feat sambanova models (#1858)

Co-authored-by: jorgep_snova <jorge.piedrahita@sambanovasystems.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>

docs/concepts/cli.mdx

@@ -161,6 +161,7 @@ The CLI will initially prompt for API keys for the following services:
 * Groq
 * Anthropic
 * Google Gemini
+* SambaNova
 
 When you select a provider, the CLI will prompt you to enter your API key.
 

docs/concepts/llms.mdx

@@ -146,6 +146,19 @@ Here's a detailed breakdown of supported models and their capabilities, you can
       Groq is known for its fast inference speeds, making it suitable for real-time applications.
     </Tip>
   </Tab>
+  <Tab title="SambaNova">
+    | Model | Context Window | Best For |
+    |-------|---------------|-----------|
+    | Llama 3.1 70B/8B | Up to 131,072 tokens | High-performance, large context tasks |
+    | Llama 3.1 405B | 8,192 tokens | High-performance and output quality |
+    | Llama 3.2 Series | 8,192 tokens | General-purpose tasks, multimodal |
+    | Llama 3.3 70B | Up to 131,072 tokens | High-performance and output quality|
+    | Qwen2 familly | 8,192 tokens | High-performance and output quality |
+
+    <Tip>
+      [SambaNova](https://cloud.sambanova.ai/) has several models with fast inference speed at full precision.
+    </Tip>
+  </Tab>
   <Tab title="Others">
     | Provider | Context Window | Key Features |
     |----------|---------------|--------------|

docs/how-to/llm-connections.mdx

@@ -32,6 +32,7 @@ LiteLLM supports a wide range of providers, including but not limited to:
 - Cloudflare Workers AI
 - DeepInfra
 - Groq
+- SambaNova
 - [NVIDIA NIMs](https://docs.api.nvidia.com/nim/reference/models-1)
 - And many more!
 

src/crewai/cli/constants.py

@@ -85,6 +85,12 @@ ENV_VARS = {
             "key_name": "CEREBRAS_API_KEY",
         },
     ],
+    "sambanova": [
+        {
+            "prompt": "Enter your SambaNovaCloud API key (press Enter to skip)",
+            "key_name": "SAMBANOVA_API_KEY",
+        }
+    ],
 }
 
 
@@ -98,6 +104,7 @@ PROVIDERS = [
     "bedrock",
     "azure",
     "cerebras",
+    "sambanova",
 ]
 
 MODELS = {
@@ -156,6 +163,19 @@ MODELS = {
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "bedrock/mistral.mixtral-8x7b-instruct-v0:1",
     ],
+    "sambanova": [
+        "sambanova/Meta-Llama-3.3-70B-Instruct",
+        "sambanova/QwQ-32B-Preview",
+        "sambanova/Qwen2.5-72B-Instruct",
+        "sambanova/Qwen2.5-Coder-32B-Instruct",
+        "sambanova/Meta-Llama-3.1-405B-Instruct",
+        "sambanova/Meta-Llama-3.1-70B-Instruct",
+        "sambanova/Meta-Llama-3.1-8B-Instruct",
+        "sambanova/Llama-3.2-90B-Vision-Instruct",
+        "sambanova/Llama-3.2-11B-Vision-Instruct",
+        "sambanova/Meta-Llama-3.2-3B-Instruct",
+        "sambanova/Meta-Llama-3.2-1B-Instruct",
+    ],
 }
 
 DEFAULT_LLM_MODEL = "gpt-4o-mini"

src/crewai/llm.py

@@ -76,6 +76,18 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "mixtral-8x7b-32768": 32768,
     "llama-3.3-70b-versatile": 128000,
     "llama-3.3-70b-instruct": 128000,
+    #sambanova
+    "Meta-Llama-3.3-70B-Instruct": 131072,
+    "QwQ-32B-Preview": 8192,
+    "Qwen2.5-72B-Instruct": 8192,
+    "Qwen2.5-Coder-32B-Instruct": 8192,
+    "Meta-Llama-3.1-405B-Instruct": 8192,
+    "Meta-Llama-3.1-70B-Instruct": 131072,
+    "Meta-Llama-3.1-8B-Instruct": 131072,
+    "Llama-3.2-90B-Vision-Instruct": 16384,
+    "Llama-3.2-11B-Vision-Instruct": 16384,
+    "Meta-Llama-3.2-3B-Instruct": 4096,
+    "Meta-Llama-3.2-1B-Instruct": 16384,
 }
 
 DEFAULT_CONTEXT_WINDOW_SIZE = 8192