llm-gemini 0.16__py3-none-any.whl → 0.18__py3-none-any.whl

{llm_gemini-0.16.dist-info → llm_gemini-0.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llm-gemini
-Version: 0.16
+Version: 0.18
 Summary: LLM plugin to access Google's Gemini family of models
 Author: Simon Willison
 License: Apache-2.0
@@ -57,9 +57,18 @@ llm -m gemini-2.0-flash "A short joke about a pelican and a walrus"
 >
 > The walrus sighs and says, "It's a long story. Let's just say we met through a mutual friend... of the fin."
 
+You can set the [default model](https://llm.datasette.io/en/stable/setup.html#setting-a-custom-default-model) to avoid the extra `-m` option:
+
+```bash
+llm models default gemini-2.0-flash
+llm "A joke about a pelican and a walrus"
+```
+
 Other models are:
 
-- `gemini-2.5-pro-exp-03-25` - experimental release of Gemini 2.5 Pro
+- `gemini-2.5-flash-preview-04-17` - Gemini 2.5 Flash preview
+- `gemini-2.5-pro-exp-03-25` - free experimental release of Gemini 2.5 Pro
+- `gemini-2.5-pro-preview-03-25` - paid preview of Gemini 2.5 Pro
 - `gemma-3-27b-it` - [Gemma 3](https://blog.google/technology/developers/gemma-3/) 27B
 - `gemini-2.0-pro-exp-02-05` - experimental release of Gemini 2.0 Pro
 - `gemini-2.0-flash-lite` - Gemini 2.0 Flash-Lite
@@ -79,23 +88,23 @@ Other models are:
 Gemini models are multi-modal. You can provide images, audio or video files as input like this:
 
 ```bash
-llm -m gemini-1.5-flash-latest 'extract text' -a image.jpg
+llm -m gemini-2.0-flash 'extract text' -a image.jpg
 ```
 Or with a URL:
 ```bash
-llm -m gemini-1.5-flash-8b-latest 'describe image' \
+llm -m gemini-2.0-flash-lite 'describe image' \
   -a https://static.simonwillison.net/static/2024/pelicans.jpg
 ```
 Audio works too:
 
 ```bash
-llm -m gemini-1.5-pro-latest 'transcribe audio' -a audio.mp3
+llm -m gemini-2.0-flash 'transcribe audio' -a audio.mp3
 ```
 
 And video:
 
 ```bash
-llm -m gemini-1.5-pro-latest 'describe what happens' -a video.mp4
+llm -m gemini-2.0-flash 'describe what happens' -a video.mp4
 ```
 The Gemini prompting guide includes [extensive advice](https://ai.google.dev/gemini-api/docs/file-prompting-strategies) on multi-modal prompting.
 
@@ -104,7 +113,7 @@ The Gemini prompting guide includes [extensive advice](https://ai.google.dev/gem
 Use `-o json_object 1` to force the output to be JSON:
 
 ```bash
-llm -m gemini-1.5-flash-latest -o json_object 1 \
+llm -m gemini-2.0-flash -o json_object 1 \
   '3 largest cities in California, list of {"name": "..."}'
 ```
 Outputs:
@@ -119,7 +128,7 @@ Gemini models can [write and execute code](https://ai.google.dev/gemini-api/docs
 To enable this feature, use `-o code_execution 1`:
 
 ```bash
-llm -m gemini-1.5-pro-latest -o code_execution 1 \
+llm -m gemini-2.0-flash -o code_execution 1 \
 'use python to calculate (factorial of 13) * 3'
 ```
 ### Google search
@@ -131,7 +140,7 @@ Using this feature may incur additional requirements in terms of how you use the
 To run a prompt with Google search enabled, use `-o google_search 1`:
 
 ```bash
-llm -m gemini-1.5-pro-latest -o google_search 1 \
+llm -m gemini-2.0-flash -o google_search 1 \
   'What happened in Ireland today?'
 ```
 
@@ -142,7 +151,7 @@ Use `llm logs -c --json` after running a prompt to see the full JSON response, w
 To chat interactively with the model, run `llm chat`:
 
 ```bash
-llm chat -m gemini-1.5-pro-latest
+llm chat -m gemini-2.0-flash
 ```
 
 ## Embeddings
@@ -205,4 +214,3 @@ You will need to have stored a valid Gemini API key using this command first:
 llm keys set gemini
 # Paste key here
 ```
-

llm_gemini-0.18.dist-info/RECORD

@@ -0,0 +1,7 @@
+llm_gemini.py,sha256=eoMPxKnWgEN3Li1HDsKIgKnXT5AL4stDhWc1MU6uIRE,17558
+llm_gemini-0.18.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+llm_gemini-0.18.dist-info/METADATA,sha256=X3NSwwbxo8TIAgyf3PA13WUzSWKTxXc38EhpD2VK_ds,8047
+llm_gemini-0.18.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+llm_gemini-0.18.dist-info/entry_points.txt,sha256=n544bpgUPIBc5l_cnwsTxPc3gMGJHPtAyqBNp-CkMWk,26
+llm_gemini-0.18.dist-info/top_level.txt,sha256=WUQmG6_2QKbT_8W4HH93qyKl_0SUteL4Ra6_PhyNGKU,11
+llm_gemini-0.18.dist-info/RECORD,,

{llm_gemini-0.16.dist-info → llm_gemini-0.18.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.0.2)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

llm_gemini.py

@@ -37,6 +37,9 @@ GOOGLE_SEARCH_MODELS = {
     "gemini-2.0-flash-exp",
     "gemini-2.0-flash",
 }
+THINKING_BUDGET_MODELS = {
+    "gemini-2.5-flash-preview-04-17",
+}
 
 
 @llm.hookimpl
@@ -68,17 +71,24 @@ def register_models(register):
         "gemma-3-27b-it",
         # 25th March 2025:
         "gemini-2.5-pro-exp-03-25",
+        # 4th April 2025 (paid):
+        "gemini-2.5-pro-preview-03-25",
+        # 17th April 2025:
+        "gemini-2.5-flash-preview-04-17",
     ]:
         can_google_search = model_id in GOOGLE_SEARCH_MODELS
+        can_thinking_budget = model_id in THINKING_BUDGET_MODELS
         register(
             GeminiPro(
                 model_id,
                 can_google_search=can_google_search,
+                can_thinking_budget=can_thinking_budget,
                 can_schema="flash-thinking" not in model_id,
             ),
             AsyncGeminiPro(
                 model_id,
                 can_google_search=can_google_search,
+                can_thinking_budget=can_thinking_budget,
                 can_schema="flash-thinking" not in model_id,
             ),
         )
@@ -206,12 +216,27 @@ class _SharedGemini:
             default=None,
         )
 
-    def __init__(self, model_id, can_google_search=False, can_schema=False):
+    class OptionsWithThinkingBudget(OptionsWithGoogleSearch):
+        thinking_budget: Optional[int] = Field(
+            description="Indicates the thinking budget in tokens. Set to 0 to disable.",
+            default=None,
+        )
+
+    def __init__(
+        self,
+        model_id,
+        can_google_search=False,
+        can_thinking_budget=False,
+        can_schema=False,
+    ):
         self.model_id = model_id
         self.can_google_search = can_google_search
         self.supports_schema = can_schema
         if can_google_search:
             self.Options = self.OptionsWithGoogleSearch
+        self.can_thinking_budget = can_thinking_budget
+        if can_thinking_budget:
+            self.Options = self.OptionsWithThinkingBudget
 
     def build_messages(self, prompt, conversation):
         messages = []
@@ -264,10 +289,18 @@ class _SharedGemini:
         if prompt.system:
             body["systemInstruction"] = {"parts": [{"text": prompt.system}]}
 
+        generation_config = {}
+
         if prompt.schema:
-            body["generationConfig"] = {
-                "response_mime_type": "application/json",
-                "response_schema": cleanup_schema(copy.deepcopy(prompt.schema)),
+            generation_config.update(
+                {
+                    "response_mime_type": "application/json",
+                    "response_schema": cleanup_schema(copy.deepcopy(prompt.schema)),
+                }
+            )
+        if self.can_thinking_budget and prompt.options.thinking_budget is not None:
+            generation_config["thinking_config"] = {
+                "thinking_budget": prompt.options.thinking_budget
             }
 
         config_map = {
@@ -277,16 +310,17 @@ class _SharedGemini:
             "top_k": "topK",
         }
         if prompt.options and prompt.options.json_object:
-            body["generationConfig"] = {"response_mime_type": "application/json"}
+            generation_config["response_mime_type"] = "application/json"
 
         if any(
             getattr(prompt.options, key, None) is not None for key in config_map.keys()
         ):
-            generation_config = {}
             for key, other_key in config_map.items():
                 config_value = getattr(prompt.options, key, None)
                 if config_value is not None:
                     generation_config[other_key] = config_value
+
+        if generation_config:
             body["generationConfig"] = generation_config
 
         return body

llm_gemini-0.16.dist-info/RECORD

@@ -1,7 +0,0 @@
-llm_gemini.py,sha256=GqrUhLIM3PxxrC3K6XNHy1cVcOCQfw44oL_36Cv7wug,16438
-llm_gemini-0.16.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-llm_gemini-0.16.dist-info/METADATA,sha256=MVM2mmBLB1QhBVYClxvhnLKP1URrVFmk-9EyzoaEo1c,7725
-llm_gemini-0.16.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
-llm_gemini-0.16.dist-info/entry_points.txt,sha256=n544bpgUPIBc5l_cnwsTxPc3gMGJHPtAyqBNp-CkMWk,26
-llm_gemini-0.16.dist-info/top_level.txt,sha256=WUQmG6_2QKbT_8W4HH93qyKl_0SUteL4Ra6_PhyNGKU,11
-llm_gemini-0.16.dist-info/RECORD,,