Use Gemini 2.0 Flash by default.

.github/workflows/publish_site.yml

@@ -51,4 +51,4 @@ jobs:
       - name: Build and deploy the docs
         env:
           LLM_GEMINI_KEY: ${{ secrets.LLM_GEMINI_KEY }}
-        run: uv run repo-guide . --gh-deploy --no-serve -v --ignore=uv.lock --model=gemini-2.0-flash-exp --google-analytics-id=G-8S5FQCP6K4
+        run: uv run repo-guide . --gh-deploy --no-serve -v --ignore=uv.lock --google-analytics-id=G-8S5FQCP6K4

README.md

@@ -101,11 +101,11 @@ Here are some of the most common flags you may want to use:
 - `--output-dir`: Change where the generated docs are written.
 - `-v` or `--verbose`: Prints details on doc generation progress instead of a
   progress bar.
-- `--model`: Sets the LLM model to use. As of 1/1/2025, the default is Gemini
-  1.5 Flash, which costs under a dollar for 10 million tokens and has a 1
-  million token context window, making it a great fit. You can try other Gemini
-  models such as `gemini-2.0-flash-exp`, or OpenAI models if `OPENAI_API_KEY` is
-  set, as supported by [simonw/llm](https://github.com/simonw/llm) and
+- `--model`: Sets the LLM model to use. As of 2/5/2025, the default is Gemini
+  2.0 Flash, which costs a dollar for 10 million tokens and has a 1 million
+  token context window, making it a great fit. You can try other Gemini models,
+  or OpenAI models if `OPENAI_API_KEY` is set, as supported by
+  [simonw/llm](https://github.com/simonw/llm) and
   [simonw/llm-gemini](https://github.com/simonw/llm-gemini).
 - `--token-budget`: Sets an approximate token budget to avoid overspending.
   Tokens are counted after each LLM call, so the actual number may be higher.

pyproject.toml

@@ -13,7 +13,7 @@ dependencies = [
     "bleach>=6.2.0",
     "click",
     "gitpython>=3.1.43",
-    "llm-gemini>=0.5a0",
+    "llm-gemini>=0.10",
     "llm>=0.19a0",
     "mkdocs-material>=9.5.46",
     "mkdocs>=1.6.1",

src/repo_guide/cli.py

@@ -472,7 +472,7 @@ def on_page_content(html, **kwargs):
 )
 @click.option(
     "--model",
-    default="gemini-1.5-flash-latest",
+    default="gemini-2.0-flash",
     show_default=True,
     help="LLM model to use",
 )