LlamaParse
Data & MLKnowledge Agents and Management in the Cloud
Release History
View all versions →llama-cloud-services-py@0.6.941 featureThis patch release includes an enhancement to include xlsx files in the extract input process.
llama_parse@0.6.941 featureThis patch release introduces the ability to include xlsx files in extract input and updates dependencies.
llama_parse@0.6.93This patch release primarily focuses on adding more warnings and updating dependencies, specifically llama-cloud-services-py to version 0.6.93.
llama-cloud-services-py@0.6.93This patch release primarily focuses on adding more warnings to the system.
llama-cloud-services-py@0.6.92This patch release primarily focuses on adding deprecation notices to the codebase.
llama-cloud-services@0.5.4This patch release primarily focused on adding deprecation notices to the codebase.
llama_parse@0.6.92This patch release primarily involved updating internal dependencies, specifically llama-cloud-services-py to version 0.6.92.
llama-cloud-services-py@0.6.911 fixThis patch release bumps patch versions for Python packages and improves error reporting for invalid extractions in ExtractedData.
llama_parse@0.6.91This patch release primarily focused on updating internal Python package dependencies, including bumping versions for several packages and specifically updating llama-cloud-services-py to v0.6.91.
llama-cloud-services-py@0.6.90This patch release primarily involved the removal of an extension filter.
llama_parse@0.6.901 fixThis patch release removes the extension filter and updates dependencies, specifically llama-cloud-services-py to version 0.6.90.
llama-cloud-services@0.5.31 fixThis patch release includes bug fixes specifically targeting the retry logic within LlamaExtract and LlamaClassify components.
llama-cloud-services@0.5.21 fixThis patch release introduces type annotations for bounding boxes, improving code clarity and maintainability.
llama_parse@0.6.89This patch release updates the llama-cloud-services-py dependency to version 0.6.89.
llama-cloud-services-py@0.6.891 fixThis patch release includes a bug fix related to parsing bounding boxes from extract job results in agent data.
llama-cloud-services@0.5.11 fixThis patch release primarily addresses an issue with publishing.
llama-cloud-services-py@0.6.881 featureThis patch release introduces the addition of tier and version information.
llama-cloud-services@0.4.31 featureThis patch release introduces the addition of tier and version information to the system.
llama_parse@0.6.88This patch release primarily updates internal dependencies, specifically upgrading llama-cloud-services-py to version 0.6.88.
llama_parse@0.6.87This patch release primarily updates internal dependencies, specifically upgrading llama-cloud-services-py to version 0.6.87.
llama-cloud-services-py@0.6.871 fixThis patch release includes an update to the spreadsheet parsing configuration.
llama_parse@0.6.861 featureThis patch release updates dependencies and enhances the extraction functionality to include confidence scores across all modes.
llama-cloud-services-py@0.6.861 featureThis patch update enhances the extraction functionality by ensuring confidence scores are accessible across all operational modes.
llama_parse@0.6.85This patch release primarily updates internal dependencies, specifically llama-cloud-services-py to version 0.6.85.
llama-cloud-services-py@0.6.851 featureThis patch release introduces support for line-level bounding boxes.
Common Errors
JobFailedException2 reportsJobFailedException in LlamaParse usually indicates an issue with the underlying parsing service, stemming from malformed input documents or service-side errors (like timeouts or model unavailability). To fix it, first ensure your input documents are valid and not excessively large, then try reducing parallelism or implementing retry logic with exponential backoff to handle potential transient service issues.
UnicodeDecodeError1 reportUnicodeDecodeError arises when Python tries to decode a byte sequence into a string using the wrong encoding. Specify the correct encoding (usually 'utf-8') when opening the file. For example, use `open(filename, 'r', encoding='utf-8')` or explicitly decode the bytes using `.decode('utf-8')`.
FileNotFoundError1 reportFileNotFoundError in LlamaParse usually arises when the specified file path in your code doesn't exist or is inaccessible. To fix this, double-check the file path for typos and ensure the file exists at that location; also, verify you have the necessary read permissions for the file. If you're using relative paths, ensure your script is running from the directory you expect it to be.
ValidationError1 reportValidationError in LlamaParse often arises when the data returned from the parsing job doesn't conform to the expected Pydantic model schema, commonly due to incorrect result_type or missing fields like 'pages' or 'job_metadata' for specific file types. To resolve this, ensure your result_type matches the actual file content (e.g., use "text" for text-based files), and verify that the parsing job provides all mandatory fields required by the JobResult schema for the specified result_type; adjust your processing or data extraction logic to create or populate these missing fields if necessary.
LlamaParserError1 reportLlamaParserError often arises from incorrect API key configuration or rate limiting issues when accessing the LlamaParse service. Ensure your `llamaparse_api_key` is correctly set in your environment or directly within your LlamaParse constructor, and verify you haven't exceeded your usage limits. Consider adding error handling with retry mechanisms to gracefully manage potential service disruptions.
Related Data & ML Packages
An Open Source Machine Learning Framework for Everyone
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
scikit-learn: machine learning in Python
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
Streamlit — A faster way to build and share data apps.
Subscribe to Updates
Get notified when new versions are released