qubitclient-vqa-review

Files (1)

• SKILL.md

SKILL.md (first lines)

## API Reference

### Installation

```bash
# Install qubitclient
pip install qubitclient[full]
```

### Quick Start

```python
from qubitclient.llm import QubitLLM
from qubitclient.llm.task import LLMTaskName

# Initialize LLM client
llm = QubitLLM()

# Run a task with an image
result = llm.run(
    LLMTaskName.DESCRIBE_PLOT,
    image_data="path/to/image.png",
    experiment_family=ExperimentFamily.T1
)
```

### Client Initialization

```python
from qubitclient.llm import QubitLLM, ExperimentFamily
from qubitclient.llm.task import LLMTaskName
```

### LLM Task Names (LLMTaskName)

| Task | Description |
|------|-------------|
| `DESCRIBE_PLOT` | Q1 - Describe chart type, axes, range, and main features |
| `CLASSIFY_OUTCOME` | Q2 - Classify experiment result as Expected/Suboptimal/Anomalous/Apparatus issue |
| `SCIENTIFIC_REASONING` | Q3 - Analyze physical meaning and suggest next steps |
| `ASSESS_FIT` | Q4 - Evaluate if data fitting is reliable for parameter extraction |
| `EXTRACT_PARAMS` | Q5 - Extract specified parameters from the chart |
| `EVALUATE_STATUS` | Q6 - Determine experiment success/failure status |

### Experiment Families (ExperimentFamily)

Supported experiment families for task-specific prompts:

```python
ExperimentFamily.T1                    # T1 relaxation time
ExperimentFamily.T1_FLUCTUATIONS       # T1 fluctuations
ExperimentFamily.T2FIT                 # T2 coherence time (not in QCalEval)
ExperimentFamily.RAMI                  # (not in QCalEval)
ExperimentFamily.RAB                   # (not in QCalEval)
ExperimentFamily.COUPLER_FLUX          # Coupler flux experiment
ExperimentFamily.CZ_BENCHMARKING       # CZ gate benchmarking
ExperimentFamily.DRAG                  # DRAG pulse optimization
ExperimentFamily.GMM                   # Gaussian mixture model
ExperimentFamily.MICROWAVE_RAMSEY      # Microwave Ramsey
ExperimentFamily.MOT_LOADING           # MOT loading
ExperimentFamily.PINCHOFF              # Pinchoff experiment
ExperimentFamily.PINGPONG              # Ping-pong experiment
ExperimentFamily.QUBIT_FLUX_SPECTROSCOPY   # Qubit flux spectroscopy
ExperimentFamily.QUBIT_SPECTROSCOPY        # Qubit spectroscopy
ExperimentFamily.QUBIT_SPECTROSCOPY_POWER_FREQUENCY  # Power-frequency spectroscopy
ExperimentFamily.RABI                  # Rabi oscillation
ExperimentFamily.RABI_HW               # Rabi hardware
ExperimentFamily.RAMSEY_CHARGE_TOMOGRAPHY   # Ramsey charge tomography
ExperimentFamily.RAMSEY_FREQ_CAL       # Ramsey frequency calibration
ExperimentFamily.RAMSEY_T2STAR         # Ramsey T2*
ExperimentFamily.RES_SPEC              # Resonator spectroscopy
ExperimentFamily.RYDBERG_RAMSEY        # Rydberg Ramsey
ExperimentFamily.RYDBERG_SPECTROSCOPY  # Rydberg spectroscopy
ExperimentFamily.TWEEZER_ARRAY         # Tweezer array
```

### Running Tasks

#### Get Prompt Only (for custom execution)

```python
# Get prompt data without running
prompt_data = llm.get_prompt(
    LLMTaskName.DESCRIBE_PLOT,
    image_data="path/to/image.png",
    experiment_family=ExperimentFamily.T1
)
# Returns: {"messages": [...], "images": [...], "response_schema": {...}}

# Execute with your own client
result = llm.chat(**prompt_data)
```

#### Run Task Directly

```python
# Run task and get result directly
result = llm.run(
    LLMTaskName.DESCRIBE_PLOT,
    image_data="path/to/image.png",
    experiment_family=ExperimentFamily.T1
)
# Returns parsed JSON result
```

### Image Input Formats

```python
# Single image path
image_data = "path/to/image.png"

# Multiple images
image_data = ["path/to/img1.png", "path/to/img2.png"]

# Image bytes
with open("image.png", "rb") as f:
    image_data = f.read()
```

From yaqiangsun/QubitClient, MIT.

More from yaqiangsun/QubitClient