The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
[Feature] Add `render.com` deployment template (#1033)
Sidharth Mohanty737837ae0bd2
diff --git a/docs/deployment/render_com.mdx b/docs/deployment/render_com.mdxnew file mode 100644index 000000000..81ba7f6df--- /dev/null+++ b/docs/deployment/render_com.mdx@@ -0,0 +1,93 @@+---+title: 'Render.com'+description: 'Deploy your RAG application to render.com platform'+---++Embedchain has a nice and simple abstraction on top of the [render.com](https://render.com/) tools to let developers deploy RAG application to render.com platform seamlessly.++Follow the instructions given below to deploy your first application quickly:++## Step-1: Install `render` command line++<CodeGroup>+```bash OSX+brew tap render-oss/render+brew install render+```++```bash Linux+# Make sure you have deno installed -> https://docs.render.com/docs/cli#from-source-unsupported-operating-systems+git clone https://github.com/render-oss/render-cli+cd render-cli+make deps+deno task run+deno compile+```++```bash Windows+choco install rendercli+```+</CodeGroup>++In case you run into issues, refer to official [render.com docs](https://docs.render.com/docs/cli).++## Step-2 Create RAG application:++We provide a command line utility called `ec` in embedchain that inherits the template for `render.com` platform and help you deploy the app. Follow the instructions to create a render.com app using the template provided:+++```bash Create application+pip install embedchain+mkdir my-rag-app+ec create --template=render.com+```++This `create` command will open a browser window and ask you to login to your render.com account and will generate a directory structure like this:++```bash+├── app.py+├── .env+├── render.yaml+├── embedchain.json+└── requirements.txt+```++Feel free to edit the files as required.+- `app.py`: Contains API app code+- `.env`: Contains environment variables for production+- `render.yaml`: Contains render.com specific configuration for deployment (configure this according to your needs, follow [this](https://docs.render.com/docs/blueprint-spec) for more info)+- `embedchain.json`: Contains embedchain specific configuration for deployment (you don't need to configure this)+- `requirements.txt`: Contains python dependencies for your application++## Step-3: Test app locally++You can run the app locally by simply doing:++```bash Run locally+pip install -r requirements.txt+ec dev+```++## Step-4: Deploy to render.com++Before deploying to render.com, you only have to set up one thing.++In the render.yaml file, make sure to modify the repo key by inserting the URL of your Git repository where your application will be hosted. You can create a repository from [GitHub](https://github.com) or [GitLab](https://gitlab.com/users/sign_in).++After that, you're ready to deploy on render.com.++```bash Deploy app+ec deploy+```++When you run this, it should open up your render dashboard and you can see the app being deployed. You can find your hosted link over there only.++You can also check the logs, monitor app status etc on their dashboard by running command `render dashboard`.++<img src="/images/fly_io.png" />++## Seeking help?++If you run into issues with deployment, please feel free to reach out to us via any of the following methods:++<Snippet file="get-help.mdx" />diff --git a/docs/get-started/deployment.mdx b/docs/get-started/deployment.mdxindex 180938c80..3312dc154 100644--- a/docs/get-started/deployment.mdx+++ b/docs/get-started/deployment.mdx@@ -8,6 +8,7 @@ After successfully setting up and testing your RAG app locally, the next step is<CardGroup cols={4}><Card title="Fly.io" href="/deployment/fly_io"></Card><Card title="Modal.com" href="/deployment/modal_com"></Card>+ <Card title="Render.com" href="/deployment/render_com"></Card><Card title="Embedchain Platform" href="#option-1-deploy-on-embedchain-platform"></Card><Card title="Self-hosting" href="#option-2-self-hosting"></Card></CardGroup>diff --git a/docs/mint.json b/docs/mint.jsonindex 99223132a..57c0aa6a2 100644--- a/docs/mint.json+++ b/docs/mint.json@@ -88,7 +88,8 @@"pages": ["get-started/deployment","deployment/fly_io",- "deployment/modal_com"+ "deployment/modal_com",+ "deployment/render_com"]},{diff --git a/embedchain/cli.py b/embedchain/cli.pyindex ba555b195..11bab2150 100644--- a/embedchain/cli.py+++ b/embedchain/cli.py@@ -43,6 +43,7 @@ def setup_fly_io_app(extra_args):fly_launch_command = ["fly", "launch", "--region", "sjc", "--no-deploy"] + list(extra_args)try:console.print(f"🚀 [bold cyan]Running: {' '.join(fly_launch_command)}[/bold cyan]")+ shutil.move(".env.example", ".env")subprocess.run(fly_launch_command, check=True)console.print("✅ [bold green]'fly launch' executed successfully.[/bold green]")except subprocess.CalledProcessError as e:@@ -60,12 +61,41 @@ def setup_modal_com_app(extra_args):"""✅ [bold green]Modal setup already done. You can now install the dependencies by doing \n`pip install -r requirements.txt`[/bold green]""")- return- modal_setup_cmd = ["modal", "setup"] + list(extra_args)- console.print(f"🚀 [bold cyan]Running: {' '.join(modal_setup_cmd)}[/bold cyan]")- subprocess.run(modal_setup_cmd, check=True)+ else:+ modal_setup_cmd = ["modal", "setup"] + list(extra_args)+ console.print(f"🚀 [bold cyan]Running: {' '.join(modal_setup_cmd)}[/bold cyan]")+ subprocess.run(modal_setup_cmd, check=True)+ shutil.move(".env.example", ".env")+ console.print(+ """Great! Now you can install the dependencies by doing: \n+ `pip install -r requirements.txt`\n+ \n+ To run your app locally:\n+ `ec dev`+ """+ )+++def setup_render_com_app():+ render_setup_file = os.path.join(os.path.expanduser("~"), ".render/config.yaml")+ if os.path.exists(render_setup_file):+ console.print(+ """✅ [bold green]Render setup already done. You can now install the dependencies by doing \n+ `pip install -r requirements.txt`[/bold green]"""+ )+ else:+ render_setup_cmd = ["render", "config", "init"]+ console.print(f"🚀 [bold cyan]Running: {' '.join(render_setup_cmd)}[/bold cyan]")+ subprocess.run(render_setup_cmd, check=True)shutil.move(".env.example", ".env")- console.print("Great! Now you can install the dependencies by doing `pip install -r requirements.txt`")+ console.print(+ """Great! Now you can install the dependencies by doing: \n+ `pip install -r requirements.txt`\n+ \n+ To run your app locally:\n+ `ec dev`+ """+ )@cli.command()@@ -75,15 +105,14 @@ def create(template, extra_args):anonymous_telemetry.capture(event_name="ec_create", properties={"template_used": template})src_path = get_pkg_path_from_name(template)shutil.copytree(src_path, os.getcwd(), dirs_exist_ok=True)- env_sample_path = os.path.join(src_path, ".env.example")- if os.path.exists(env_sample_path):- shutil.copy(env_sample_path, os.path.join(os.getcwd(), ".env"))console.print(f"✅ [bold green]Successfully created app from template '{template}'.[/bold green]")if template == "fly.io":setup_fly_io_app(extra_args)elif template == "modal.com":setup_modal_com_app(extra_args)+ elif template == "render.com":+ setup_render_com_app()else:raise ValueError(f"Unknown template '{template}'.")@@ -123,6 +152,23 @@ def run_dev_modal_com():console.print("\n🛑 [bold yellow]FastAPI server stopped[/bold yellow]")+def run_dev_render_com(debug, host, port):+ uvicorn_command = ["uvicorn", "app:app"]++ if debug:+ uvicorn_command.append("--reload")++ uvicorn_command.extend(["--host", host, "--port", str(port)])++ try:+ console.print(f"🚀 [bold cyan]Running FastAPI app with command: {' '.join(uvicorn_command)}[/bold cyan]")+ subprocess.run(uvicorn_command, check=True)+ except subprocess.CalledProcessError as e:+ console.print(f"❌ [bold red]An error occurred: {e}[/bold red]")+ except KeyboardInterrupt:+ console.print("\n🛑 [bold yellow]FastAPI server stopped[/bold yellow]")++@cli.command()@click.option("--debug", is_flag=True, help="Enable or disable debug mode.")@click.option("--host", default="127.0.0.1", help="The host address to run the FastAPI app on.")@@ -138,6 +184,8 @@ def dev(debug, host, port):run_dev_fly_io(debug, host, port)elif template == "modal.com":run_dev_modal_com()+ elif template == "render.com":+ run_dev_render_com(debug, host, port)else:raise ValueError(f"Unknown template '{template}'.")@@ -212,6 +260,21 @@ def deploy_modal():)+def deploy_render():+ render_deploy_cmd = ["render", "blueprint", "launch"]++ try:+ console.print(f"🚀 [bold cyan]Running: {' '.join(render_deploy_cmd)}[/bold cyan]")+ subprocess.run(render_deploy_cmd, check=True)+ console.print("✅ [bold green]'render blueprint launch' executed successfully.[/bold green]")+ except subprocess.CalledProcessError as e:+ console.print(f"❌ [bold red]An error occurred: {e}[/bold red]")+ except FileNotFoundError:+ console.print(+ "❌ [bold red]'render' command not found. Please ensure Render CLI is installed and in your PATH.[/bold red]"+ )++@cli.command()def deploy():# Check for platform-specific files@@ -225,5 +288,7 @@ def deploy():deploy_fly()elif template == "modal.com":deploy_modal()+ elif template == "render.com":+ deploy_render()else:console.print("❌ [bold red]No recognized deployment platform found.[/bold red]")diff --git a/embedchain/deployment/render.com/.env.example b/embedchain/deployment/render.com/.env.examplenew file mode 100644index 000000000..b29363f94--- /dev/null+++ b/embedchain/deployment/render.com/.env.example@@ -0,0 +1 @@+OPENAI_API_KEY=sk-xxx\ No newline at end of filediff --git a/embedchain/deployment/render.com/.gitignore b/embedchain/deployment/render.com/.gitignorenew file mode 100644index 000000000..4c49bd78f--- /dev/null+++ b/embedchain/deployment/render.com/.gitignore@@ -0,0 +1 @@+.envdiff --git a/embedchain/deployment/render.com/app.py b/embedchain/deployment/render.com/app.pyindex 9d1094651..659e9a9cf 100644--- a/embedchain/deployment/render.com/app.py+++ b/embedchain/deployment/render.com/app.py@@ -1,58 +1,53 @@-import logging-import os--from flask import Flask, jsonify, request--from embedchain import Pipeline as App--app = Flask(__name__)--os.environ["OPENAI_API_KEY"] = "sk-xxx"--[email protected]("/add", methods=["POST"])-def add():- data = request.get_json()- data_type = data.get("data_type")- url_or_text = data.get("url_or_text")- if data_type and url_or_text:- try:- App().add(url_or_text, data_type=data_type)- return jsonify({"data": f"Added {data_type}: {url_or_text}"}), 200- except Exception:- logging.exception(f"Failed to add {data_type=}: {url_or_text=}")- return jsonify({"error": f"Failed to add {data_type}: {url_or_text}"}), 500- return jsonify({"error": "Invalid request. Please provide 'data_type' and 'url_or_text' in JSON format."}), 400--[email protected]("/query", methods=["POST"])-def query():- data = request.get_json()- question = data.get("question")- if question:- try:- response = App().query(question)- return jsonify({"data": response}), 200- except Exception:- logging.exception(f"Failed to query {question=}")- return jsonify({"error": "An error occurred. Please try again!"}), 500- return jsonify({"error": "Invalid request. Please provide 'question' in JSON format."}), 400--[email protected]("/chat", methods=["POST"])-def chat():- data = request.get_json()- question = data.get("question")- if question:- try:- response = App().chat(question)- return jsonify({"data": response}), 200- except Exception:- logging.exception(f"Failed to chat {question=}")- return jsonify({"error": "An error occurred. Please try again!"}), 500- return jsonify({"error": "Invalid request. Please provide 'question' in JSON format."}), 400--[email protected]("/api/python")-def hello_world():- return "<p>Hello, World!</p>"+from fastapi import FastAPI, responses+from pydantic import BaseModel++from embedchain import Pipeline++app = FastAPI(title="Embedchain FastAPI App")+embedchain_app = Pipeline()+++class SourceModel(BaseModel):+ source: str+++class QuestionModel(BaseModel):+ question: str++[email protected]("/add")+async def add_source(source_model: SourceModel):+ """+ Adds a new source to the EmbedChain app.+ Expects a JSON with a "source" key.+ """+ source = source_model.source+ embedchain_app.add(source)+ return {"message": f"Source '{source}' added successfully."}++[email protected]("/query")+async def handle_query(question_model: QuestionModel):+ """+ Handles a query to the EmbedChain app.+ Expects a JSON with a "question" key.+ """+ question = question_model.question+ answer = embedchain_app.query(question)+ return {"answer": answer}++[email protected]("/chat")+async def handle_chat(question_model: QuestionModel):+ """+ Handles a chat request to the EmbedChain app.+ Expects a JSON with a "question" key.+ """+ question = question_model.question+ response = embedchain_app.chat(question)+ return {"response": response}++[email protected]("/")+async def root():+ return responses.RedirectResponse(url="/docs")diff --git a/embedchain/deployment/render.com/render.yaml b/embedchain/deployment/render.com/render.yamlnew file mode 100644index 000000000..04ec5048b--- /dev/null+++ b/embedchain/deployment/render.com/render.yaml@@ -0,0 +1,16 @@+services:+ - type: web+ name: ec-render-app+ runtime: python+ repo: https://github.com/<your-username>/<repo-name>+ scaling:+ minInstances: 1+ maxInstances: 3+ targetMemoryPercent: 60 # optional if targetCPUPercent is set+ targetCPUPercent: 60 # optional if targetMemory is set+ buildCommand: pip install -r requirements.txt+ startCommand: uvicorn app:app --host 0.0.0.0+ envVars:+ - key: OPENAI_API_KEY+ value: sk-xxx+ autoDeploy: false # optionaldiff --git a/embedchain/deployment/render.com/requirements.txt b/embedchain/deployment/render.com/requirements.txtindex 5141b9042..3a7689298 100644--- a/embedchain/deployment/render.com/requirements.txt+++ b/embedchain/deployment/render.com/requirements.txt@@ -1,5 +1,4 @@-numpy==1.24.3-Flask==2.2.2-Werkzeug==2.2.2-gunicorn+fastapi==0.104.0+uvicorn==0.23.2embedchain+beautifulsoup4\ No newline at end of file