feat(rag): secret vault injection

.gitignore

@@ -170,3 +170,5 @@ grafana/runtime-data/*
 
 prometheus/data/*
 !prometheus/data/.gitkeep
+
+*.swp

docker/api.Dockerfile

@@ -14,7 +14,7 @@ COPY --from=sev /app/sev/libsevguest.h /app/nilai-api/src/nilai_api/sev/libsevgu
 WORKDIR /app/nilai-api/
 
 RUN apt-get update && \
-apt-get install build-essential curl -y && \
+apt-get install build-essential curl git -y && \
 apt-get clean && \
 apt-get autoremove && \
 rm -rf /var/lib/apt/lists/* && \

docker/compose/docker-compose.llama-1b-gpu.yml

@@ -0,0 +1,58 @@
+services:
+  llama_32_tool_gpu:
+    build:
+      context: .
+      dockerfile: docker/vllm.Dockerfile
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities:
+                - gpu
+              driver: nvidia
+    ipc: host
+    depends_on:
+      etcd:
+        condition: service_healthy
+      watt_tool_gpu:
+        condition: service_healthy
+    command:
+      - --model
+      - meta-llama/Llama-3.2-1B-Instruct
+      - --max-model-len
+      - "10000"
+      - --device
+      - cuda
+      - --gpu-memory-utilization
+      - "0.45"
+      - --enable-auto-tool-choice
+      - --tool-call-parser
+      - llama3_json
+      - --chat-template
+      - /tmp/tool_chat_template.jinja
+    env_file:
+      - .env
+    environment:
+      SVC_HOST: "llama_32_tool_gpu"
+      SVC_PORT: "8000"
+      ETCD_HOST: "etcd"
+      ETCD_PORT: "2379"
+      TOOL_SUPPORT: true
+      MODEL_ROLE: "reasoning"
+    networks:
+      - backend_net
+    volumes:
+      - type: volume
+        source: hugging_face_models
+        target: /root/.cache/huggingface
+        volume: {}
+      - type: bind
+        source: $PWD/docker/compose/tool_chat_template_llama3.2_json.jinja
+        target: /tmp/tool_chat_template.jinja
+        bind:
+          create_host_path: true
+volumes:
+  hugging_face_models:
+
+networks:
+  backend_net:

docker/compose/docker-compose.npw.deepseek14.yml

@@ -0,0 +1,54 @@
+services:
+  deepseek_14b_gpu:
+    build:
+      context: .
+      dockerfile: docker/vllm.Dockerfile
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities:
+                - gpu
+              driver: nvidia
+    ipc: host
+    depends_on:
+      etcd:
+        condition: service_healthy
+      watt_tool_gpu:
+        condition: service_healthy
+    command:
+      - --model
+      - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+      - --max-model-len
+      - "10000"
+      - --device
+      - cuda
+      - --gpu-memory-utilization
+      - "0.45"
+    env_file:
+      - .env
+    environment:
+      SVC_HOST: "deepseek_14b_gpu"
+      SVC_PORT: "8000"
+      ETCD_HOST: "etcd"
+      ETCD_PORT: "2379"
+      TOOL_SUPPORT: true
+      MODEL_ROLE: "reasoning"
+    networks:
+      - backend_net
+    volumes:
+      - type: volume
+        source: hugging_face_models
+        target: /root/.cache/huggingface
+        volume: {}
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"] 
+      interval: 30s
+      retries: 3
+      start_period: 60s
+      timeout: 10s
+volumes:
+  hugging_face_models:
+
+networks:
+  backend_net:

docker/compose/docker-compose.watt-8b-gpu.yml

@@ -0,0 +1,62 @@
+services:
+  watt_tool_gpu:
+    build:
+      context: .
+      dockerfile: docker/vllm.Dockerfile
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities:
+                - gpu
+              driver: nvidia
+    ipc: host
+    depends_on:
+      etcd:
+        condition: service_healthy
+    command:
+      - --model
+      - watt-ai/watt-tool-8B
+      - --max-model-len
+      - "10000"
+      - --device
+      - cuda
+      - --gpu-memory-utilization
+      - "0.45"
+      - --enable-auto-tool-choice
+      - --tool-call-parser
+      - llama3_json
+      - --chat-template
+      - /tmp/tool_chat_template.jinja
+    env_file:
+      - .env
+    environment:
+      SVC_HOST: "watt_tool_gpu"
+      SVC_PORT: "8000"
+      ETCD_HOST: "etcd"
+      ETCD_PORT: "2379"
+      TOOL_SUPPORT: true
+      MODEL_ROLE: "worker"
+    networks:
+      - backend_net
+    volumes:
+      - type: volume
+        source: hugging_face_models
+        target: /root/.cache/huggingface
+        volume: {}
+      - type: bind
+        source: $PWD/docker/compose/tool_chat_template_llama3.1_json.jinja
+        target: /tmp/tool_chat_template.jinja
+        bind:
+          create_host_path: true
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"] 
+      interval: 30s
+      retries: 3
+      start_period: 60s
+      timeout: 10s
+volumes:
+  hugging_face_models:
+
+networks:
+  backend_net:

docker/compose/tool_chat_template_llama3.1_json.jinja

@@ -0,0 +1,120 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {#- Llama 3.1 doesn't pass all tests if the tools are in the system prompt #}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content']|trim %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text']|trim %}
+    {%- endif %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- if tools is not none %}
+        {%- set system_message = "You are a helpful assistant with tool calling capabilities. Only reply with a tool call if the function exists in the library provided by the user. If it doesn't exist, just reply directly in natural language. When you receive a tool call response, use the output to format an answer to the original user question." %}
+    {%- else %}
+        {%- set system_message = "" %}
+    {%- endif %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call. " }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. ' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- if messages[0]['content'] is string %}
+            {%- set first_user_message = messages[0]['content']|trim %}
+        {%- else %}
+            {%- set first_user_message = messages[0]['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | map('trim') | join('\n') %}
+        {%- endif %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+    {%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. ' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] | trim}}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'text' %}
+                    {{- content['text'] | trim }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is string %}
+            {{- { "output": message.content } | tojson }}
+        {%- else %}
+            {%- for content in message['content']  %}
+                {%- if content['type']  == 'text' %}
+                    {{- { "output": content['text']  } | tojson }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}