Fix type issue

docs/concepts/llms.mdx

@@ -29,7 +29,7 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
 
 ## Available Models and Their Capabilities
 
-Here's a detailed breakdown of supported models and their capabilities:
+Here's a detailed breakdown of supported models and their capabilities, you can compare performance at [lmarena.ai](https://lmarena.ai/):
 
 <Tabs>
   <Tab title="OpenAI">
@@ -43,6 +43,17 @@ Here's a detailed breakdown of supported models and their capabilities:
       1 token ≈ 4 characters in English. For example, 8,192 tokens ≈ 32,768 characters or about 6,000 words.
     </Note>
   </Tab>
+  <Tab title="Gemini">
+    | Model | Context Window | Best For |
+    |-------|---------------|-----------|
+    | Gemini 1.5 Flash | 1M tokens | Balanced multimodal model, good for most tasks |
+    | Gemini 1.5 Flash 8B | 1M tokens | Fastest, most cost-efficient, good for high-frequency tasks |
+    | Gemini 1.5 Pro | 2M tokens | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+
+    <Tip>
+      Google's Gemini models are all multimodal, supporting audio, images, video and text, supporting context caching, json schema, function calling, etc.
+    </Tip>
+  </Tab>
   <Tab title="Groq">
     | Model | Context Window | Best For |
     |-------|---------------|-----------|
@@ -128,10 +139,10 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
         # llm: anthropic/claude-2.1
         # llm: anthropic/claude-2.0
 
-        # Google Models - Good for general tasks
+        # Google Models - Strong reasoning, large cachable context window, multimodal
-        # llm: gemini/gemini-pro
         # llm: gemini/gemini-1.5-pro-latest
-        # llm: gemini/gemini-1.0-pro-latest
+        # llm: gemini/gemini-1.5-flash-latest
+        # llm: gemini/gemini-1.5-flash-8b-latest
 
         # AWS Bedrock Models - Enterprise-grade
         # llm: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
@@ -350,13 +361,18 @@ Learn how to get the most out of your LLM configuration:
 
   <Accordion title="Google">
     ```python Code
+    # Option 1. Gemini accessed with an API key.
+    # https://ai.google.dev/gemini-api/docs/api-key
     GEMINI_API_KEY=<your-api-key>
+
+    # Option 2. Vertex AI IAM credentials for Gemini, Anthropic, and anything in the Model Garden.
+    # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
     Example usage:
     ```python Code
     llm = LLM(
-        model="gemini/gemini-pro",
+        model="gemini/gemini-1.5-pro-latest",
         temperature=0.7
     )
     ```

src/crewai/llm.py

@@ -43,6 +43,10 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "gpt-4-turbo": 128000,
     "o1-preview": 128000,
     "o1-mini": 128000,
+    # gemini
+    "gemini-1.5-pro": 2097152,
+    "gemini-1.5-flash": 1048576,
+    "gemini-1.5-flash-8b": 1048576,
     # deepseek
     "deepseek-chat": 128000,
     # groq
@@ -61,6 +65,9 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "mixtral-8x7b-32768": 32768,
 }
 
+DEFAULT_CONTEXT_WINDOW_SIZE = 8192
+CONTEXT_WINDOW_USAGE_RATIO = 0.75
+
 
 @contextmanager
 def suppress_warnings():
@@ -124,6 +131,7 @@ class LLM:
         self.api_version = api_version
         self.api_key = api_key
         self.callbacks = callbacks
+        self.context_window_size = 0
         self.kwargs = kwargs
 
         litellm.drop_params = True
@@ -191,7 +199,16 @@ class LLM:
 
     def get_context_window_size(self) -> int:
         # Only using 75% of the context window size to avoid cutting the message in the middle
-        return int(LLM_CONTEXT_WINDOW_SIZES.get(self.model, 8192) * 0.75)
+        if self.context_window_size != 0:
+            return self.context_window_size
+
+        self.context_window_size = int(
+            DEFAULT_CONTEXT_WINDOW_SIZE * CONTEXT_WINDOW_USAGE_RATIO
+        )
+        for key, value in LLM_CONTEXT_WINDOW_SIZES.items():
+            if self.model.startswith(key):
+                self.context_window_size = int(value * CONTEXT_WINDOW_USAGE_RATIO)
+        return self.context_window_size
 
     def set_callbacks(self, callbacks: List[Any]):
         callback_types = [type(callback) for callback in callbacks]