docs fireworks ai

docs/my-website/docs/providers/fireworks_ai.md

@@ -1,7 +1,12 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
 # Fireworks AI
 https://fireworks.ai/
 
+:::info
 **We support ALL Fireworks AI models, just set `fireworks_ai/` as a prefix when sending completion requests**
+:::
 
 ## API Key
 ```python
@@ -16,7 +21,7 @@ import os
 
 os.environ['FIREWORKS_AI_API_KEY'] = ""
 response = completion(
-    model="fireworks_ai/mixtral-8x7b-instruct", 
+    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", 
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -31,7 +36,7 @@ import os
 
 os.environ['FIREWORKS_AI_API_KEY'] = ""
 response = completion(
-    model="fireworks_ai/mixtral-8x7b-instruct", 
+    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", 
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -43,8 +48,103 @@ for chunk in response:
 ```
 
 
+## Usage with LiteLLM Proxy 
+
+### 1. Set Fireworks AI Models on config.yaml
+
+```yaml
+model_list:
+  - model_name: fireworks-llama-v3-70b-instruct
+    litellm_params:
+      model: fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
+      api_key: "os.environ/FIREWORKS_AI_API_KEY"
+```
+
+### 2. Start Proxy 
+
+```
+litellm --config config.yaml
+```
+
+### 3. Test it
+
+
+<Tabs>
+<TabItem value="Curl" label="Curl Request">
+
+```shell
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--data ' {
+      "model": "fireworks-llama-v3-70b-instruct",
+      "messages": [
+        {
+          "role": "user",
+          "content": "what llm are you"
+        }
+      ]
+    }
+'
+```
+</TabItem>
+<TabItem value="openai" label="OpenAI v1.0.0+">
+
+```python
+import openai
+client = openai.OpenAI(
+    api_key="anything",
+    base_url="http://0.0.0.0:4000"
+)
+
+# request sent to model set on litellm proxy, `litellm --model`
+response = client.chat.completions.create(model="fireworks-llama-v3-70b-instruct", messages = [
+    {
+        "role": "user",
+        "content": "this is a test request, write a short poem"
+    }
+])
+
+print(response)
+
+```
+</TabItem>
+<TabItem value="langchain" label="Langchain">
+
+```python
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+    SystemMessagePromptTemplate,
+)
+from langchain.schema import HumanMessage, SystemMessage
+
+chat = ChatOpenAI(
+    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
+    model = "fireworks-llama-v3-70b-instruct",
+    temperature=0.1
+)
+
+messages = [
+    SystemMessage(
+        content="You are a helpful assistant that im using to make a test request to."
+    ),
+    HumanMessage(
+        content="test from litellm. tell me why it's amazing in 1 sentence"
+    ),
+]
+response = chat(messages)
+
+print(response)
+```
+</TabItem>
+</Tabs>
+
 ## Supported Models - ALL Fireworks AI Models Supported!
+
+:::info
 We support ALL Fireworks AI models, just set `fireworks_ai/` as a prefix when sending completion requests
+:::
 
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|

litellm/proxy/proxy_config.yaml

@@ -1,17 +1,8 @@
 model_list:
-  - model_name: gpt-4
+  - model_name: fireworks-llama-v3-70b-instruct
     litellm_params:
-      model: openai/fake
+      model: fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
-      api_key: fake-key
+      api_key: "os.environ/FIREWORKS_AI_API_KEY"
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      tags: ["free"] # 👈 Key Change
-  - model_name: gpt-4
-    litellm_params:
-      model: openai/gpt-4o
-      api_key: os.environ/OPENAI_API_KEY
-      tags: ["paid"] # 👈 Key Change
 
-router_settings:
-  enable_tag_filtering: True # 👈 Key Change
 general_settings: 
   master_key: sk-1234