/v/evaluatr.png)](https://pypi.org/project/evaluatr/)
-[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
-[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue.png)](https://franckalbinet.github.io/evaluatr/)
+- **Time-intensive process**: Hundreds of staff-hours required per
+  comprehensive mapping exercise
+- **Individual consistency**: Even expert evaluators may categorize the
+  same content differently across sessions
+- **Cross-evaluator consistency**: Different evaluators may interpret
+  and map identical content to different framework outputs
+- **Scale vs. thoroughness**: Growing volume of evaluation reports
+  creates pressure to choose between speed and comprehensive analysis
 
 ## Understanding Evaluation Mapping in the UN Context
 
@@ -80,47 +78,6 @@ relevant reports) and recall (avoiding irrelevant ones).
 > Throughout this documentation, we use “mapping” and “tagging”
 > interchangeably.
 
-## The Challenge We Solve
-
-IOM evaluators possess deep expertise in mapping evaluation reports
-against frameworks like the Strategic Results Framework (SRF), but face
-significant operational challenges when processing reports that often
-exceed 150 pages of diverse content across multiple projects and
-contexts.
-
-The core challenges are:
-
-- **Time-intensive process**: Hundreds of staff-hours required per
-  comprehensive mapping exercise
-- **Individual consistency**: Even expert evaluators may categorize the
-  same content differently across sessions
-- **Cross-evaluator consistency**: Different evaluators may interpret
-  and map identical content to different framework outputs
-- **Scale vs. thoroughness**: Growing volume of evaluation reports
-  creates pressure to choose between speed and comprehensive analysis
-
-## What is Evaluatr?
-
-`Evaluatr` is an AI-powered system that automates mapping evaluation
-reports against structured frameworks while maintaining interpretability
-and human oversight. Initially developed for [IOM (International
-Organization for Migration)](https://www.iom.int) evaluation reports and
-the [Strategic Results Framework (SRF)](https://srf.iom.int), it
-transforms a traditionally manual, time-intensive process into an
-efficient, transparent workflow.
-
-The system maps evaluation reports against hierarchical frameworks like
-the SRF (objectives, enablers, cross-cutting priorities, outcomes,
-outputs, indicators) and connects to broader frameworks like the
-[Sustainable Development Goals (SDGs)](https://sdgs.un.org) for
-interoperability.
-
-Beyond automation, `Evaluatr` prioritizes **interpretability and
-human-AI collaboration**—enabling evaluators to understand the mapping
-process, audit AI decisions, perform error analysis, and build training
-datasets over time, ensuring the system aligns with organizational needs
-through actionable, transparent, auditable methodology.
-
 ## Key Features
 
 ### 1. Document Preparation Pipeline ✅ **Available**
@@ -210,7 +167,7 @@ model provider beyond the examples above.
 
 ## Quick Start
 
-### IOM Workflow (Programmatic)
+### Reading & standardizing evaluations repository
 
 For IOM evaluators working with the official evaluation repository,
 download the most recent evaluations from
@@ -231,9 +188,37 @@ evals[0]
 **Year:** 2025 \| **Organization:** IOM \| **Countries:** Worldwide
 
 **Documents:** 2 available  
-**ID:** `99923109...`
+**ID:** `9992310969aa2f428bc8aba29f865cf3`
+
+To find a particular evaluation by `title` or `url`:
+
+``` python
+from evaluatr.readers import find_eval
+
+title = 'Evaluation of IOM Accountability to Affected Populations'
+find_eval(evals, title, by='title')
+```
+
+### Evaluation of IOM Accountability to Affected Populations
+
+**Year:** 2025 \| **Organization:** IOM \| **Countries:** Worldwide
+
+**Documents:** 4 available  
+**ID:** `6c3c2cf3fa479112967612b0baddab72`
+
+``` python
+url = "https://evaluation.iom.int/sites/g/files/tmzbdl151/files/docs/resources/AAP%20Evaluation%20Report_final_.pdf"
+find_eval(evals, url, by='url')
+```
+
+### Evaluation of IOM Accountability to Affected Populations
+
+**Year:** 2025 \| **Organization:** IOM \| **Countries:** Worldwide
+
+**Documents:** 4 available  
+**ID:** `6c3c2cf3fa479112967612b0baddab72`
 
-**Downloading Evaluation Documents**
+### Downloading Evaluation Documents
 
 ``` python
 from evaluatr.downloaders import download_docs
@@ -244,7 +229,7 @@ base_dir = Path("files/test/pdf_library")
 download_docs(fname, base_dir=base_dir, n_workers=0, overwrite=True)
 ```
 
-### Universal CLI Workflow
+### Command Line Interface (CLI) Workflow
 
 Process any evaluation report from PDF to tagged outputs using three
 streamlined commands.