(docs) litellm ollama docker image

cookbook/litellm-ollama-docker-image/Dockerfile

@@ -0,0 +1,25 @@
+FROM ollama/ollama as ollama
+
+RUN echo "auto installing llama2"
+
+# auto install ollama/llama2
+RUN ollama serve & sleep 2 && ollama pull llama2
+
+RUN echo "installing litellm"
+
+RUN apt-get update
+
+# Install Python
+RUN apt-get install -y python3 python3-pip
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+
+RUN python3 -m pip install litellm
+COPY start.sh /start.sh
+ENTRYPOINT [ "/bin/bash", "/start.sh" ]

cookbook/litellm-ollama-docker-image/requirements.txt

@@ -0,0 +1 @@
+litellm

cookbook/litellm-ollama-docker-image/start.sh

@@ -0,0 +1,2 @@
+ollama serve &
+litellm

cookbook/litellm-ollama-docker-image/test.py

@@ -0,0 +1,36 @@
+
+import openai
+
+api_base = f"http://0.0.0.0:8000"
+
+openai.api_base = api_base
+openai.api_key = "temp-key"
+print(openai.api_base)
+
+
+print(f'LiteLLM: response from proxy with streaming')
+response = openai.ChatCompletion.create(
+    model="ollama/llama2", 
+    messages = [
+        {
+            "role": "user",
+            "content": "this is a test request, acknowledge that you got it"
+        }
+    ],
+    stream=True
+)
+
+for chunk in response:
+    print(f'LiteLLM: streaming response from proxy {chunk}')
+
+response = openai.ChatCompletion.create(
+    model="ollama/llama2", 
+    messages = [
+        {
+            "role": "user",
+            "content": "this is a test request, acknowledge that you got it"
+        }
+    ]
+)
+
+print(f'LiteLLM: response from proxy {response}')