v0.5.2 - File upload bugfix

Bug Fix

• Fix file uploads by @MarkDaoust in #291

New Features

• Support for new TaskTypes and output_dimensionality param by @mayureshagashe2105 in #285

Full Changelog: v0.5.1...v0.5.2

v0.5.1 - Add json mode

New features

• Add JSON mode by @shilpakancharla in #274

Docs and small fixes

• Fix: incorrect type checking by @Yeuoly in #283
• Fix an internal test failure by @markmcd in #279
• Allow incomplete GenerationConfigDict by @markmcd in #286
• Use generativelanguage v0.6.2 for json mode + update package version. by @MarkDaoust in #287

New Contributors

• @Yeuoly made their first contribution in #283

Full Changelog: v0.5.0...v0.5.1

v0.5.0 - Files

What's Changed

New features

• Files API

  You can now upload files to the api. Then instead of resending an image with each request, just pass a file reference in your prompt:

  f = genai.upload_file(path="image.png")
  m = genai.GenerativeModel(model_name=...)
  response = m.generate_content(["Please describe this file:", f])
  

  • Add initial prototype supporting the files API by @MarkDaoust in #249
  • Files API: improve error messages, add delete_file, add .uri property by @TYMichaelChen in #260

• Semantic retriever

  Using answer.generate_answer, you can now either pass "inline_passages" to include the reference material in the request:

  from google.generativeai import answer
  answer.generate_answer(
      content=question,
      inline_passages=splitter.split(document)
  )
  

  Or pass a reference to a retriever Document or Corpus:

  from google.generativeai import answer
  from google.generativeai import retriever
  my_corpus = retriever.get_corpus('my_corpus')
  genai.generate_answer(
      content=question,
      semantic_retreiver=my_corpus
  )
  

  • Finish Semantic Retriever. by @shilpakancharla in #230

• System instructions

  When creating a model you can pass a string (or Content) as system_instructions: genai.GenerativeModel(system_instructions="Be good!")

  • Add basic SI and tool_config support by @MarkDaoust in #257
  • Add system_instruction to model repr by @markmcd in #272

• Function Calling - Tool Config

  The list of tools available for function calling during a chat session is typically constant. The new tool_config argument lets you switch the function calling mode between None (No function calls), Auto (The model chooses to return text or a FunctionCall), and Any (the model must call a function).

  model = genai.GenerativeModel(tools=[my_functions])
  chat = model.start_chat()
  chat.send_message(tool_config={"function_calling_config": "ANY"})
  

  In Any mode the model will return a function call. You may also pass allowed_function_names to restrict the calls to a subset of the available functions: `chat.send_message(tool_config={"function_calling_config": "ANY", "allowed_function_names": [...]})

  In Any mode the model can use constrained decoding to more strictly follow the argument specifications in the function declarations.

  • Add basic SI and tool_config support by @MarkDaoust in #257
  • Function calling mode patch by @mayureshagashe2105 in #271

Docs, bug fixes, and minor updates.

• Update README.md by @aertoria in #256
• Fix incorrect reference to self.candidates[0].parts, self.candidates[0].parts[0].text by @Andy963 in #239
• Fix TypedDict usage for compatibility with PyDantic by @MarkDaoust in #259
• Simplify the Python SDK README by @random-forests in #267
• Sdk update to use glm 0.6.1 by @mayureshagashe2105 in #270

New Contributors

• @aertoria made their first contribution in #256
• @TYMichaelChen made their first contribution in #260
• @random-forests made their first contribution in #267

Full Changelog: v0.4.1...v0.5.0

v0.4.1 - Bugfix

Bugfix

• The send_message_async method should call the asynchronous method generate_content_async by @xnny in #229

Docs

• Fix wrong arg name in README by @lll-lll-lll-lll in #228

New Contributors

• @lll-lll-lll-lll made their first contribution in #228
• @xnny made their first contribution in #229

Full Changelog: v0.4.0...v0.4.1

v0.4.0 - Function calling, Semantic retriever, AQA, and more

What's new

Features

• Update notebook magics to work with Gemini by @markmcd in #109
• Semantic retriever by @shilpakancharla in #168
• Attributed question answering (genai.generate_answer) by @shilpakancharla in #169
• Automatic function calling. by @MarkDaoust in #201

   model = genai.GenerativeModel(..., tools=[my_function])
   chat = model.start_chat(enable_automatic_function_calling=True)
  

• Request options (timeouts, retry, ...) by @aidoskanapyanov in #204

  Model.generate_content(..., 
      request_options={'timeout': 100, 'retry': google.api_core.retry.Retry()})
  

• Permissions module by @mayureshagashe2105 in #205

More updates

• Lock google-auth version to fix #114 by @yihong0618 in #115
• Update code in README.md and generate_content documentation by @Hamza-nabil in #149
• Make error message more readable by @ftnext in #163
• Python 3.12 support. by @MarkDaoust in #165
• Rename model defaults to use gemini-pro by @markmcd in #175
• Add a more explicit error when no parts are returned by @markmcd in #180
• Add embed_content_async implementation by @mayureshagashe2105 in #189
• Link embed_content reference page to model details page by @kaycebasques in #194
• Implement __repr__ for GenerateContentResponse and ChatSession by @aidoskanapyanov in #202
• Fixed #166. Thanks @piresramon. by @MarkDaoust in #208

New Contributors

• @yihong0618 made their first contribution in #115
• @ftnext made their first contribution in #163
• @mayureshagashe2105 made their first contribution in #189
• @kaycebasques made their first contribution in #194
• @aidoskanapyanov made their first contribution in #202

Full Changelog: v0.3.2...v0.4.0

v0.3.2

What's Changed

Fix GenerativeModel.count_tokens.
Add basic function call support.
Fix async streaming with python 3.9.
Use typing_extensions for TypedDict.
Fix docs and error messages.

New Contributors

• @Andy963 made their first contribution in #123
• @luo-anthony made their first contribution in #132
• @thesanju made their first contribution in #131
• @mpursley made their first contribution in #129
• @Hamza-nabil made their first contribution in #140
• @YebowenHu made their first contribution in #116
• @eavanvalkenburg made their first contribution in #104

Full Changelog: v0.3.1...v0.3.2

v0.3.1 - Doc and Bug fixes.

Doc and Bug fixes.

v0.3.0 - Generate Content

Adds the Content family of methods to support Gemini models.

v0.2.2

• Handle maximum batch size for embed_text.
• Restore types.ModelNameOptions.
• Update tuning to handle more dataset types (json, pandas, urls, google-sheets).
• Expose count_text_tokens
• Expose operations management.
• Allow users to pass custom metadata (HTML headers).
• Add dataclass prettyprinting.

v0.2.1

• Bugfix: Add missing enum names to saftey_types.py
• Update to google.ai.generativelanguage v0.3.3
  • replace generativelanguage_v1beta3 with generativelanguage
    since that's the default in v0.3.3.