Add sandbox dataset loaders (#155)

* Add loaders wip and removed prefetch model

* Tidy sandboxclient API and tests

* Consolidate url params and make synth gen more explicit

* Add synthea dataloader

* Add bundle counting helper

* Update cookbook usage

* Add error handling for empty responses

* Update tests

* Update docs

Author: jenniferjiangkells

cookbook/cds_discharge_summarizer_hf_chat.py

@@ -81,12 +81,11 @@ def start_api():
 
     # Create sandbox client and load test data
     client = SandboxClient(
-        api_url="http://localhost:8000",
-        endpoint="/cds/cds-services/discharge-summarizer",
+        url="http://localhost:8000/cds/cds-services/discharge-summarizer",
+        workflow="encounter-discharge",
     )
     # Load discharge notes from CSV
     client.load_free_text(
-        workflow="encounter-discharge",
         csv_path="data/discharge_notes.csv",
         column_name="text",
     )

cookbook/cds_discharge_summarizer_hf_trf.py

@@ -54,12 +54,11 @@ def start_api():
 
     # Create sandbox client and load test data
     client = SandboxClient(
-        api_url="http://localhost:8000",
-        endpoint="/cds/cds-services/discharge-summarizer",
+        url="http://localhost:8000/cds/cds-services/discharge-summarizer",
+        workflow="encounter-discharge",
     )
     # Load discharge notes from CSV
     client.load_free_text(
-        workflow="encounter-discharge",
         csv_path="data/discharge_notes.csv",
         column_name="text",
     )

cookbook/notereader_clinical_coding_fhir.py

@@ -132,7 +132,9 @@ def run_server():
 
     # Create sandbox client for testing
     client = SandboxClient(
-        api_url="http://localhost:8000", endpoint="/notereader/fhir/", protocol="soap"
+        url="http://localhost:8000/notereader/fhir/",
+        workflow="sign-note-inpatient",
+        protocol="soap",
     )
     # Load clinical document from file
     client.load_from_path("./data/notereader_cda.xml")

docs/cookbook/clinical_coding.md

@@ -224,8 +224,7 @@ from healthchain.sandbox import SandboxClient
 
 # Create sandbox client for SOAP/CDA testing
 client = SandboxClient(
-    api_url="http://localhost:8000",
-    endpoint="/notereader/ProcessDocument",
+    url="http://localhost:8000/notereader/ProcessDocument",
     workflow="sign-note-inpatient",
     protocol="soap"
 )

docs/cookbook/discharge_summarizer.md

@@ -159,16 +159,14 @@ from healthchain.sandbox import SandboxClient
 
 # Create sandbox client for testing
 client = SandboxClient(
-    api_url="http://localhost:8000",
-    endpoint="/cds/cds-services/discharge-summarizer",
+    url="http://localhost:8000/cds/cds-services/discharge-summarizer",
     workflow="encounter-discharge"
 )
 
 # Load discharge notes from CSV and generate FHIR data
 client.load_free_text(
     csv_path="data/discharge_notes.csv",
-    column_name="text",
-    workflow="encounter-discharge"
+    column_name="text"
 )
 ```
 

docs/quickstart.md

@@ -185,15 +185,19 @@ Test your AI applications in realistic healthcare contexts with `SandboxClient`
 ```python
 from healthchain.sandbox import SandboxClient
 
-# Create client and load test data
+# Create client with service URL and workflow
 client = SandboxClient(
-    api_url="http://localhost:8000",
-    endpoint="/cds/cds-services/my-service",
+    url="http://localhost:8000/cds/cds-services/my-service",
     workflow="encounter-discharge"
 )
 
 # Load from datasets or files
-client.load_from_registry("synthea", num_patients=5)
+client.load_from_registry(
+    "synthea-patient",
+    data_dir="./data/synthea",
+    resource_types=["Condition", "DocumentReference"],
+    sample_size=3
+)
 responses = client.send_requests()
 ```
 

docs/reference/utilities/data_generator.md

@@ -10,7 +10,7 @@ According to the [UK ONS synthetic data classification](https://www.ons.gov.uk/m
 
 ## CDS Data Generator
 
-The `.generate_prefetch()` method will return a `Prefetch` model with the `prefetch` field populated with a dictionary of FHIR resources. Each key in the dictionary corresponds to a FHIR resource type, and the value is a list of FHIR resources of that type. For more information, check out the [CDS Hooks documentation](https://cds-hooks.org/specification/current/#providing-fhir-resources-to-a-cds-service).
+The `.generate_prefetch()` method will return a dictionary of resources. Each key in the dictionary corresponds to a FHIR resource type, and the value is a list of FHIR resources or a Bundle of that type. For more information, check out the [CDS Hooks documentation](https://cds-hooks.org/specification/current/#providing-fhir-resources-to-a-cds-service).
 
 For each workflow, a pre-configured list of FHIR resources is randomly generated and placed in the `prefetch` field of a `CDSRequest`.
 
@@ -33,16 +33,14 @@ You can use the data generator with `SandboxClient.load_free_text()` or standalo
 
     # Create client
     client = SandboxClient(
-        api_url="http://localhost:8000",
-        endpoint="/cds/cds-services/my-service",
+        url="http://localhost:8000/cds/cds-services/my-service",
         workflow="encounter-discharge"
     )
 
     # Generate FHIR data from clinical notes
     client.load_free_text(
         csv_path="./data/discharge_notes.csv",
         column_name="text",
-        workflow="encounter-discharge",
         random_seed=42
     )