Add support for local llm (mistral 7b) (#31)

demos/weather-forecast-local-llm/katanemo-config.yaml

@@ -0,0 +1,46 @@
+default_prompt_endpoint: "127.0.0.1"
+load_balancing: "round_robin"
+timeout_ms: 5000
+
+embedding_provider:
+  name: "SentenceTransformer"
+  model: "all-MiniLM-L6-v2"
+
+llm_providers:
+
+  - name: open-ai-gpt-4
+    api_key: "$OPEN_AI_API_KEY"
+    model: gpt-4
+
+  - name: mistral_7b_instruct
+    model: mistral-7b-instruct
+    endpoint: http://mistral_7b_instruct:10001/v1/chat/completions
+    default: true
+
+prompt_targets:
+
+  - type: context_resolver
+    name: weather_forecast
+    few_shot_examples:
+      - what is the weather in New York?
+      - how is the weather in San Francisco?
+      - what is the forecast in Chicago?
+    entities:
+      - name: city
+        required: true
+      - name: days
+    endpoint:
+      cluster: weatherhost
+      path: /weather
+    system_prompt: |
+      You are a helpful weather forecaster. Use weater data that is provided to you. Please following following guidelines when responding to user queries:
+      - Use farenheight for temperature
+      - Use miles per hour for wind speed
+
+#TODO: add support for adding custom clusters e.g.
+    #  clusters:
+    #     qdrant:
+    #       options:
+    #         - address: "qdrant"
+    #         - address: "weatherhost"
+    #         - port: 6333