add ollama model server

chatbot-langchain/chatbot_ui.py

@@ -3,22 +3,41 @@
 from langchain_community.callbacks import StreamlitCallbackHandler
 from langchain_core.prompts import ChatPromptTemplate
 import streamlit as st
+import requests
+import json
 import os 
 
 
 model_service = os.getenv("MODEL_SERVICE_ENDPOINT",
                           "http://localhost:8001/v1")
+@st.cache_data
+def get_models():
+    try:
+        response = requests.get(f"{model_service[:-2]}api/tags")
+        return [i["name"].split(":")[0] for i in  
+            json.loads(response.content)["models"]]
+    except:
+        return None
+
+models = get_models()
+model = ""
 
 st.title("💬 Chatbot")  
 if "messages" not in st.session_state:
     st.session_state["messages"] = [{"role": "assistant", 
                                      "content": "How can I help you?"}]
 
+if models:
+    with st.sidebar:
+        model = st.radio(label="Select Model",
+                    options=models)
+
 for msg in st.session_state.messages:
     st.chat_message(msg["role"]).write(msg["content"])
 
 llm = ChatOpenAI(base_url=model_service, 
              api_key="sk-no-key-required",
+             model=model,
              streaming=True,
              callbacks=[StreamlitCallbackHandler(st.container(),
                                                 expand_new_thoughts=True,

model_servers/ollama/README.md

@@ -0,0 +1,43 @@
+# Ollama 🦙 Model Server
+
+We can also use the official [Ollama](https://ollama.ai) image for our model service, [ollama/ollama:latest](https://hub.docker.com/r/ollama/ollama).
+
+### Get a model
+
+Use the ollama cli to pull a model.
+
+```bash
+ollama pull mistral
+```
+
+### Run the model server
+
+Run the model server and create a volume mount on your local host to where the ollama models are stored. 
+```bash
+podman run -it --rm -v /<LOCAL_PATH>/.ollama/:/root/.ollama:Z -p 11434:11434 ollama
+```
+
+### Interact with your model
+
+Once your service is up and running it will expose a REST API that you can use to interact with your model.
+
+```bash
+curl -X POST http://localhost:11434/api/generate -d '{
+  "model": "mistral",
+  "prompt":"Why is the sky blue?"
+ }'
+```
+Please note that the ollama API is slightly different from the llamacpp python API used throughout this repository. Be sure to make any appropriate changes to application code to accommodate these differences.  
+
+The full API docs for the ollama model server can be found here: https://github.com/ollama/ollama/blob/main/docs/api.md 
+
+
+However, the ollama model server **does** currently has partial OpenAI API compatibility and should work with any tool that calls `/v1/chat/completions`
+
+```python
+from langchain_openai import ChatOpenAI
+llm = ChatOpenAI(base_url="http://localhost:11434/v1", 
+             api_key="sk-no-key-required",
+             model="mistral")
+llm.invoke("hello")
+```

model_servers/ollama/builds/Containerfile

@@ -0,0 +1 @@
+FROM ollama/ollama