example: add example for BAML (#1256)

* example: add example for BAML

* chore: update `pyproject.toml` and `README`

* fix: `pyproject`

Author: georgeh0

README.md

@@ -202,6 +202,7 @@ It defines an index flow like this:
 | [Custom Output Files](examples/custom_output_files) | Convert markdown files to HTML files and save them to a local directory, using *CocoIndex Custom Targets* |
 | [Patient intake form extraction](examples/patient_intake_extraction) | Use LLM to extract structured data from patient intake forms with different formats |
 | [HackerNews Trending Topics](examples/hn_trending_topics) | Extract trending topics from HackerNews threads and comments, using *CocoIndex Custom Source* and LLM |
+| [Patient Intake Form Extraction with BAML](examples/patient_intake_extraction_baml) | Extract structured data from patient intake forms using BAML |
 
 More coming and stay tuned 👀!
 

examples/patient_intake_extraction_baml/.env.example

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

examples/patient_intake_extraction_baml/.gitignore

@@ -0,0 +1,20 @@
+# BAML generated files
+baml_client/
+.baml/
+
+# Environment files
+.env
+
+# Python
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.so
+*.egg-info/
+dist/
+build/
+
+# CocoIndex
+.cocoindex/

examples/patient_intake_extraction_baml/README.md

@@ -0,0 +1,53 @@
+# Extract structured data from patient intake forms with BAML
+
+[![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex)
+We appreciate a star ⭐ at [CocoIndex Github](https://github.com/cocoindex-io/cocoindex) if this is helpful.
+
+This example shows how to use [BAML](https://boundaryml.com/) to extract structured data from patient intake PDFs. BAML provides type-safe structured data extraction with native PDF support.
+
+- **BAML Schema** (`baml_src/patient.baml`) - Defines the data structure and extraction function
+- **CocoIndex Flow** (`main.py`) - Wraps BAML in a custom function, provide the flow to and process files incrementally.
+
+## Prerequisites
+
+1. [Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
+
+2. Install dependencies
+
+   ```sh
+   pip install -U cocoindex baml-py
+   ```
+
+3. **Generate BAML client code** (required step!)
+
+   ```sh
+   baml generate
+   ```
+
+   This generates the `baml_client/` directory with Python code to call your BAML functions.
+
+4. Create a `.env` file. You can copy it from `.env.example` first:
+
+   ```sh
+   cp .env.example .env
+   ```
+
+   Then edit the file to fill in your `GEMINI_API_KEY`.
+
+## Run
+
+Update index:
+
+```sh
+cocoindex update main
+```
+
+## CocoInsight
+
+I used CocoInsight (Free beta now) to troubleshoot the index generation and understand the data lineage of the pipeline. It just connects to your local CocoIndex server, with zero pipeline data retention. Run following command to start CocoInsight:
+
+```sh
+cocoindex server -ci main
+```
+
+Then open the CocoInsight UI at [https://cocoindex.io/cocoinsight](https://cocoindex.io/cocoinsight).

examples/patient_intake_extraction_baml/baml_src/generators.baml

@@ -0,0 +1,7 @@
+// BAML Generator Configuration
+
+generator python_client {
+  output_type python/pydantic
+  output_dir "../"
+  version "0.212.0"
+}

examples/patient_intake_extraction_baml/baml_src/patient.baml

@@ -0,0 +1,91 @@
+// BAML Schema for Patient Intake Form Extraction
+
+class Contact {
+  name string
+  phone string
+  relationship string
+}
+
+class Address {
+  street string
+  city string
+  state string
+  zip_code string
+}
+
+class Pharmacy {
+  name string
+  phone string
+  address Address
+}
+
+class Insurance {
+  provider string
+  policy_number string
+  group_number string?
+  policyholder_name string
+  relationship_to_patient string
+}
+
+class Condition {
+  name string
+  diagnosed bool
+}
+
+class Medication {
+  name string
+  dosage string
+}
+
+class Allergy {
+  name string
+}
+
+class Surgery {
+  name string
+  date string
+}
+
+class Patient {
+  name string
+  dob string
+  gender string
+  address Address
+  phone string
+  email string
+  preferred_contact_method string
+  emergency_contact Contact
+  insurance Insurance?
+  reason_for_visit string
+  symptoms_duration string
+  past_conditions Condition[]
+  current_medications Medication[]
+  allergies Allergy[]
+  surgeries Surgery[]
+  occupation string?
+  pharmacy Pharmacy?
+  consent_given bool
+  consent_date string?
+}
+
+function ExtractPatientInfo(intake_form: pdf) -> Patient {
+  client Gemini
+  prompt #"
+    Extract all patient information from the following intake form document.
+    Please be thorough and extract all available information accurately.
+
+    {{ intake_form }}
+
+    Fill in with "N/A" for required fields if the information is not available.
+
+    {{ ctx.output_format }}
+  "#
+}
+
+client<llm> Gemini {
+  provider google-ai
+  options {
+    model gemini-2.5-flash
+    api_key env.GEMINI_API_KEY
+  }
+}

examples/patient_intake_extraction_baml/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.
+