Merge pull request #37 from gschmutz/support-for-env-variables

Support if environment variables to configure the app

Author: rlancemartin

.env.example

@@ -1,3 +1,11 @@
+OLLAMA_BASE_URL=                # the endpoint of the Ollama service, defaults to http://localhost:11434 if not set
+OLLAMA_MODEL=                   # the name of the model to use, defaults to 'llama3.2' if not set
+
+# Which search service to use, either 'duckduckgo' or 'tavily' or 'perplexity'
+SEARCH_API=
 # Web Search API Keys (choose one or both)
 TAVILY_API_KEY=tvly-xxxxx      # Get your key at https://tavily.com
 PERPLEXITY_API_KEY=pplx-xxxxx  # Get your key at https://www.perplexity.ai
+
+MAX_WEB_RESEARCH_LOOPS=
+FETCH_FULL_PAGE=

.github/workflows/docker-image.yml

@@ -0,0 +1,63 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: ghcr.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # Setup QEMU for multi-platform build support
+      # https://docs.docker.com/build/ci/github-actions/multi-platform/
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3 
+
+      # Set up BuildKit Docker container builder to be able to build
+      # multi-platform images and export cache
+      # https://github.com/docker/setup-buildx-action
+      - name: Setup Docker buildx
+        uses: docker/setup-buildx-action@v3
+
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Log into registry ${{ env.REGISTRY }}
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GH_TOKEN }}
+
+      # Extract metadata (tags, labels) for Docker
+      # https://github.com/docker/metadata-action
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # Build and push Docker image with Buildx (don't push on PR)
+      # https://github.com/docker/build-push-action
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest
+          labels: ${{ steps.meta.outputs.labels }}          
+

README.md

@@ -36,7 +36,17 @@ By default, it will use [DuckDuckGo](https://duckduckgo.com/) for web search, wh
 ```bash
 cp .env.example .env
 ```
- 
+
+The following environment variables are supported:
+
+  * `OLLAMA_BASE_URL` - the endpoint of the Ollama service, defaults to `http://localhost:11434` if not set 
+  * `OLLAMA_MODEL` - the model to use, defaults to `llama3.2` if not set
+  * `SEARCH_API` - the search API to use, either `duckduckgo` (default) or `tavily` or `perplexity`. You need to set the corresponding API key if tavily or perplexity is used.
+  * `TAVILY_API_KEY` - the tavily API key to use
+  * `PERPLEXITY_API_KEY` - the perplexity API key to use
+  * `MAX_WEB_RESEARCH_LOOPS` - the maximum number of research loop steps, defaults to `3`
+  * `FETCH_FULL_PAGE` - fetch the full page content if using `duckduckgo` for the search API, defaults to `false`
+
 5. (Recommended) Create a virtual environment:
 ```bash
 python -m venv .venv
@@ -172,7 +182,7 @@ https://github.com/PacoVK/ollama-deep-researcher-ts
 
 ## Running as a Docker container
 
-The included `Dockerfile` only runs LangChain Studio with ollama-deep-researcher as a service, but does not include Ollama as a dependant service. You must run Ollama separately and configure the `OLLAMA_BASE_URL` environment variable.
+The included `Dockerfile` only runs LangChain Studio with ollama-deep-researcher as a service, but does not include Ollama as a dependant service. You must run Ollama separately and configure the `OLLAMA_BASE_URL` environment variable. Optionally you can also specify the Ollama model to use by providing the `OLLAMA_MODEL` environment variable.
 
 Clone the repo and build an image:
 ```
@@ -182,8 +192,10 @@ $ docker build -t ollama-deep-researcher .
 Run the container:
 ```
 $ docker run --rm -it -p 2024:2024 \
+  -e SEARCH_API="tavily" \ 
   -e TAVILY_API_KEY="tvly-***YOUR_KEY_HERE***" \
   -e OLLAMA_BASE_URL="http://host.docker.internal:11434/" \
+  -e OLLAMA_MODEL="llama3.2" \  
   ollama-deep-researcher
 ```
 

src/assistant/configuration.py

@@ -15,11 +15,11 @@ class SearchAPI(Enum):
 @dataclass(kw_only=True)
 class Configuration:
     """The configurable fields for the research assistant."""
-    max_web_research_loops: int = 3
-    local_llm: str = "llama3.2"
-    search_api: SearchAPI = SearchAPI.DUCKDUCKGO  # Default to DUCDUCKGO
-    fetch_full_page: bool = False  # Default to False
-    ollama_base_url: str = "http://localhost:11434/"
+    max_web_research_loops: int = int(os.environ.get("MAX_WEB_RESEARCH_LOOPS", "3"))
+    local_llm: str = os.environ.get("OLLAMA_MODEL", "llama3.2")
+    search_api: SearchAPI = SearchAPI(os.environ.get("SEARCH_API", SearchAPI.DUCKDUCKGO.value))  # Default to DUCKDUCKGO
+    fetch_full_page: bool = os.environ.get("FETCH_FULL_PAGE", "False").lower() in ("true", "1", "t")
+    ollama_base_url: str = os.environ.get("OLLAMA_BASE_URL", "http://localhost:11434/")
 
     @classmethod
     def from_runnable_config(

src/assistant/utils.py

@@ -149,7 +149,10 @@ def tavily_search(query, include_raw_content=True, max_results=3):
                 - content (str): Snippet/summary of the content
                 - raw_content (str): Full content of the page if available"""
 
-    tavily_client = TavilyClient()
+    api_key = os.getenv("TAVILY_API_KEY")
+    if not api_key:
+        raise ValueError("TAVILY_API_KEY environment variable is not set")
+    tavily_client = TavilyClient(api_key=api_key)
     return tavily_client.search(query, 
                          max_results=max_results, 
                          include_raw_content=include_raw_content)