v0.3.15

Highlights

• Four new templates: alz_treat, gene_extraction, storms, and onto_usage - see below for more details.
• The pubmed-extract and pubmed-annotate commands now allow setting the text segment size (in number of characters) with the max-text-length option. Many LLMs now allow for large contexts, so set this to 100000 or so to parse the full text of a scientific article (along with the --get-pmc option).
  • Example: ontogpt -vvv pubmed-annotate -t storms --get-pmc --model gpt-4o --limit 1 --max-text-length 100000 -o storms_test.yaml "36598999"

What's Changed

• Add template for alternate gene symbol extraction strategy by @caufieldjh in #390
• Template for Alzheimer's Disease extractions from literature; expose the max-text-length option for pubmed_annotate by @caufieldjh in #392
• Add ontology usage extraction template by @caufieldjh in #393
• Fixes #396 by @cmungall in #397
• Adding STORMS checklist by @cmungall in #395
• Bump version to 0.3.15 by @caufieldjh in #398

Full Changelog: v0.3.14...v0.3.15

v0.3.14

What's Changed

• Add custom template loader by @caufieldjh in #388
  • Custom templates in yaml may now be passed directly to ontogpt commands - no make needed.
• Updates for docs by @caufieldjh in #389

Full Changelog: v0.3.13...v0.3.14

v0.3.13

What's Changed

• Include only input-relevant named entities when producing output by @caufieldjh in #382
• More webapp updates - more models and all templates by @caufieldjh in #385
• Add notebook with two quick CLI and webapp examples by @caufieldjh in #386

Full Changelog: v0.3.12...v0.3.13

v0.3.12

What's Changed

• Part of a process for evaluating model performance in multi-language prompt situations.
  • Multilanguage gpt by @cmungall in #369
  • Started on command extract_case_report_info() by @justaddcoffee in #141
  • Ground multilingual to MONDO only by @caufieldjh in #372
• Much-needed updates for the demo webapp.
  • Updates for the webapp by @caufieldjh in #375
  • More fixes for the webapp by @caufieldjh in #377
• Add support for gpt-4o by @caufieldjh in #378
• Update options for embedding models by @caufieldjh in #380

Full Changelog: v0.3.11...v0.3.12

v0.3.11

What's Changed

• Add template suggestion command by @caufieldjh in #365
• Update default model for OpenAI to gpt-4-turbo by @caufieldjh in #366
• Documentation updates, mostly to the README

Full Changelog: v0.3.10...v0.3.11

v0.3.10

What's Changed

• Functions to parse YAML output to KGX-compliant CSV by @serenalotreck in #349
• Debug relation formatting in csv_wrapper by @serenalotreck in #354
• Make azure_settings import conditional on using the azure_select flag by @caufieldjh in #359
• Fixes for #355 - more parsing for KGX output by @caufieldjh in #360
• Expand the MAXO annotation extraction schema by @caufieldjh in #283

New Contributors

• @serenalotreck made their first contribution in #349

Full Changelog: v0.3.9...v0.3.10

v0.3.9

What's Changed

• Add new OpenAI model endpoints by @caufieldjh in #331
• Further updates to dietitian notes extraction schema by @caufieldjh in #335
• Add rdf to prefixes on templates to avoid extra warnings by @caufieldjh in #339
• Update citation metadata for repository by @caufieldjh in #341
• Further updates to dietitian notes schema to restructure nutritional support extraction by @caufieldjh in #342
• add azure openai api support to ontogpt by @k-bandi in #322
• Repair synonym and diagnose functions by @caufieldjh in #345
• General cleanup; bump version to 0.3.9 by @caufieldjh in #350

New Contributors

• @k-bandi made their first contribution in #322

Full Changelog: v0.3.8...v0.3.9

v0.3.8

Highlights

Try out ontogpt list-templates to see all the available extraction templates, including the new data_sheets_schema and updated clinical dietitian notes schema.

What's Changed

• Updates for dietitian notes extraction by @caufieldjh in #313
• Add data_sheets_schema template by @caufieldjh in #310
• Add further context to dietitian notes schema by @caufieldjh in #319
• Add list-templates command by @caufieldjh in #326
• Fix for errors on OWL write by @caufieldjh in #327
• Update prefixes defined in schemas by @caufieldjh in #328
• Version changes for v0.3.8 by @caufieldjh in #329

Full Changelog: v0.3.7...v0.3.8

v0.3.7

What's Changed

• Documentation updates by @caufieldjh in #302
• First draft of dietician notes extraction schema by @caufieldjh in #288
• Dentin dysplasia by @sierra-moxon in #187
• Testing figures template. by @balhoff in #171
• Start on kidney template by @justaddcoffee in #150
• Try extraction to nmdc-schema by @caufieldjh in #148
• Rebuild all templates by @caufieldjh in #303
• Enable running extractions on all files in a directory by @caufieldjh in #304
• Remove TALISMAN functions by @caufieldjh in #309
• Restructure SPIRESEngine to accomodate abstract model by @caufieldjh in #306

New Contributors

• @balhoff made their first contribution in #171

Full Changelog: v0.3.6...v0.3.7

v0.3.6

What's Changed

• Make introspection pydantic v2 compatible, fixes #294 by @cmungall in #295
• Add three simple extraction templates by @caufieldjh in #296
• Create draft template for extracting metadata to Datasheets by @caufieldjh in #231
• Use correct pydantic-version parameter with gen-pydantic by @caufieldjh in #299
• Dependency updates; bump version to 0.3.6 by @caufieldjh in #300

Full Changelog: v0.3.5...v0.3.6