dapr
/
dapr-agents
mirror of https://github.com/dapr/dapr-agents.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixed docs, and added build and social media links to the readme (#110) 

Signed-off-by: Bilgin Ibryam <bibryam@gmail.com>
This commit is contained in:
Bilgin Ibryam 2025-05-01 17:08:45 +01:00 committed by GitHub
parent 4dce1c0300
commit 889b7bf7ef
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
7 changed files with 21 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -1,5 +1,13 @@
# Dapr Agents: A Framework for Agentic AI Systems
[![PyPI - Version](https://img.shields.io/pypi/v/dapr-agents?style=flat&logo=pypi&logoColor=white&label=Latest%20version)](https://pypi.org/project/dapr-agents/)
[![PyPI - Downloads](https://img.shields.io/pypi/dm/dapr-agents?style=flat&logo=pypi&logoColor=white&label=Downloads)](https://pypi.org/project/dapr-agents/)
[![GitHub Actions Workflow Status](https://img.shields.io/github/actions/workflow/status/dapr/dapr-agents/.github%2Fworkflows%2Fbuild.yaml?branch=main&label=Build&logo=github)](https://github.com/dapr/dapr-agents/actions/workflows/build.yaml)
[![GitHub License](https://img.shields.io/github/license/dapr/dapr-agents?style=flat&label=License&logo=github)](https://github.com/dapr/dapr-agents/blob/main/LICENSE)
[![Discord](https://img.shields.io/discord/778680217417809931?label=Discord&style=flat&logo=discord)](http://bit.ly/dapr-discord)
[![YouTube Channel Views](https://img.shields.io/youtube/channel/views/UCtpSQ9BLB_3EXdWAUQYwnRA?style=flat&label=YouTube%20views&logo=youtube)](https://youtube.com/@daprdev)
[![X (formerly Twitter) Follow](https://img.shields.io/twitter/follow/daprdev?logo=x&style=flat)](https://twitter.com/daprdev)
Dapr Agents is a developer framework designed to build production-grade resilient AI agent systems that operate at scale. Built on top of the battle-tested Dapr project, it enables software developers to create AI agents that reason, act, and collaborate using Large Language Models (LLMs), while leveraging built-in observability and stateful workflow execution to guarantee agentic workflows complete successfully, no matter how complex.
![](./docs/img/logo-workflows.png)
@ -60,8 +68,8 @@ As a part of **CNCF**, Dapr Agents is vendor-neutral, eliminating concerns about
Here are some of the major features we're working on for the current quarter:
### Q2 2024
- **MCP Support** - Integration with Anthropic's MCP platform ([#50](https://github.com/dapr/dapr-agents/issues/50))
### Q2 2025
- **MCP Support** - Integration with Anthropic's MCP platform ([#50](https://github.com/dapr/dapr-agents/issues/50) ✅ )
- **Agent Interaction Tracing** - Enhanced observability of agent interactions with LLMs and tools ([#79](https://github.com/dapr/dapr-agents/issues/79))
- **Streaming LLM Output** - Real-time streaming capabilities for LLM responses ([#80](https://github.com/dapr/dapr-agents/issues/80))
- **HTTP Endpoint Tools** - Support for using Dapr's HTTP endpoint capabilities for tool calling ([#81](https://github.com/dapr/dapr-agents/issues/81))

2
docs/concepts/agents.md
View File

@ -44,7 +44,7 @@ In Dapr Agents, Agent Patterns define the built-in loops that allow agents to dy
### Tool Calling
Tool Calling is an essential pattern in autonomous agent design, allowing AI agents to interact dynamically with external tools based on user input. One reliable method for enabling this is through [OpenAI's Function Calling](https://platform.openai.com/docs/guides/function-calling?ref=blog.openthreatresearch.com) capabilities, introduced on [June 13, 2023](https://openai.com/index/function-calling-and-other-api-updates/?ref=blog.openthreatresearch.com). This feature allows developers to describe functions to models trained to generate structured JSON objects containing the necessary arguments for tool execution, based on user queries.
Tool Calling is an essential pattern in autonomous agent design, allowing AI agents to interact dynamically with external tools based on user input. One reliable method for enabling this is through [OpenAI's Function Calling](https://platform.openai.com/docs/guides/function-calling) capability. This feature allows developers to describe functions to models trained to generate structured JSON objects containing the necessary arguments for tool execution, based on user queries.
#### How It Works

4
docs/home/installation.md
View File

@ -62,7 +62,7 @@ Once running, access the Redis Insight interface at `http://localhost:5540/`
* Port: 6379
* Host (Linux): 172.17.0.1
* Host (Windows/Mac): docker.host.internal
* Host (Windows/Mac): host.docker.internal (example `host.docker.internal:6379`)
Redis Insight makes it easy to visualize and manage the data powering your agentic workflows, ensuring efficient debugging, monitoring, and optimization.
@ -83,7 +83,7 @@ AZURE_OPENAI_API_VERSION="azure_openai_api_version"
**NB!** the `AZURE_OPENAI_DEPLOYMENT` refers to the _model_, e.g., `gpt-4o`. `AZURE_OPENAI_API_VERSION` has been tested to work against `2024-08-01-preview`.
Then instansiate the agent(s) as well as the orchestrator as follows:
Then instantiate the agent(s) as well as the orchestrator as follows:
```python
from dapr_agents import AssistantAgent, OpenAIChatClient

4
docs/home/quickstarts/index.md
View File

@ -16,4 +16,6 @@
| [Agent Tool Call](https://github.com/dapr/dapr-agents/tree/main/quickstarts/03-agent-tool-call)<br>Build your first AI agent with custom tools by creating a practical weather assistant that fetches information and performs actions. | - **Tool Definition**: Creating reusable tools with the `@tool` decorator <br> - **Agent Configuration**: Setting up agents with roles, goals, and tools <br> - **Function Calling**: Enabling LLMs to execute Python functions |
| [Agentic Workflow](https://github.com/dapr/dapr-agents/tree/main/quickstarts/04-agentic-workflow)<br>Dive into stateful workflows with Dapr Agents by orchestrating sequential and parallel tasks through powerful workflow capabilities. | - **LLM-powered Tasks**: Using language models in workflows <br> - **Task Chaining**: Creating resilient multi-step processes executing in sequence <br> - **Fan-out/Fan-in**: Executing activities in parallel; then synchronizing these activities until all preceding activities have completed |
| [Multi-Agent Workflows](https://github.com/dapr/dapr-agents/tree/main/quickstarts/05-multi-agent-workflow-dapr-workflows)<br>Explore advanced event-driven workflows featuring a Lord of the Rings themed multi-agent system where autonomous agents collaborate to solve problems. | - **Multi-agent Systems**: Creating a network of specialized agents <br> - **Event-driven Architecture**: Implementing pub/sub messaging between agents <br> - **Actor Model**: Using Dapr Actors for stateful agent management <br> - **Workflow Orchestration**: Coordinating agents through different selection strategies <br><br> *Note: To see Actor-based workflow see [Multi-Agent Actors](https://github.com/dapr/dapr-agents/tree/main/quickstarts/05-multi-agent-workflow-actors).* |
| [Document Agent with Chainlit](https://github.com/dapr/dapr-agents/tree/main/quickstarts/06-document-agent-chainlit)<br>Create a conversational agent with an operational UI that can ingest, upload and learn unstructured documents while retaining long-term memory. | - **Conversational Document Agent**: Upload and converse over unstructured documents <br> - **Cloud Agnostic Storage**: Upload files to multiple storage providers |
| [Multi-Agent Workflow on Kubernetes](https://github.com/dapr/dapr-agents/tree/main/quickstarts/07-k8s-multi-agent-workflow)<br>Run multi-agent workflows in Kubernetes, demonstrating deployment and orchestration of event-driven agent systems in a containerized environment. | - **Kubernetes Deployment**: Running agents on Kubernetes <br> - **Container Orchestration**: Managing agent lifecycles with K8s <br> - **Service Communication**: Inter-agent communication in K8s |
| [Document Agent with Chainlit](https://github.com/dapr/dapr-agents/tree/main/quickstarts/06-document-agent-chainlit)<br>Create a conversational agent with an operational UI that can upload, and learn unstructured documents while retaining long-term memory. | - **Conversational Document Agent**: Upload and converse over unstructured documents <br> - **Cloud Agnostic Storage**: Upload files to multiple storage providers <br> - **Conversation Memory Storage**: Persists conversation history using external storage. |
| [Data Agent with MCP and Chainlit](https://github.com/dapr/dapr-agents/tree/main/quickstarts/08-data-agent-mcp-chainlit)<br>Build a conversational agent over a Postgres database using Model Composition Protocol (MCP) with a ChatGPT-like interface. | - **Database Querying**: Natural language queries to relational databases <br> - **MCP Integration**: Connecting to databases without DB-specific code <br> - **Data Analysis**: Complex data analysis through conversation |

2
mkdocs.yml
View File

@ -11,7 +11,7 @@ repo_url: https://github.com/dapr/dapr-agents
edit_uri: edit/main/docs/
# Copyright
copyright: Copyright &copy; 2024 Dapr maintainers
copyright: Copyright &copy; 2025 Dapr maintainers
theme:
name: material

6
quickstarts/06-document-agent-chainlit/README.md
View File

@ -7,7 +7,7 @@ This quickstart demonstrates how to build a fully functional, enterprise-ready a
- **Converse With Unstructured Data**: Users can upload documents and have them parsed, contextualized and be made chattable
- **Conversational Memory**: The agent maintains context across interactions in the user's [database of choice](https://docs.dapr.io/reference/components-reference/supported-state-stores/)
- **UI Interface**: Use an out-of-the-box, LLM-ready chat interface using [Chainlit](https://github.com/Chainlit/chainlit)
- **Cloud agnostic**: Uploads are handled automatically by Dapr and can be configured to target [different backends](https://docs.dapr.io/reference/components-reference/supported-bindings)
- **Cloud Agnostic**: Uploads are handled automatically by Dapr and can be configured to target [different backends](https://docs.dapr.io/reference/components-reference/supported-bindings)
## Prerequisites
@ -70,9 +70,9 @@ Upload a PDF of your choice, or use the example `red_foxes.pdf` file in this exa
#### Testing the agent's memory
If you exit the app and restart it, the agent will remember all the previously uploaded documents and conversations. The state is stored in the binding component configured in `./components/filestorage.yaml`.
If you exit the app and restart it, the agent will remember all the previously uploaded documents. The documents are stored in the binding component configured in `./components/filestorage.yaml`.
When you insall Dapr using `dapr init`, Redis is installed by default and this is where the conversation memory is saved. To change it, edit the `./components/conversationmemory.yaml` file.
When you install Dapr using `dapr init`, Redis is installed by default and this is where the conversation memory is saved. To change it, edit the `./components/conversationmemory.yaml` file.
## Summary

2
quickstarts/08-data-agent-mcp-chainlit/README.md
View File

@ -147,7 +147,7 @@ You can find the agent page at http://localhost:8001.
### Ask Questions
Now you can start talking to your data. If using the sample database, ask questons like `Show me all churned users from the past month` and `Can you identify the problematic area in our product that led to users churning?`.
Now you can start talking to your data. If using the sample database, ask questions like `Show me all churned users from the past month` and `Can you identify the problematic area in our product that led to users churning?`.
#### Testing the agent's memory