[CAI-271] - Monitoring with Langfuse

.gitmodules

@@ -1,3 +1,3 @@
 [submodule "apps/nextjs-website/.tmp-docs"]
 	path = apps/nextjs-website/.tmp-docs
-	url = https://github.com/pagopa/devportal-docs.git
+	url = https://github.com/pagopa/devportal-docs.git

apps/chatbot/.dockerignore

@@ -2,3 +2,4 @@
 build-devp
 .pytest_cache
 load-test
+*.ipynb

apps/chatbot/.env.example

@@ -2,6 +2,7 @@ environment=local
 CORS_DOMAINS=["*"]
 PYTHONPATH=app-path
 LOG_LEVEL=DEBUG
+
 CHB_AWS_ACCESS_KEY_ID=...
 CHB_AWS_SECRET_ACCESS_KEY=...
 CHB_AWS_DEFAULT_REGION=eu-south-1
@@ -20,12 +21,28 @@ CHB_MODEL_ID=...
 CHB_MODEL_TEMPERATURE=...
 CHB_MODEL_MAXTOKENS=...
 CHB_EMBED_MODEL_ID=...
+CHB_USE_CHAT_ENGINE=True
 CHB_ENGINE_SIMILARITY_TOPK=...
 CHB_ENGINE_SIMILARITY_CUTOFF=...
 CHB_ENGINE_USE_ASYNC=True
 CHB_ENGINE_USE_STREAMING=...
-CHB_ENGINE_USE_CHAT_ENGINE=...
 CHB_QUERY_TABLE_PREFIX=chatbot-local
 CHB_DYNAMODB_URL=http://locahost:8080
 CHB_USE_PRESIDIO=True
 CHB_SESSION_MAX_DURATION_DAYS=1
+
+DATABASE_URL=postgresql://postgres:postgres@postgres:5432/postgres
+LANGFUSE_HOST=http://langfuse:3000
+NEXTAUTH_SECRET=mysecret
+SALT=mysalt
+ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000
+LANGFUSE_ORG_ID=...
+LANGFUSE_ORG_NAME=...
+LANGFUSE_PROJECT_ID=...
+LANGFUSE_PROJECT_NAME=...
+LANGFUSE_PUBLIC_KEY=...
+LANGFUSE_SECRET_KEY=...
+[email protected]
+LANGFUSE_USER_NAME=User
+LANGFUSE_USER_PASSWORD=abcd1234
+LANGFUSE_TAG=development

apps/chatbot/README.md

@@ -7,10 +7,16 @@ Even though the provider is the Google one, we stored its API key in AWS. So, be
 
 The Retrieval-Augmented Generation (RAG) was implemented using [llama-index](https://docs.llamaindex.ai/en/stable/). All the parameters and prompts used are stored in `config`.
 
+The monitoring is done using [Langfuse](https://langfuse.com/) deployed on AWS.
+
 ## Environment Variables
 
 Create a `.env` file inside this folder and store the environment variables listed in `.env.example`.
 
+cp .env.example .env
+
+Note that the envirables inside `.env` file should be pointing to the AWS infrastructure.s
+
 ## Virtual environment
 
 Before creating your virtual environment, install [Miniconda](https://docs.anaconda.com/miniconda/#quick-command-line-install) and [Poetry](https://python-poetry.org/docs/main#installation) on your device.
@@ -36,30 +42,42 @@ In this way, `PYTHONPATH` points to where the Python packages and modules are, n
 
 To reach the remote redis instance, it is necessary to open a tunnel:
 
-```
     ./scripts/redis-tunnel.sh
-```
 
 Verify that the HTML files that compose the Developer Portal documentation exist in a directory. Otherwise create the documentation. Once you have the documentation directory ready, put its path in `params` and, in the end, create the vector index doing:
 
-```
     python src/modules/create_vector_index.py --params config/params.yaml
-```
 
 This script reads the documentation, split it into chucks with gerarchical organization, and stores it on Redis.
 
 Check out the params in order to store your vector index accordingly.
 
-## test
+## Test
+
+Run the tests for the chatbot and the APIs running:
+
+    pytest
+
+## Docker
+
+In order to run the chatbot locally for the first time, you need to:
+
+- install [Docker Compose](https://docs.docker.com/compose/install/),
+- create `.env.local` file running:
+
+        cp .env.example .env.local
+
+  and fill it in,
+
+- run the following bash scripts:
 
-```
-pytest
-```
+        ./docker/docker-compose-build-local.sh
+        ./docker/docker-compose-run-create_index.sh
 
-## Web App
+In this way, the docker images are built and the vector index is stored in Redis.
 
-    python src/webapp/app.py
+Now you can start the API running:
 
-This scripts uses [Gradio](https://www.gradio.app/) framework to lunch a web application at the [default link](http://127.0.0.1:7860) where the user can interact with the chatbot.
+    ./docker/docker-compose-up-api.sh
 
-Both [`user icon`](https://www.flaticon.com/free-icon/user_1077012) and [`chatbot icon`](https://www.flaticon.com/free-icon/chatbot_8943377) are made by [Freepick](https://www.freepik.com/) and they were downloaded from [Flaticon](https://www.flaticon.com/).
+Note that the `docker/compose.yaml` needs `.env.local` file with the correct environment variables.

apps/chatbot/config/params.yaml

@@ -52,6 +52,8 @@ config_presidio:
   allow_list:
     - Discovery
     - discovery
+    - rispondo
+    - Rispondo
     - Rif
     - SEND
     - send
@@ -61,8 +63,12 @@ config_presidio:
     - Gpd
     - STATO
     - stato
-    - PagoPA 
+    - PagoPA
     - pagoPA
+    - Devportal
+    - devPortal
+    - DevPortal
+    - devportal
     - pagopa
     - Pagopa
     - Firma con IO

apps/chatbot/docker/app.local.Dockerfile

@@ -19,11 +19,13 @@ RUN pip install --upgrade pip \
   && pip install poetry awscli
 
 WORKDIR /app
-COPY pyproject.toml .
-COPY poetry.lock .
+COPY ./pyproject.toml .
+COPY ./poetry.lock .
+COPY ./src ./src
+COPY ./config ./config
+COPY ./scripts ./scripts
+
 RUN poetry config virtualenvs.create false
 RUN poetry install
 
-COPY . .
-
 CMD ["fastapi", "dev", "src/app/main.py", "--port", "8080", "--host", "0.0.0.0"]

apps/chatbot/docker/compose.test.yaml

@@ -26,13 +26,17 @@ services:
       - AWS_SECRET_ACCESS_KEY=dummy
       - AWS_DEFAULT_REGION=local
     healthcheck:
-      test: ["CMD-SHELL", '[ "$(curl -s -o /dev/null -I -w ''%{http_code}'' http://localhost:8000)" == "400" ]']
+      test:
+        [
+          "CMD-SHELL",
+          '[ "$(curl -s -o /dev/null -I -w ''%{http_code}'' http://localhost:8000)" == "400" ]',
+        ]
       interval: 10s
       timeout: 10s
       retries: 10
     networks:
       - ntw
-  
+
   redis:
     image: redis/redis-stack:7.2.0-v13
     networks:

apps/chatbot/docker/compose.yaml

@@ -1,9 +1,9 @@
+---
 services:
   api:
     build:
       context: ..
       dockerfile: docker/app.local.Dockerfile
-    env_file: ../.env.local
     command: "./scripts/run.local.sh"
     ports:
       - "8080:8080"
@@ -16,6 +16,26 @@ services:
         condition: service_started
       dynamodb:
         condition: service_started
+      langfuse:
+        condition: service_started
+    env_file: ../.env.local
+
+    networks:
+      - ntw
+
+  postgres:
+    image: postgres:17.2-alpine
+    restart: always
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U postgres"]
+      interval: 3s
+      timeout: 3s
+      retries: 10
+    ports:
+      - "5432:5432"
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    env_file: ../.env.local
     networks:
       - ntw
 
@@ -35,6 +55,8 @@ services:
     ports:
       - "6379:6379"
       - "8001:8001"
+    volumes:
+      - redis_data:/data
     networks:
       - ntw
 
@@ -47,13 +69,32 @@ services:
     volumes:
       - ..:/app
       - ../../nextjs-website/out:/app/build-devp/out
-    command: "python src/modules/create_vector_index.py --params config/params.yaml"
+    command: >
+      "python src/modules/create_vector_index.py --params config/params.yaml"
     tty: true
     depends_on:
       redis:
         condition: service_started
+    env_file: ../.env.local
     networks:
       - ntw
 
+  langfuse:
+    image: langfuse/langfuse:2
+    depends_on:
+      postgres:
+        condition: service_healthy
+    ports:
+      - "3001:3000"
+    env_file: ../.env.local
+    networks:
+      - ntw
+
+volumes:
+  postgres_data:
+    driver: local
+  redis_data:
+    driver: local
+
 networks:
   ntw:

apps/chatbot/docker/docker-compose-build-local.sh

@@ -1,2 +1,2 @@
 #!/bin/bash
-docker compose --env-file .env -f docker/compose.yaml -p chatbot build
+docker compose -f docker/compose.yaml -p chatbot build

apps/chatbot/docker/docker-compose-run-create_index.sh

@@ -1,2 +1,2 @@
 #!/bin/bash
-docker compose --env-file .env -f docker/compose.yaml -p chatbot run create_index
+docker compose -f docker/compose.yaml -p chatbot run create_index