OpenAI Provider

pip install langextract[openai]

import langextract as lx
import os

result = lx.extract(
    text="Your document text",
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract key information",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False
)

import langextract as lx

# Recommended for most use cases
result = lx.extract(
    text="Your text",
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract information",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False
)

# For complex tasks requiring advanced reasoning
result = lx.extract(
    text="Your text",
    model_id="gpt-4o",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract complex relationships",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False
)

result = lx.extract(
    text="Your document",
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract entities",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False,
    # Provider-specific parameters:
    temperature=0.7,          # Sampling temperature (0.0-2.0)
    max_output_tokens=1000,  # Maximum tokens in response
    top_p=0.95,              # Nucleus sampling
)

from langextract.providers.openai import OpenAILanguageModel

model = OpenAILanguageModel(
    model_id="gpt-4o",
    api_key="your-key",
    temperature=0.7,
    max_workers=10,           # Parallel API calls
    base_url=None,            # Custom API endpoint (optional)
    organization=None         # OpenAI organization ID (optional)
)

result = lx.extract(
    text="Complex problem requiring reasoning",
    model_id="o1",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract and reason about entities",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False,
    reasoning_effort="high"  # or "medium", "low"
)

result = lx.extract(
    text="Your document",
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract structured data",
    examples=[...],
    format_type=lx.data.FormatType.JSON,  # Enables JSON mode automatically
    fence_output=True,
    use_schema_constraints=False
)

result = lx.extract(
    text="Your long document",
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract entities",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False,
    max_workers=20,           # Process up to 20 chunks in parallel
    max_chunk_size=3000      # Split document into 3000-char chunks
)

import langextract as lx
import os

# Define your task
prompt = "Extract person names, locations, and dates in order of appearance."

examples = [
    lx.data.ExampleData(
        text="Dr. Jane Smith visited Paris on March 15, 2024.",
        extractions=[
            lx.data.Extraction(
                extraction_class="person",
                extraction_text="Dr. Jane Smith",
                attributes={"title": "Dr."}
            ),
            lx.data.Extraction(
                extraction_class="location",
                extraction_text="Paris",
                attributes={"type": "city"}
            ),
            lx.data.Extraction(
                extraction_class="date",
                extraction_text="March 15, 2024",
                attributes={"format": "full date"}
            )
        ]
    )
]

# Run extraction
result = lx.extract(
    text="Prof. John Doe traveled to London on April 20, 2024.",
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description=prompt,
    examples=examples,
    fence_output=True,
    use_schema_constraints=False
)

print(f"Found {len(result.extractions)} extractions")
for ext in result.extractions:
    print(f"{ext.extraction_class}: {ext.extraction_text}")

import langextract as lx
import os

# Process a long document with optimal settings
result = lx.extract(
    text="https://example.com/long-document.txt",  # Or pass text directly
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    prompt_description="Extract all medication mentions",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False,
    # Chunking and parallelization:
    max_chunk_size=3000,      # Smaller chunks for accuracy
    max_workers=20,           # High parallelism for speed
    extraction_passes=3,      # Multiple passes for recall
    # Provider configuration:
    temperature=0.0,          # Deterministic output
    max_output_tokens=2000,   # Allow longer responses
)

from langextract.providers.openai import OpenAILanguageModel

model = OpenAILanguageModel(
    model_id="gpt-4o",
    api_key="your-key",
    base_url="https://your-azure-endpoint.openai.azure.com/",
    organization="your-org-id"  # Optional
)

# Use with lx.extract by passing the model instance
result = lx.extract(
    text="Your text",
    model=model,
    prompt_description="Extract data",
    examples=[...],
    fence_output=True,
    use_schema_constraints=False
)

import langextract as lx
from langextract.core.exceptions import InferenceConfigError, InferenceRuntimeError

try:
    result = lx.extract(
        text="Your text",
        model_id="gpt-4o-mini",
        api_key=os.environ.get('OPENAI_API_KEY'),
        prompt_description="Extract data",
        examples=[...],
        fence_output=True,
        use_schema_constraints=False
    )
except InferenceConfigError as e:
    # Configuration errors (missing API key, invalid parameters)
    print(f"Configuration error: {e}")
    if "OpenAI provider requires openai package" in str(e):
        print("Install with: pip install langextract[openai]")
except InferenceRuntimeError as e:
    # Runtime errors (API errors, rate limits, timeouts)
    print(f"Runtime error: {e}")

from langextract.providers.openai import OpenAILanguageModel
from langextract.core.types import ScoredOutput
import os

model = OpenAILanguageModel(
    model_id="gpt-4o-mini",
    api_key=os.environ.get('OPENAI_API_KEY'),
    temperature=0.7,
    max_workers=10
)

# Run inference on prompts
prompts = ["Extract entities from: ...", "Summarize: ..."]
for outputs in model.infer(prompts):
    for scored_output in outputs:
        print(f"Score: {scored_output.score}, Output: {scored_output.output}")