Merge branch 'main' into patch-1

.env-template

@@ -5,6 +5,7 @@ DATABASE_URL=postgresql+psycopg2://postgres:postgres@db:5432
 # TOOLS
 PYTHON_INTERPRETER_URL=http://localhost:8080
 TAVILY_API_KEY=<API_KEY_HERE>
+WOLFRAM_ALPHA_APP_ID=<APP_ID_HERE>
 
 # DEPLOYMENTS
 # To use the Toolkit, at least one deployment must be setup, the simplest
@@ -24,3 +25,6 @@ AZURE_CHAT_ENDPOINT_URL=<ENDPOINT URL>
 
 # Experimental features 
 USE_EXPERIMENTAL_LANGCHAIN=False
+
+# Community features
+USE_COMMUNITY_FEATURES='True'

CONTRIBUTING.md

@@ -25,3 +25,8 @@ Remember that there are many ways to contribute other than writing code: writing
 3. [Fork this repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo)
 4. Make your changes on your fork and make sure all your [commits are signed](https://docs.github.com/en/authentication/managing-commit-signature-verification/about-commit-signature-verification)!
 5. [Submit the fork as a Pull Request](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/creating-a-pull-request-from-a-fork) pointing to the `main` branch this repository. A maintainer should comment and/or review your Pull Request within a few days. Although depending on the circumstances, it may take longer.
+
+
+## How to add features
+
+All features must be added to the `community` folder. That's where you'll find tools and deployments that are not managed by Codeowners.

Makefile

@@ -1,7 +1,11 @@
 dev:
 	@docker compose watch
+down:
+	@docker compose down
 run-tests:
 	docker compose run --build backend poetry run pytest src/backend/tests/$(file)
+run-community-tests:
+	docker compose run --build backend poetry run pytest src/community/tests/$(file)
 attach: 
 	@docker attach cohere-toolkit-backend-1
 exec-backend:

README.md

@@ -17,32 +17,30 @@ Toolkit is a collection of prebuilt components enabling users to quickly build a
 
 ## Quick start
 
-### Deploying to Google Cloud Run
-
-Before deploying to Google Cloud Run, you'll need a postgres database accessible to your Google Cloud Project, authenticated by a username and password. You'll be prompted for a `DATABASE_URL` before the container builds.
+Try the default Toolkit application yourself by deploying it in a container locally. You will need to have [Docker](https://www.docker.com/products/docker-desktop/) and [Docker-compose >= 2.22](https://docs.docker.com/compose/install/) installed.
 
-[![Run on Google Cloud](https://deploy.cloud.run/button.svg)](https://deploy.cloud.run)
+```bash
 
-### Deploying to Azure
+docker run -e COHERE_API_KEY='>>YOUR_API_KEY<<' -p 8000:8000 -p 4000:4000 ghcr.io/cohere-ai/cohere-toolkit:latest
 
-You can deploy Toolkit with one click to Microsoft Azure Platform:
+```
 
-[<img src="https://aka.ms/deploytoazurebutton" height="48px">](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fcohere-ai%2Fcohere-toolkit%2Fmain%2Fazuredeploy.json)
+Go to localhost:4000 in your browser and start chatting with the model. This will use the model hosted on Cohere's platform. If you want to add your own tools or use another model, follow the instructions below to fork the repository.
 
 ### Building and running locally
 
 Clone the repo and run
 
 ```bash
-make setup
+make first-run
 ```
 
 Follow the instructions to configure the model - either AWS Sagemaker, Azure, or Cohere's platform. This can also be done by running `make setup` (See Option 2 below), which will help generate a file for you, or by manually creating a `.env` file and copying the contents of the provided `.env-template`. Then replacing the values with the correct ones.
 
 <details>
   <summary>Environment variables</summary>
 
-  ### Cohere Platform
+### Cohere Platform
 
 - `COHERE_API_KEY`: If your application will interface with Cohere's API, you will need to supply an API key. Not required if using AWS Sagemaker or Azure.
   Sign up at https://dashboard.cohere.com/ to create an API key.
@@ -75,6 +73,7 @@ Requirements:
 - [Docker](https://www.docker.com/products/docker-desktop/)
 - [Poetry](https://python-poetry.org/docs/#installation)
 - [Docker-compose >= 2.22](https://docs.docker.com/compose/install/)
+- [Postgres](https://www.postgresql.org/download/)
 
 #### Option 1 - Install locally with Docker:
 
@@ -130,12 +129,35 @@ Components in this repo include:
 
 ## Deployment Guides
 
-Looking to deploy the Toolkit to your preferred cloud service provider? See our guides below:
+Looking to serve your application in production? Deploy the Toolkit to your preferred cloud provider by following our guides below:
 
+### Other deployment options
 - [Single Container Setup](docs/deployment_guides/single_container.md): Useful as a quickstart to run the Toolkit, or deploy to AWS on an EC2 instance.
-- [AWS ECS Deployment](docs/deployment_guides/aws_ecs_single_container.md): Deploy the Toolkit single container to AWS ECS(Fargate).
+- [AWS ECS Fargate Deployment](docs/deployment_guides/aws_ecs_single_container.md): Deploy the Toolkit single container to AWS ECS(Fargate).
+- [AWS ECS EC2 Deployment](docs/deployment_guides/aws_ecs_single_container_ec2.md): Deploy the Toolkit single container to AWS ECS(EC2).
 - [Google Cloud Platform](docs/deployment_guides/gcp_deployment.md): Help setup your Cloud SQL instance, then build, push and deploy backend+frontend containers to Cloud Run.
 
+### Deploying to Azure
+
+You can deploy Toolkit with one click to Microsoft Azure Platform:
+
+[<img src="https://aka.ms/deploytoazurebutton" height="48px">](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fcohere-ai%2Fcohere-toolkit%2Fmain%2Fazuredeploy.json)
+
+This deployment type uses Azure Container Instances to host the Toolkit.
+After your deployment is complete click "Go to resource" button.
+1) Check the logs to see if the container is running successfully:
+   - click on the "Containers" button on the left side of the screen
+   - click on the container name
+   - click on "Logs" tab to see the logs
+2) Navigate to the "Overview" tab to see the FQDN of the container instance
+3) Open the \<FQDN\>:4000 in your browser to access the Toolkit
+
+### Deploying to Google Cloud Run
+
+Before deploying to Google Cloud Run, you'll need a postgres database accessible to your Google Cloud Project, authenticated by a username and password. You'll be prompted for a `DATABASE_URL` before the container builds.
+
+[![Run on Google Cloud](https://deploy.cloud.run/button.svg)](https://deploy.cloud.run)
+
 ## Setup for Development
 
 ### Setting up Poetry
@@ -155,6 +177,13 @@ poetry run black .
 poetry run isort .
 ```
 
+## Setting up the Environment Variables
+**Please confirm that you have at least one configuration of the Cohere Platform, SageMaker or Azure.**
+
+You have two methods to set up the environment variables:
+1. Run `make setup` and follow the instructions to configure it.
+2. Run `cp .env-template .env` and adjust the values in the `.env` file according to your situation.
+
 ### Setting up Your Local Database
 
 The docker-compose file should spin up a local `db` container with a PostgreSQL server. The first time you setup this project, and whenever new migrations are added, you will need to run:
@@ -209,6 +238,11 @@ make migrate
 
 ### Troubleshooting
 
+#### Community features are not accessible
+
+Make sure you add `USE_COMMUNITY_FEATURES=True` to your .env file.
+
+
 #### Multiple errors after running make dev for the first time
 
 Make sure you run the following command before running make dev:
@@ -217,6 +251,19 @@ Make sure you run the following command before running make dev:
 make migrate
 ```
 
+
+#### Error: pg_config executable not found.
+
+Make sure that all requirements including postgres are properly installed.
+
+If you're using MacOS, run:
+```bash
+brew install postgresql
+```
+
+For other operating systems, you can check the [postgres documentation](https://www.postgresql.org/download/).
+
+
 #### Debugging locally
 
 To debug any of the backend logic while the Docker containers are running, you can run:
@@ -241,6 +288,14 @@ it will allow you to debug.
 
 ## Component Guides
 
+### How to use community features
+
+By default, the toolkit runs without community tools or deployments. If you want to enable them, add the following to the .env file or use `make setup` to set this variable:
+
+```bash
+USE_COMMUNITY_FEATURES=True
+```
+
 ### How to add your own model deployment
 
 A model deployment is a running version of one of the Cohere command models. The Toolkit currently supports the model deployments:
@@ -252,9 +307,9 @@ A model deployment is a running version of one of the Cohere command models. The
 - SageMaker (model_deployments/sagemaker.py)
   - This deployment option calls into your SageMaker deployment. To create a SageMaker endpoint [follow the steps here](https://docs.cohere.com/docs/amazon-sagemaker-setup-guide), alternatively [follow a command notebook here](https://github.com/cohere-ai/cohere-aws/tree/main/notebooks/sagemaker). Note your region and endpoint name when executing the notebook as these will be needed in the environment variables.
 - To add your own deployment:
-  1. Create a deployment file, add it to [/model_deployments](https://github.com/cohere-ai/toolkit/tree/main/src/backend/chat/custom/model_deployments) folder, implement the function calls from `BaseDeployment` similar to the other deployments.
-  2. Add the deployment to [src/backend/config/deployments.py](https://github.com/cohere-ai/toolkit/blob/main/src/backend/config/deployments.py)
-  3. Add the option to [cli/main.py](https://github.com/cohere-ai/toolkit/blob/main/cli/main.py) and the environment variables required to the env template.
+  1. Create a deployment file, add it to [/community/model_deployments](https://github.com/cohere-ai/cohere-toolkit/tree/main/src/community/model_deployments) folder, implement the function calls from `BaseDeployment` similar to the other deployments.
+  2. Add the deployment to [src/community/config/deployments.py](https://github.com/cohere-ai/cohere-toolkit/blob/main/src/community/config/deployments.py)
+  3. Add the environment variables required to the env template.
 - To add a Cohere private deployment, use the steps above copying the cohere platform implementation changing the base_url for your private deployment and add in custom auth steps.
 
 ### How to call the backend as an API
@@ -273,11 +328,11 @@ curl --location 'http://localhost:8000/chat-stream' \
 
 ### How to add your own chat interface
 
-Currently the core chat interface is the Coral frontend. To add your own interface, take the steps above for call the backend as an API in your implementation and add it alongside `src/interfaces/coral_web`.
+Currently the core chat interface is the Coral frontend. To add your own interface, take the steps above for call the backend as an API in your implementation and add it alongside `src/community/interfaces/`.
 
 ### How to add a connector to the Toolkit
 
-If you have already created a [connector](https://docs.cohere.com/docs/connectors), it can be used in the toolkit with `ConnectorRetriever`. Add in your configuration and then add the definition in [config/tools.py](https://github.com/cohere-ai/toolkit/blob/main/src/backend/config/tools.py) similar to `Arxiv` implementation with the category `Category.DataLoader`. You can now use the Coral frontend and API with the connector.
+If you have already created a [connector](https://docs.cohere.com/docs/connectors), it can be used in the toolkit with `ConnectorRetriever`. Add in your configuration and then add the definition in [community/config/tools.py](https://github.com/cohere-ai/cohere-toolkit/blob/main/src/community/config/tools.py) similar to `Arxiv` implementation with the category `Category.DataLoader`. You can now use the Coral frontend and API with the connector.
 
 ### How to set up web search with the Toolkit
 

cli/main.py

@@ -3,6 +3,14 @@
 import inquirer
 from dotenv import set_key
 
+from backend.config.deployments import (
+    AVAILABLE_MODEL_DEPLOYMENTS as MANAGED_DEPLOYMENTS_SETUP,
+)
+from community.config.deployments import (
+    AVAILABLE_MODEL_DEPLOYMENTS as COMMUNITY_DEPLOYMENTS_SETUP,
+)
+from community.config.tools import COMMUNITY_TOOLS_SETUP
+
 
 class bcolors:
     OKCYAN = "\033[96m"
@@ -13,12 +21,6 @@ class bcolors:
     ENDC = "\033[0m"
 
 
-"""
-To add a new deployment, add a new DeploymentName enum and a new entry in the DEPLOYMENTS dictionary containing the secrets required for the deployment.
-If the deployment requires a custom implementation, add a new key "custom_implementation" with the function that will be called to set up the deployment.
-"""
-
-
 class DeploymentName(StrEnum):
     COHERE_PLATFORM = "Cohere Platform"
     SAGE_MAKER = "SageMaker"
@@ -83,14 +85,22 @@ def database_url_prompt(secrets):
 
 
 def deployment_prompt(secrets, configs):
-    for secret in configs["secrets"]:
-        if configs.get("custom_implementation"):
-            configs["custom_implementation"](secrets)
-        else:
-            value = inquirer.text(
-                f"Enter the value for {secret}", validate=lambda _, x: len(x) > 0
-            )
-            secrets[secret] = value
+    for secret in configs.env_vars:
+        value = inquirer.text(
+            f"Enter the value for {secret}", validate=lambda _, x: len(x) > 0
+        )
+        secrets[secret] = value
+
+
+def community_tools_prompt(secrets):
+    print_styled(
+        "🏘️ We have some community tools that you can set up. These tools are not required for the Cohere Toolkit to run."
+    )
+    use_community_features = inquirer.confirm(
+        "Do you want to set up community features (tools and deployments)?"
+    )
+    secrets["USE_COMMUNITY_FEATURES"] = use_community_features
+    return use_community_features
 
 
 def tool_prompt(secrets, name, configs):
@@ -129,23 +139,24 @@ def update_variable_prompt(_, variables_to_update):
 
 def write_env_file(secrets):
     for key, value in secrets.items():
-        print_styled(f"🔑 Setting {key} in {DOT_ENV_FILE_PATH} file.")
-        set_key(DOT_ENV_FILE_PATH, key, value)
+        set_key(DOT_ENV_FILE_PATH, key, str(value))
 
 
-def select_deployments_prompt(_):
+def select_deployments_prompt(deployments, _):
     print_styled("🚀 Let's set up your deployments.", bcolors.MAGENTA)
 
     deployments = inquirer.checkbox(
         "Select the deployments you want to set up",
-        choices=[deployment.value for deployment in DeploymentName],
+        choices=[deployment.value for deployment in deployments.keys()],
         default=["Cohere Platform"],
         validate=lambda _, x: len(x) > 0,
     )
     return deployments
 
 
 def wrap_up(deployments):
+    print_styled("✅ Your .env file has been set up.", bcolors.OKGREEN)
+
     print_styled(
         "🎉 You're all set up! You can now run 'make migrate' and 'make dev' to start the Cohere Toolkit. Make sure Docker is running.",
         bcolors.OKGREEN,
@@ -222,29 +233,6 @@ def show_examples():
 }
 
 
-DEPLOYMENTS = {
-    DeploymentName.COHERE_PLATFORM: {
-        "secrets": [
-            "COHERE_API_KEY",
-        ],
-        "custom_implementation": cohere_api_key_prompt,
-    },
-    DeploymentName.SAGE_MAKER: {
-        "secrets": [
-            "SAGE_MAKER_PROFILE_NAME",
-            "SAGE_MAKER_REGION_NAME",
-            "SAGE_MAKER_ENDPOINT_NAME",
-        ],
-    },
-    DeploymentName.AZURE: {
-        "secrets": [
-            "AZURE_API_KEY",
-            "AZURE_CHAT_ENDPOINT_URL",
-        ],
-    },
-}
-
-
 def start():
     secrets = {}
     print_styled(WELCOME_MESSAGE, bcolors.OKGREEN)
@@ -257,14 +245,22 @@ def start():
         implementation(secrets)
 
     # SET UP TOOLS
+    use_community_features = community_tools_prompt(secrets)
+    if use_community_features:
+        TOOLS.update(COMMUNITY_TOOLS_SETUP)
+
     for name, configs in TOOLS.items():
         tool_prompt(secrets, name, configs)
 
-    deployments = select_deployments_prompt(secrets)
-
     # SET UP ENVIRONMENT FOR DEPLOYMENTS
-    for deployment in deployments:
-        deployment_prompt(secrets, DEPLOYMENTS[deployment])
+    all_deployments = MANAGED_DEPLOYMENTS_SETUP.copy()
+    if use_community_features:
+        all_deployments.update(COMMUNITY_DEPLOYMENTS_SETUP)
+
+    selected_deployments = select_deployments_prompt(all_deployments, secrets)
+
+    for deployment in selected_deployments:
+        deployment_prompt(secrets, all_deployments[deployment])
 
     # SET UP .ENV FILE
     write_env_file(secrets)
@@ -273,10 +269,8 @@ def start():
     variables_to_update = review_variables_prompt(secrets)
     update_variable_prompt(secrets, variables_to_update)
 
-    print_styled("✅ Your .env file has been set up.", bcolors.OKGREEN)
-
     # WRAP UP
-    wrap_up(deployments)
+    wrap_up(selected_deployments)
 
     # SHOW SOME EXAMPLES
     show_examples()

docker-compose.yml

@@ -39,6 +39,13 @@ services:
           - __pycache__/
           - alembic/
           - data/
+        - action: sync
+          path: ./src/community
+          target: /workspace/src/community
+          ignore:
+          - __pycache__/
+          - alembic/
+          - data/
     stdin_open: true
     tty: true
     ports:

docker_scripts/env-defaults

@@ -10,4 +10,9 @@ DB_USER=${DB_USER:-}
 DB_PASS=${DB_PASS:-}
 DB_TEMPLATE=${DB_TEMPLATE:-template1}
 
-DB_EXTENSION=${DB_EXTENSION:-}
+DB_EXTENSION=${DB_EXTENSION:-}
+
+# Defaults for the toolkit
+export NEXT_PUBLIC_API_HOSTNAME=${NEXT_PUBLIC_API_HOSTNAME:-http://localhost:8000}
+export PYTHON_INTERPRETER_URL=${PYTHON_INTERPRETER_URL:-http://localhost:8080}
+export DATABASE_URL=${DATABASE_URL:-postgresql+psycopg2://postgre:postgre@localhost:5432/toolkit}