v0.2.1

What's Changed

• Add streaming feature with chat history by @izyuumi in #55
• Store chat history with stream update by @ushinnary in #56
• Llama3.1 Function Calling + New Tools by @andthattoo in #59
• Create images_to_ollama.rs by @heydocode in #63
• Update embeddings generation to /api/embed endpoint and allow for batch embedding by @pepperoni21 in #61
• Update readme to provide compilable embeddings examples by @ephraimkunz in #69
• feat: Added suffix in completion request by @SpeedCrash100 in #68
• Fixed GenerateEmbeddingsResponse float type by @pepperoni21 in #71

New Contributors

• @izyuumi made their first contribution in #55
• @heydocode made their first contribution in #63
• @ephraimkunz made their first contribution in #69
• @SpeedCrash100 made their first contribution in #68

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• Replace host string and port with Url by @zeozeozeo in #45
• Flatten final response data by @erhant in #47
• Examples folder should contain working versions of the current release by @yasinldev in #48
• Revert "Examples folder should contain working versions of the current release" by @pepperoni21 in #49
• Ollama Function Calling by @andthattoo in #51
• OllamaError for function-calling by @andthattoo in #54

New Contributors

• @erhant made their first contribution in #47
• @yasinldev made their first contribution in #48
• @andthattoo made their first contribution in #51

Full Changelog: v0.1.9...v0.2.0

v0.1.9

What's Changed

• Add Serialize Support for Further Stucts by @bencevans in #36
• fix: Adds back custom Result type for generate function by @jpmcb in #37
• update: update README streaming example by @milosgajdos in #39
• make ModelInfo fields empty by default by @zeozeozeo in #40
• make GenerationContext with pub field by @Vebnik in #43

New Contributors

• @bencevans made their first contribution in #36
• @jpmcb made their first contribution in #37
• @milosgajdos made their first contribution in #39
• @zeozeozeo made their first contribution in #40
• @Vebnik made their first contribution in #43

Full Changelog: v0.1.8...v0.1.9

v0.1.8

What's Changed

• feat: make GenerationOptions deserializable by @AlexisTM in #28
• feat: Add an example to show how to load GenerationOptions from a json string by @AlexisTM in #30
• Derive Eq, PartialEq on MessageRole by @Sir-Photch in #33
• Re-add Send for GenerationResponseStream by @functorism in #34
• feat: Store chat history by @ushinnary in #32

New Contributors

• @AlexisTM made their first contribution in #28
• @Sir-Photch made their first contribution in #33
• @ushinnary made their first contribution in #32

Full Changelog: v0.1.7...v0.1.8

v0.1.7

What's Changed

• Adds example on how to use completion options to README and /examples by @dezoito in #23
• Derives 'serialize' in GenerationResponse and GenerationFinalResponse by @dezoito in #25
• GenerationOptions 'stop' should be a string array, not string by @functorism in #26

New Contributors

• @dezoito made their first contribution in #23
• @functorism made their first contribution in #26

Full Changelog: v0.1.6...v0.1.7

v0.1.6

What's Changed

• Added the Send trait bound to all stream types by @varonroy in #14
• Fix return type for generate function by @SimonCW in #16
• Fix chatbot example link by @Rushmore75 in #18
• Fixed deserialization when streaming by @pepperoni21 in #13

New Contributors

• @varonroy made their first contribution in #14
• @SimonCW made their first contribution in #16
• @Rushmore75 made their first contribution in #18

Full Changelog: v0.1.5...v0.1.6

v0.1.5

Added image supports:

• images are represented with the Image struct which is a wrapper for the base64 encoding of the image
• using images and add_image methods of GenerationRequest
• using with_images and add_image methods of ChatMessage

v0.1.4

• Added chat endpoint support with send_chat_messages and send_chat_messages_stream methods (see https://github.com/pepperoni21/ollama-rs/blob/master/examples/chat_api_chatbot.rs)
• Fixed final data not being parsed in the GenerationResponse due to a change from Ollama

v0.1.3

• Added rustls support through the rustls feature

• create_model and create_model_stream methods now take a CreateModelRequest as the parameter, allowing to create a model by passing the content of the Modelfile as parameter.

  For example, this:

  ollama.create_model("model".into(), "/tmp/Modelfile.example".into())

  becomes:

  ollama.create_model(CreateModelRequest::path("model".into(), "/tmp/Modelfile.example".into()))

v0.1.2

• Fixed GenerateEmbeddingsResponse struct by making the embeddings field accessible