gemini-webapi 1.8.4__tar.gz → 1.9.0__tar.gz

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gemini-webapi
-Version: 1.8.4
+Version: 1.9.0
 Summary: ✨ An elegant async Python wrapper for Google Gemini web app
 Author: UZQueen
 License:                     GNU AFFERO GENERAL PUBLIC LICENSE
@@ -725,14 +725,15 @@ A reverse-engineered asynchronous python wrapper for [Google Gemini](https://gem
 - [Authentication](#authentication)
 - [Usage](#usage)
   - [Initialization](#initialization)
+  - [Select language model](#select-language-model)
   - [Generate contents from text](#generate-contents-from-text)
   - [Generate contents from image](#generate-contents-from-image)
   - [Conversations across multiple turns](#conversations-across-multiple-turns)
   - [Continue previous conversations](#continue-previous-conversations)
+  - [Retrieve model's thought process](#retrieve-models-thought-process)
   - [Retrieve images in response](#retrieve-images-in-response)
   - [Generate images with ImageFx](#generate-images-with-imagefx)
   - [Save images to local files](#save-images-to-local-files)
-  - [Specify language model version](#specify-language-model-version)
   - [Generate contents with Gemini extensions](#generate-contents-with-gemini-extensions)
   - [Check and switch to other reply candidates](#check-and-switch-to-other-reply-candidates)
   - [Control log level](#control-log-level)
@@ -815,6 +816,41 @@ asyncio.run(main())
 >
 > `auto_close` and `close_delay` are optional arguments for automatically closing the client after a certain period of inactivity. This feature is disabled by default. In an always-on service like chatbot, it's recommended to set `auto_close` to `True` combined with reasonable seconds of `close_delay` for better resource management.
 
+### Select language model
+
+You can specify which language model to use by passing `model` argument to `GeminiClient.generate_content` or `GeminiClient.start_chat`. The default value is `unspecified`.
+
+Currently available models (as of Feb 5, 2025):
+
+- `unspecified` - Default model (same as `gemini-2.0-flash` if account does NOT have Gemini Advanced subscription)
+- `gemini-2.0-flash` - Gemini 2.0 Flash
+- `gemini-2.0-flash-thinking` - Gemini 2.0 Flash Thinking Experimental
+- `gemini-2.0-flash-thinking-with-apps` - Gemini 2.0 Flash Thinking Experimental with apps
+- `gemini-1.5-flash` - Gemini 1.5 Flash
+
+Models pending update (may not work as expected):
+
+- `gemini-2.0-exp-advanced` - Gemini 2.0 Experimental Advanced **(requires Gemini Advanced account)**
+- `gemini-1.5-pro` - Gemini 1.5 Pro **(requires Gemini Advanced account)**
+- `gemini-1.5-pro-research` - Gemini 1.5 Pro with Deep Research **(requires Gemini Advanced account)**
+
+```python
+from gemini_webapi.constants import Model
+
+async def main():
+    response1 = await client.generate_content(
+        "What's you language model version? Reply version number only.",
+        model=Model.G_2_0_FLASH,
+    )
+    print(f"Model version ({Model.G_2_0_FLASH.model_name}): {response1.text}")
+
+    chat = client.start_chat(model="gemini-2.0-flash-thinking")
+    response2 = await chat.send_message("What's you language model version? Reply version number only.")
+    print(f"Model version (gemini-2.0-flash-thinking): {response2.text}")
+
+asyncio.run(main())
+```
+
 ### Generate contents from text
 
 Ask a one-turn quick question by calling `GeminiClient.generate_content`.
@@ -885,6 +921,21 @@ async def main():
 asyncio.run(main())
 ```
 
+### Retrieve model's thought process
+
+When using models with thinking capabilities, the model's thought process will be populated in `ModelOutput.thoughts`.
+
+```python
+async def main():
+    response = await client.generate_content(
+            "What's 1+1?", model="gemini-2.0-flash-thinking"
+        )
+    print(response.thoughts)
+    print(response.text)
+
+asyncio.run(main())
+```
+
 ### Retrieve images in response
 
 Images in the API's output are stored as a list of `Image` objects. You can access the image title, URL, and description by calling `image.title`, `image.url` and `image.alt` respectively.
@@ -938,36 +989,6 @@ async def main():
 asyncio.run(main())
 ```
 
-### Specify language model version
-
-You can choose a specified language model version by passing `model` argument to `GeminiClient.generate_content` or `GeminiClient.start_chat`. The default value is `unspecified`.
-
-Currently available models (as of Feb 1, 2025):
-
-- `unspecified` - Default model (Gemini 2.0 Flash if account does NOT have Gemini Advanced subscription)
-- `gemini-1.5-flash` - Gemini 1.5 Flash
-- `gemini-1.5-pro` - Gemini 1.5 Pro **(requires Gemini Advanced account)**
-- `gemini-1.5-pro-research` - Gemini 1.5 Pro with Deep Research **(requires Gemini Advanced account)**
-- `gemini-2.0-flash-exp` - Gemini 2.0 Flash Experimental
-- `gemini-2.0-exp-advanced` - Gemini 2.0 Experimental Advanced **(requires Gemini Advanced account)**
-
-```python
-from gemini_webapi.constants import Model
-
-async def main():
-    response1 = await client.generate_content(
-        "What's you language model version? Reply version number only.",
-        model="gemini-1.5-flash",
-    )
-    print(f"Model version (gemini-1.5-flash): {response1.text}")
-
-    chat = client.start_chat(model=Model.G_2_0_FLASH_EXP)
-    response2 = await chat.send_message("What's you language model version? Reply version number only.")
-    print(f"Model version ({Model.G_2_0_FLASH_EXP.model_name}): {response2.text}")
-
-asyncio.run(main())
-```
-
 ### Generate contents with Gemini extensions
 
 > [!IMPORTANT]

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/README.md

@@ -43,14 +43,15 @@ A reverse-engineered asynchronous python wrapper for [Google Gemini](https://gem
 - [Authentication](#authentication)
 - [Usage](#usage)
   - [Initialization](#initialization)
+  - [Select language model](#select-language-model)
   - [Generate contents from text](#generate-contents-from-text)
   - [Generate contents from image](#generate-contents-from-image)
   - [Conversations across multiple turns](#conversations-across-multiple-turns)
   - [Continue previous conversations](#continue-previous-conversations)
+  - [Retrieve model's thought process](#retrieve-models-thought-process)
   - [Retrieve images in response](#retrieve-images-in-response)
   - [Generate images with ImageFx](#generate-images-with-imagefx)
   - [Save images to local files](#save-images-to-local-files)
-  - [Specify language model version](#specify-language-model-version)
   - [Generate contents with Gemini extensions](#generate-contents-with-gemini-extensions)
   - [Check and switch to other reply candidates](#check-and-switch-to-other-reply-candidates)
   - [Control log level](#control-log-level)
@@ -133,6 +134,41 @@ asyncio.run(main())
 >
 > `auto_close` and `close_delay` are optional arguments for automatically closing the client after a certain period of inactivity. This feature is disabled by default. In an always-on service like chatbot, it's recommended to set `auto_close` to `True` combined with reasonable seconds of `close_delay` for better resource management.
 
+### Select language model
+
+You can specify which language model to use by passing `model` argument to `GeminiClient.generate_content` or `GeminiClient.start_chat`. The default value is `unspecified`.
+
+Currently available models (as of Feb 5, 2025):
+
+- `unspecified` - Default model (same as `gemini-2.0-flash` if account does NOT have Gemini Advanced subscription)
+- `gemini-2.0-flash` - Gemini 2.0 Flash
+- `gemini-2.0-flash-thinking` - Gemini 2.0 Flash Thinking Experimental
+- `gemini-2.0-flash-thinking-with-apps` - Gemini 2.0 Flash Thinking Experimental with apps
+- `gemini-1.5-flash` - Gemini 1.5 Flash
+
+Models pending update (may not work as expected):
+
+- `gemini-2.0-exp-advanced` - Gemini 2.0 Experimental Advanced **(requires Gemini Advanced account)**
+- `gemini-1.5-pro` - Gemini 1.5 Pro **(requires Gemini Advanced account)**
+- `gemini-1.5-pro-research` - Gemini 1.5 Pro with Deep Research **(requires Gemini Advanced account)**
+
+```python
+from gemini_webapi.constants import Model
+
+async def main():
+    response1 = await client.generate_content(
+        "What's you language model version? Reply version number only.",
+        model=Model.G_2_0_FLASH,
+    )
+    print(f"Model version ({Model.G_2_0_FLASH.model_name}): {response1.text}")
+
+    chat = client.start_chat(model="gemini-2.0-flash-thinking")
+    response2 = await chat.send_message("What's you language model version? Reply version number only.")
+    print(f"Model version (gemini-2.0-flash-thinking): {response2.text}")
+
+asyncio.run(main())
+```
+
 ### Generate contents from text
 
 Ask a one-turn quick question by calling `GeminiClient.generate_content`.
@@ -203,6 +239,21 @@ async def main():
 asyncio.run(main())
 ```
 
+### Retrieve model's thought process
+
+When using models with thinking capabilities, the model's thought process will be populated in `ModelOutput.thoughts`.
+
+```python
+async def main():
+    response = await client.generate_content(
+            "What's 1+1?", model="gemini-2.0-flash-thinking"
+        )
+    print(response.thoughts)
+    print(response.text)
+
+asyncio.run(main())
+```
+
 ### Retrieve images in response
 
 Images in the API's output are stored as a list of `Image` objects. You can access the image title, URL, and description by calling `image.title`, `image.url` and `image.alt` respectively.
@@ -256,36 +307,6 @@ async def main():
 asyncio.run(main())
 ```
 
-### Specify language model version
-
-You can choose a specified language model version by passing `model` argument to `GeminiClient.generate_content` or `GeminiClient.start_chat`. The default value is `unspecified`.
-
-Currently available models (as of Feb 1, 2025):
-
-- `unspecified` - Default model (Gemini 2.0 Flash if account does NOT have Gemini Advanced subscription)
-- `gemini-1.5-flash` - Gemini 1.5 Flash
-- `gemini-1.5-pro` - Gemini 1.5 Pro **(requires Gemini Advanced account)**
-- `gemini-1.5-pro-research` - Gemini 1.5 Pro with Deep Research **(requires Gemini Advanced account)**
-- `gemini-2.0-flash-exp` - Gemini 2.0 Flash Experimental
-- `gemini-2.0-exp-advanced` - Gemini 2.0 Experimental Advanced **(requires Gemini Advanced account)**
-
-```python
-from gemini_webapi.constants import Model
-
-async def main():
-    response1 = await client.generate_content(
-        "What's you language model version? Reply version number only.",
-        model="gemini-1.5-flash",
-    )
-    print(f"Model version (gemini-1.5-flash): {response1.text}")
-
-    chat = client.start_chat(model=Model.G_2_0_FLASH_EXP)
-    response2 = await chat.send_message("What's you language model version? Reply version number only.")
-    print(f"Model version ({Model.G_2_0_FLASH_EXP.model_name}): {response2.text}")
-
-asyncio.run(main())
-```
-
 ### Generate contents with Gemini extensions
 
 > [!IMPORTANT]

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/src/gemini_webapi/client.py

@@ -364,6 +364,10 @@ class GeminiClient:
                 # Plain request
                 body = json.loads(response_json[0][2])
 
+                if not body[4]:
+                    # Request with thinking models
+                    body = json.loads(response_json[1][2])
+
                 if not body[4]:
                     # Request with Gemini extensions enabled
                     body = json.loads(response_json[4][2])
@@ -386,6 +390,11 @@ class GeminiClient:
                     ):
                         text = candidate[22] and candidate[22][0] or text
 
+                    try:
+                        thoughts = candidate[37][0][0]
+                    except (TypeError, IndexError):
+                        thoughts = None
+
                     web_images = (
                         candidate[12]
                         and candidate[12][1]
@@ -435,6 +444,7 @@ class GeminiClient:
                         Candidate(
                             rcid=candidate[0],
                             text=text,
+                            thoughts=thoughts,
                             web_images=web_images,
                             generated_images=generated_images,
                         )

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/src/gemini_webapi/constants.py

@@ -25,6 +25,31 @@ class Headers(Enum):
 
 class Model(Enum):
     UNSPECIFIED = ("unspecified", {}, False)
+    G_2_0_FLASH = (
+        "gemini-2.0-flash",
+        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"f299729663a2343f"]'},
+        False,
+    )
+    G_2_0_FLASH_EXP = (
+        "gemini-2.0-flash-exp",
+        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"f299729663a2343f"]'},
+        False,
+    )  # Deprecated, should be removed in the future
+    G_2_0_FLASH_THINKING = (
+        "gemini-2.0-flash-thinking",
+        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"9c17b1863f581b8a"]'},
+        False,
+    )
+    G_2_0_FLASH_THINKING_WITH_APPS = (
+        "gemini-2.0-flash-thinking-with-apps",
+        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"f8f8f5ea629f5d37"]'},
+        False,
+    )
+    G_2_0_EXP_ADVANCED = (
+        "gemini-2.0-exp-advanced",
+        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"b1e46a6037e6aa9f"]'},
+        True,
+    )
     G_1_5_FLASH = (
         "gemini-1.5-flash",
         {"x-goog-ext-525001261-jspb": '[null,null,null,null,"418ab5ea040b5c43"]'},
@@ -40,16 +65,6 @@ class Model(Enum):
         {"x-goog-ext-525001261-jspb": '[null,null,null,null,"e5a44cb1dae2b489"]'},
         True,
     )
-    G_2_0_FLASH_EXP = (
-        "gemini-2.0-flash-exp",
-        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"f299729663a2343f"]'},
-        False,
-    )
-    G_2_0_EXP_ADVANCED = (
-        "gemini-2.0-exp-advanced",
-        {"x-goog-ext-525001261-jspb": '[null,null,null,null,"b1e46a6037e6aa9f"]'},
-        True,
-    )
 
     def __init__(self, name, header, advanced_only):
         self.model_name = name

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/src/gemini_webapi/types/candidate.py

@@ -13,6 +13,8 @@ class Candidate(BaseModel):
         Reply candidate ID to build the metadata
     text: `str`
         Text output
+    thoughts: `str`, optional
+        Model's thought process, can be empty. Only populated with `-thinking` models
     web_images: `list[WebImage]`, optional
         List of web images in reply, can be empty.
     generated_images: `list[GeneratedImage]`, optional
@@ -21,6 +23,7 @@ class Candidate(BaseModel):
 
     rcid: str
     text: str
+    thoughts: str | None = None
     web_images: list[WebImage] = []
     generated_images: list[GeneratedImage] = []
 

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/src/gemini_webapi/types/modeloutput.py

@@ -32,6 +32,10 @@ class ModelOutput(BaseModel):
     def text(self) -> str:
         return self.candidates[self.chosen].text
 
+    @property
+    def thoughts(self) -> str | None:
+        return self.candidates[self.chosen].thoughts
+
     @property
     def images(self) -> list[Image]:
         return self.candidates[self.chosen].images

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/src/gemini_webapi.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gemini-webapi
-Version: 1.8.4
+Version: 1.9.0
 Summary: ✨ An elegant async Python wrapper for Google Gemini web app
 Author: UZQueen
 License:                     GNU AFFERO GENERAL PUBLIC LICENSE
@@ -725,14 +725,15 @@ A reverse-engineered asynchronous python wrapper for [Google Gemini](https://gem
 - [Authentication](#authentication)
 - [Usage](#usage)
   - [Initialization](#initialization)
+  - [Select language model](#select-language-model)
   - [Generate contents from text](#generate-contents-from-text)
   - [Generate contents from image](#generate-contents-from-image)
   - [Conversations across multiple turns](#conversations-across-multiple-turns)
   - [Continue previous conversations](#continue-previous-conversations)
+  - [Retrieve model's thought process](#retrieve-models-thought-process)
   - [Retrieve images in response](#retrieve-images-in-response)
   - [Generate images with ImageFx](#generate-images-with-imagefx)
   - [Save images to local files](#save-images-to-local-files)
-  - [Specify language model version](#specify-language-model-version)
   - [Generate contents with Gemini extensions](#generate-contents-with-gemini-extensions)
   - [Check and switch to other reply candidates](#check-and-switch-to-other-reply-candidates)
   - [Control log level](#control-log-level)
@@ -815,6 +816,41 @@ asyncio.run(main())
 >
 > `auto_close` and `close_delay` are optional arguments for automatically closing the client after a certain period of inactivity. This feature is disabled by default. In an always-on service like chatbot, it's recommended to set `auto_close` to `True` combined with reasonable seconds of `close_delay` for better resource management.
 
+### Select language model
+
+You can specify which language model to use by passing `model` argument to `GeminiClient.generate_content` or `GeminiClient.start_chat`. The default value is `unspecified`.
+
+Currently available models (as of Feb 5, 2025):
+
+- `unspecified` - Default model (same as `gemini-2.0-flash` if account does NOT have Gemini Advanced subscription)
+- `gemini-2.0-flash` - Gemini 2.0 Flash
+- `gemini-2.0-flash-thinking` - Gemini 2.0 Flash Thinking Experimental
+- `gemini-2.0-flash-thinking-with-apps` - Gemini 2.0 Flash Thinking Experimental with apps
+- `gemini-1.5-flash` - Gemini 1.5 Flash
+
+Models pending update (may not work as expected):
+
+- `gemini-2.0-exp-advanced` - Gemini 2.0 Experimental Advanced **(requires Gemini Advanced account)**
+- `gemini-1.5-pro` - Gemini 1.5 Pro **(requires Gemini Advanced account)**
+- `gemini-1.5-pro-research` - Gemini 1.5 Pro with Deep Research **(requires Gemini Advanced account)**
+
+```python
+from gemini_webapi.constants import Model
+
+async def main():
+    response1 = await client.generate_content(
+        "What's you language model version? Reply version number only.",
+        model=Model.G_2_0_FLASH,
+    )
+    print(f"Model version ({Model.G_2_0_FLASH.model_name}): {response1.text}")
+
+    chat = client.start_chat(model="gemini-2.0-flash-thinking")
+    response2 = await chat.send_message("What's you language model version? Reply version number only.")
+    print(f"Model version (gemini-2.0-flash-thinking): {response2.text}")
+
+asyncio.run(main())
+```
+
 ### Generate contents from text
 
 Ask a one-turn quick question by calling `GeminiClient.generate_content`.
@@ -885,6 +921,21 @@ async def main():
 asyncio.run(main())
 ```
 
+### Retrieve model's thought process
+
+When using models with thinking capabilities, the model's thought process will be populated in `ModelOutput.thoughts`.
+
+```python
+async def main():
+    response = await client.generate_content(
+            "What's 1+1?", model="gemini-2.0-flash-thinking"
+        )
+    print(response.thoughts)
+    print(response.text)
+
+asyncio.run(main())
+```
+
 ### Retrieve images in response
 
 Images in the API's output are stored as a list of `Image` objects. You can access the image title, URL, and description by calling `image.title`, `image.url` and `image.alt` respectively.
@@ -938,36 +989,6 @@ async def main():
 asyncio.run(main())
 ```
 
-### Specify language model version
-
-You can choose a specified language model version by passing `model` argument to `GeminiClient.generate_content` or `GeminiClient.start_chat`. The default value is `unspecified`.
-
-Currently available models (as of Feb 1, 2025):
-
-- `unspecified` - Default model (Gemini 2.0 Flash if account does NOT have Gemini Advanced subscription)
-- `gemini-1.5-flash` - Gemini 1.5 Flash
-- `gemini-1.5-pro` - Gemini 1.5 Pro **(requires Gemini Advanced account)**
-- `gemini-1.5-pro-research` - Gemini 1.5 Pro with Deep Research **(requires Gemini Advanced account)**
-- `gemini-2.0-flash-exp` - Gemini 2.0 Flash Experimental
-- `gemini-2.0-exp-advanced` - Gemini 2.0 Experimental Advanced **(requires Gemini Advanced account)**
-
-```python
-from gemini_webapi.constants import Model
-
-async def main():
-    response1 = await client.generate_content(
-        "What's you language model version? Reply version number only.",
-        model="gemini-1.5-flash",
-    )
-    print(f"Model version (gemini-1.5-flash): {response1.text}")
-
-    chat = client.start_chat(model=Model.G_2_0_FLASH_EXP)
-    response2 = await chat.send_message("What's you language model version? Reply version number only.")
-    print(f"Model version ({Model.G_2_0_FLASH_EXP.model_name}): {response2.text}")
-
-asyncio.run(main())
-```
-
 ### Generate contents with Gemini extensions
 
 > [!IMPORTANT]

{gemini_webapi-1.8.4 → gemini_webapi-1.9.0}/tests/test_client_features.py

@@ -25,8 +25,27 @@ class TestGeminiClient(unittest.IsolatedAsyncioTestCase):
 
     @logger.catch(reraise=True)
     async def test_successful_request(self):
-        response = await self.geminiclient.generate_content("Hello World!")
-        self.assertTrue(response.text)
+        response = await self.geminiclient.generate_content(
+            "Hello World!", model=Model.G_2_0_FLASH
+        )
+        logger.debug(response.text)
+
+    @logger.catch(reraise=True)
+    async def test_thinking_model(self):
+        response = await self.geminiclient.generate_content(
+            "What's 1+1?", model=Model.G_2_0_FLASH_THINKING
+        )
+        logger.debug(response.thoughts)
+        logger.debug(response.text)
+
+    @logger.catch(reraise=True)
+    async def test_thinking_with_apps(self):
+        response = await self.geminiclient.generate_content(
+            "Tell me a fact about today in history and illustrate it with a youtube video",
+            model=Model.G_2_0_FLASH_THINKING_WITH_APPS,
+        )
+        logger.debug(response.thoughts)
+        logger.debug(response.text)
 
     @logger.catch(reraise=True)
     async def test_switch_model(self):