Merge pull request #43 from reactome/dep-update

Dep update

.github/workflows/ci.yml

@@ -0,0 +1,96 @@
+name: reactome_chatbot CI
+
+on:
+  workflow_dispatch:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+  push:
+    branches:
+      - main
+
+permissions:
+  id-token: write
+  contents: read
+
+jobs:
+
+  lint:
+    if: ${{ github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch' }}
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install poetry
+        poetry install --no-root
+
+    - name: Run linters
+      run: |
+        poetry run ruff check .
+        poetry run mypy .
+        poetry run isort --check .
+
+  docker-build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
+
+    - name: Build and push Docker image
+      uses: docker/build-push-action@v4
+      with:
+        context: .
+        file: ./Dockerfile
+        push: false
+        tags: reactome_chatbot:${{ github.sha }}
+
+    - uses: actions/upload-artifact@v3
+      with:
+        name: docker-image
+        path: /tmp/image.tar
+
+  docker-push:
+    if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+    needs: docker-build
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/download-artifact@v3
+      with:
+        name: docker-image
+        path: /tmp
+
+    - name: Configure AWS credentials
+      uses: aws-actions/configure-aws-credentials@v2
+      with:
+        aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+        aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+        aws-region: us-east-1
+
+    - name: Login to Amazon ECR
+      id: login-ecr
+      uses: aws-actions/amazon-ecr-login@v2
+
+    - name: Build, tag, and push image to Amazon ECR
+      env:
+        ECR_REGISTRY: ${{ steps.login-ecr.outputs.registry }}
+        IMAGE_TAG: ${{ github.sha }}
+      run: |
+        docker load --input /tmp/image.tar
+        docker tag reactome_chatbot:${{ github.sha }} $ECR_REGISTRY/reactome-chatbot:$IMAGE_TAG
+        docker tag reactome_chatbot:${{ github.sha }} $ECR_REGISTRY/reactome-chatbot:latest
+        docker push $ECR_REGISTRY/reactome_chatbot:$IMAGE_TAG
+        docker push $ECR_REGISTRY/reactome_chatbot:latest

Dockerfile

@@ -1,5 +1,5 @@
 # Use an official Python runtime as a parent image
-FROM python:3.9-slim
+FROM python:3.10-slim
 
 # Set the working directory in the container
 WORKDIR /app

README.md

@@ -160,7 +160,7 @@ poetry run isort .
 
 To run these inside of docker run a command like
 ```bash
-docker build -t reactome-chatbot .; docker run -v $(pwd)/bin:/app/bin -v$(pwd)/src:/app/src reactome-chatbot /bin/bash -c "poetry run ruff ."
+docker build -t reactome-chatbot .; docker run -v $(pwd)/bin:/app/bin -v$(pwd)/src:/app/src reactome-chatbot /bin/bash -c "poetry run ruff check ."
 sudo chown $(id -u):$(id -g) * -R
 ```
 

bin/chat-chainlit.py

@@ -5,8 +5,8 @@
 import os
 
 import chainlit as cl
-
 from dotenv import load_dotenv
+
 from retreival_chain import initialize_retrieval_chain
 from util.embedding_environment import EmbeddingEnvironment
 
@@ -47,14 +47,15 @@ async def chat_profile():
         cl.ChatProfile(
             name="React-to-me",
             markdown_description="An AI assistant specialized in exploring **Reactome** biological pathways and processes.",
-            icon="https://reactome.org/templates/favourite/favicon.ico"
+            icon="https://reactome.org/templates/favourite/favicon.ico",
         )
     ]
 
 
 @cl.on_chat_start
-async def quey_llm() -> None:
+async def start() -> None:
     chat_profile = cl.user_session.get("chat_profile")
+
     embeddings_directory = EmbeddingEnvironment.get_dir(env)
     llm_chain = initialize_retrieval_chain(
         env,
@@ -71,15 +72,15 @@ async def quey_llm() -> None:
 
 
 @cl.on_message
-async def query_llm(message: cl.Message) -> None:
+async def main(message: cl.Message) -> None:
     llm_chain = cl.user_session.get("llm_chain")
     cb = cl.AsyncLangchainCallbackHandler(
         stream_final_answer=True, answer_prefix_tokens=["FINAL", "ANSWER"]
     )
     cb.answer_reached = True
 
     res = await llm_chain.ainvoke(message.content, callbacks=[cb])
-    if cb.has_streamed_final_answer:
+    if cb.has_streamed_final_answer and cb.final_stream is not None:
         await cb.final_stream.update()
     else:
         await cl.Message(content=res).send()

bin/chat-fastapi.py

@@ -2,11 +2,11 @@
 import hmac
 import os
 
+import requests
 from chainlit.utils import mount_chainlit
 from dotenv import load_dotenv
 from fastapi import FastAPI, HTTPException, Request, Response
 from fastapi.responses import RedirectResponse
-import requests
 
 load_dotenv()
 
@@ -16,17 +16,19 @@
 CLOUDFLARE_SITE_KEY = os.getenv("CLOUDFLARE_SITE_KEY")
 
 
-def make_signature(value:str) -> str:
+def make_signature(value: str) -> str:
+    if CLOUDFLARE_SECRET_KEY is None:
+        raise ValueError("CLOUDFLARE_SECRET_KEY is not set")
     return hmac.new(
-        CLOUDFLARE_SECRET_KEY.encode(),
-        value.encode(),
-        hashlib.sha256
+        CLOUDFLARE_SECRET_KEY.encode(), value.encode(), hashlib.sha256
     ).hexdigest()
 
-def create_secure_cookie(value:str) -> str:
+
+def create_secure_cookie(value: str) -> str:
     signature = make_signature(value)
     return f"{value}|{signature}"
 
+
 def verify_secure_cookie(cookie_value: str) -> bool:
     try:
         value, signature = cookie_value.split("|", 1)
@@ -40,7 +42,8 @@ def verify_secure_cookie(cookie_value: str) -> bool:
 async def verify_captcha_middleware(request: Request, call_next):
     # Allow access to CAPTCHA pages and static files
     if (
-        request.url.path in ["/chat/verify_captcha", "/chat/verify_captcha_page", "/chat/static"]
+        request.url.path
+        in ["/chat/verify_captcha", "/chat/verify_captcha_page", "/chat/static"]
         or request.url.path.startswith("/static")
         or not os.getenv("CLOUDFLARE_SECRET_KEY")
     ):
@@ -93,16 +96,15 @@ async def captcha_page():
 async def verify_captcha(request: Request):
     form_data = await request.form()
     cf_turnstile_response = form_data.get("cf-turnstile-response")
-
-    if not cf_turnstile_response:
-        raise HTTPException(status_code=400, detail="CAPTCHA response is missing")
+    if not isinstance(cf_turnstile_response, str):
+        raise HTTPException(status_code=400, detail="CAPTCHA response is invalid")
 
     # Verify the CAPTCHA with Cloudflare
     url = "https://challenges.cloudflare.com/turnstile/v0/siteverify"
     data = {
         "secret": os.getenv("CLOUDFLARE_SECRET_KEY"),
         "response": cf_turnstile_response,
-        "remoteip": request.client.host
+        "remoteip": request.client.host if request.client else "127.0.0.1",
     }
 
     # Perform request to Cloudflare Turnstile verification endpoint
@@ -120,8 +122,8 @@ async def verify_captcha(request: Request):
         key="captcha_verified",
         value=cookie_value,
         max_age=3600,  # Cookie expires in 1 hour
-        secure=True,   # HTTPS only
-        httponly=True  # inaccessible to client side JS
+        secure=True,  # HTTPS only
+        httponly=True,  # inaccessible to client side JS
     )
 
     return redirect_response

mypy.ini

@@ -0,0 +1,8 @@
+[mypy]
+ignore_missing_imports = True
+allow_untyped_calls = True
+allow_untyped_defs = True
+allow_untyped_globals = True
+
+[mypy.plugins.pandas.*]
+init_forbid_dynamic = False