patient intake structured extraction example (#680)

Author: badmonster0

examples/patient_intake_extraction/.env.example

@@ -0,0 +1,4 @@
+# Postgres database address for cocoindex
+COCOINDEX_DATABASE_URL=postgres://cocoindex:cocoindex@localhost/cocoindex
+
+OPENAI_API_KEY=

examples/patient_intake_extraction/README.md

@@ -0,0 +1,58 @@
+# Extract structured data from patient intake forms with LLM
+[![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex)
+
+
+This repo shows how to use OpenAI API to extract structured data from patient intake forms with different formats, like PDF, Docx, etc. from Google Drive. 
+
+We appreciate a star ⭐ at [CocoIndex Github](https://github.com/cocoindex-io/cocoindex) if this is helpful.
+
+![Structured Data From Patient Intake Forms](https://github.com/user-attachments/assets/1f6afb69-d26d-4a08-8774-13982d6aec1e)
+
+
+## Tutorials
+- Step by step tutorial - Check out the [blog](https://cocoindex.io/blogs/patient-intake-form-extraction-with-llm).
+- Video tutorial - [Youtube](https://youtu.be/_mjlwVtnBn0?si=cpH-4kkOAYm2HhK6).
+
+## Prerequisite
+1. [Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
+
+2. Install CocoIndex
+   ```bash
+   pip install -U cocoindex
+   ```
+
+3. Install MarkItDown
+   ```bash
+   pip install 'markitdown[all]'
+   ```
+4. Create a `.env` file from `.env.example`, and fill `OPENAI_API_KEY`.
+
+## Run
+
+Setup index:
+
+```bash
+cocoindex setup main.py
+```
+
+Update index:
+
+```bash
+cocoindex update main.py
+```
+
+Run query:
+
+```bash
+python main.py
+```
+
+Run with CocoInsight:
+```bash
+cocoindex server -ci main.py
+```
+<img width="1405" alt="Screenshot 2025-07-02 at 11 59 24 AM" src="https://github.com/user-attachments/assets/6f5154cd-8a53-4baa-b914-cd60ffecf3d4" />
+
+
+
+View results at https://cocoindex.io/cocoinsight

examples/patient_intake_extraction/data/README.md

@@ -0,0 +1,4 @@
+## Note:
+Example files here are purely artificial and not real, for testing purposes only.
+Please do not use these examples for any other purpose.
+

examples/patient_intake_extraction/data/patient_forms/Patient_Intake_Form_David_Artificial.docx

@@ -0,0 +1,130 @@
+import datetime
+import tempfile
+import dataclasses
+import os
+
+from markitdown import MarkItDown
+from openai import OpenAI
+
+import cocoindex
+
+@dataclasses.dataclass
+class Contact:
+    name: str
+    phone: str
+    relationship: str
+
+@dataclasses.dataclass
+class Address:
+    street: str
+    city: str
+    state: str
+    zip_code: str
+
+@dataclasses.dataclass
+class Pharmacy:
+    name: str
+    phone: str
+    address: Address
+
+@dataclasses.dataclass
+class Insurance:
+    provider: str
+    policy_number: str
+    group_number: str | None
+    policyholder_name: str
+    relationship_to_patient: str
+
+@dataclasses.dataclass
+class Condition:
+    name: str
+    diagnosed: bool
+
+@dataclasses.dataclass
+class Medication:
+    name: str
+    dosage: str
+
+@dataclasses.dataclass
+class Allergy:
+    name: str
+
+@dataclasses.dataclass
+class Surgery:
+    name: str
+    date: str
+
+@dataclasses.dataclass
+class Patient:
+    name: str
+    dob: datetime.date
+    gender: str
+    address: Address
+    phone: str
+    email: str
+    preferred_contact_method: str
+    emergency_contact: Contact
+    insurance: Insurance | None
+    reason_for_visit: str
+    symptoms_duration: str
+    past_conditions: list[Condition]
+    current_medications: list[Medication]
+    allergies: list[Allergy]
+    surgeries: list[Surgery]
+    occupation: str | None
+    pharmacy: Pharmacy | None
+    consent_given: bool
+    consent_date: datetime.date | None
+
+
+class ToMarkdown(cocoindex.op.FunctionSpec):
+    """Convert a document to markdown."""
+
+@cocoindex.op.executor_class(gpu=True, cache=True, behavior_version=1)
+class ToMarkdownExecutor:
+    """Executor for ToMarkdown."""
+
+    spec: ToMarkdown
+    _converter: MarkItDown
+
+    def prepare(self):
+        client = OpenAI()
+        self._converter = MarkItDown(llm_client=client, llm_model="gpt-4o")
+
+    def __call__(self, content: bytes, filename: str) -> str:
+        suffix = os.path.splitext(filename)[1]
+        with tempfile.NamedTemporaryFile(delete=True, suffix=suffix) as temp_file:
+            temp_file.write(content)
+            temp_file.flush()
+            text = self._converter.convert(temp_file.name).text_content
+            return text
+
+@cocoindex.flow_def(name="PatientIntakeExtraction")
+def patient_intake_extraction_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope):
+    """
+    Define a flow that extracts patient information from intake forms.
+    """
+    data_scope["documents"] = flow_builder.add_source(
+        cocoindex.sources.LocalFile(path="data/patient_forms", binary=True))
+
+    patients_index = data_scope.add_collector()
+
+    with data_scope["documents"].row() as doc:
+
+        doc["markdown"] = doc["content"].transform(ToMarkdown(), filename = doc["filename"])
+        doc["patient_info"] = doc["markdown"].transform(
+            cocoindex.functions.ExtractByLlm(
+                llm_spec=cocoindex.LlmSpec(
+                    api_type=cocoindex.LlmApiType.OPENAI, model="gpt-4o"),
+                output_type=Patient,
+                instruction="Please extract patient information from the intake form."))
+        patients_index.collect(
+            filename=doc["filename"],
+            patient_info=doc["patient_info"],
+        )
+
+    patients_index.export(
+        "patients",
+        cocoindex.storages.Postgres(table_name="patients_info"),
+        primary_key_fields=["filename"],
+    )

examples/patient_intake_extraction/data/patient_forms/Patient_Intake_Form_Emily_Artificial.pdf

@@ -0,0 +1,11 @@
+[project]
+name = "patient-intake-extraction"
+version = "0.1.0"
+description = "Extract structured information from patient intake forms using LLM."
+requires-python = ">=3.10"
+dependencies = [
+    "cocoindex>=0.1.45",
+    "python-dotenv>=1.0.1",
+    "markitdown>=0.1.2",
+    "openai>=1.68.2"
+]