update Google Gemini model

CHANGELOG.md

@@ -10,6 +10,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+## [0.65.0]
+
+### Breaking
+- Changed the official ENV variable for MistralAI API from `MISTRALAI_API_KEY` to `MISTRAL_API_KEY` to be compatible with the Mistral docs.
+
+### Added
+- Added a new Gemini Experimental model from November 2024 (`gemini-exp-1121` with alias `gemexp`).
+
+### Updated
+- Changed the ENV variable for MistralAI API from `MISTRALAI_API_KEY` to `MISTRAL_API_KEY` to be compatible with the Mistral docs.
+
 ## [0.64.0]
 
 ### Added
@@ -618,13 +629,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.4.0]
 
-### Breaking
-- Changed the official ENV variable for MistralAI API from `MISTRALAI_API_KEY` to `MISTRAL_API_KEY` to be compatible with the Mistral docs.
-
 ### Added
 - Improved AICode parsing and error handling (eg, capture more REPL prompts, detect parsing errors earlier, parse more code fence types), including the option to remove unsafe code (eg, `Pkg.add("SomePkg")`) with `AICode(msg; skip_unsafe=true, vebose=true)`
 - Added new prompt templates: `JuliaRecapTask`, `JuliaRecapCoTTask`, `JuliaExpertTestCode` and updated `JuliaExpertCoTTask` to be more robust against early stopping for smaller OSS models
-- Added support for MistralAI API via the MistralOpenAISchema(). All their standard models have been registered, so you should be able to just use `model="mistral-tiny` in your `aigenerate` calls without any further changes. Remember to either provide `api_kwargs.api_key` or ensure you have ENV variable `MISTRAL_API_KEY` set.
+- Added support for MistralAI API via the MistralOpenAISchema(). All their standard models have been registered, so you should be able to just use `model="mistral-tiny` in your `aigenerate` calls without any further changes. Remember to either provide `api_kwargs.api_key` or ensure you have ENV variable `MISTRALAI_API_KEY` set. Note: This has been since changed to `MISTRAL_API_KEY` to be compatible with the Mistral docs, refer to the versions after v0.65.
 - Added support for any OpenAI-compatible API via `schema=CustomOpenAISchema()`. All you have to do is to provide your `api_key` and `url` (base URL of the API) in the `api_kwargs` keyword argument. This option is useful if you use [Perplexity.ai](https://docs.perplexity.ai/), [Fireworks.ai](https://app.fireworks.ai/), or any other similar services.
 
 ## [0.3.0]

Project.toml

@@ -1,7 +1,7 @@
 name = "PromptingTools"
 uuid = "670122d1-24a8-4d70-bfce-740807c42192"
 authors = ["J S @svilupp and contributors"]
-version = "0.64.0"
+version = "0.65.0"
 
 [deps]
 AbstractTrees = "1520ce14-60c1-5f80-bbc7-55ef81b5835c"

src/user_preferences.jl

@@ -190,8 +190,8 @@ function load_api_keys!()
     AZURE_OPENAI_HOST = @load_preference("AZURE_OPENAI_HOST",
         default=get(ENV, "AZURE_OPENAI_HOST", ""))
     global MISTRAL_API_KEY
-    MISTRAL_API_KEY = @load_preference("MISTRAL_API_KEY", 
-        default=get(ENV, "MISTRAL_API_KEY", 
+    MISTRAL_API_KEY = @load_preference("MISTRAL_API_KEY",
+        default=get(ENV, "MISTRAL_API_KEY",
             get(ENV, "MISTRALAI_API_KEY", "")))
     if !isempty(get(ENV, "MISTRALAI_API_KEY", ""))
         @warn "The MISTRALAI_API_KEY environment variable is deprecated. Use MISTRAL_API_KEY instead."
@@ -483,7 +483,7 @@ aliases = merge(
         "gem15p" => "gemini-1.5-pro-latest",
         "gem15f8" => "gemini-1.5-flash-8b-latest",
         "gem15f" => "gemini-1.5-flash-latest",
-        "gemexp" => "gemini-exp-1114" # latest experimental model from November 2024
+        "gemexp" => "gemini-exp-1121" # latest experimental model from November 2024
     ),
     ## Load aliases from preferences as well
     @load_preference("MODEL_ALIASES", default=Dict{String, String}()))
@@ -1130,6 +1130,11 @@ registry = Dict{String, ModelSpec}(
         3.0e-7,
         "Gemini 1.5 Flash is a high-performance model optimized for speed while maintaining strong capabilities across various tasks. 128K context window."),
     "gemini-exp-1114" => ModelSpec("gemini-exp-1114",
+        GoogleOpenAISchema(),
+        1.25e-6,
+        5e-6,
+        "Gemini Experimental Model from November 2024. Pricing assumed as per Gemini 1.5 Pro. See details [here](https://ai.google.dev/gemini-api/docs/models/experimental-models#use-an-experimental-model)."),
+    "gemini-exp-1121" => ModelSpec("gemini-exp-1121",
         GoogleOpenAISchema(),
         1.25e-6,
         5e-6,