Qwen Coding Agent offers an advanced framework for developing applications utilizing large language models (LLMs), enhancing capabilities such as instruction following, tool usage, planning, and memory.

Introduction

Qwen Coding Agent provides a robust platform for building LLM applications, leveraging the advanced features of Qwen models (version 2.0 and above). It facilitates the development of intelligent agents capable of understanding and executing complex tasks by integrating functionalities like function calling, code interpretation, retrieval-augmented generation (RAG), and browser interaction. This framework serves as the backend for Qwen Chat, enabling seamless integration and deployment of AI-driven solutions.

Key Features

Function Calling

The framework supports dynamic function calling, allowing agents to execute predefined functions based on user instructions, thereby enhancing interactivity and task automation.

Code Interpreter

Qwen Coding Agent includes a code interpreter that enables agents to write, execute, and debug code in real-time, facilitating tasks such as data analysis, computation, and script execution.

Retrieval-Augmented Generation (RAG)

By integrating RAG, the framework allows agents to access and incorporate external knowledge sources during response generation, ensuring up-to-date and contextually relevant outputs.

Browser Assistant

The framework includes a browser assistant that enables agents to interact with web pages, retrieve information, and perform web-based tasks autonomously.

Use Cases

Automated Research

Agents can autonomously browse the internet to gather information, summarize findings, and present comprehensive reports, streamlining research processes.

Data Analysis

With the code interpreter, agents can process datasets, perform statistical analyses, and generate visualizations, aiding in data-driven decision-making.

Custom Assistants

Developers can create tailored AI assistants capable of handling specific tasks, such as scheduling, content creation, or customer support, by leveraging the framework's modular design. By utilizing Qwen Coding Agent, developers can create sophisticated AI applications that perform complex tasks, interact dynamically with users, and access real-time information, thereby enhancing operational efficiency and user engagement. Toggle navigation Explore By company size By use case By industry Topics Explore Repositories Available add-ons Search or jump to... Clear You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. openai / Public 10.1k Star 62.4k Code Issues 34 Pull requests 31 Actions Security Insights Code Issues Pull requests Actions Security Insights main main main .github .github articles articles examples examples azure azure book_translation book_translation chatgpt chatgpt dalle dalle data data evaluation evaluation fine-tuned_qa fine-tuned_qa gpt4o gpt4o multimodal multimodal o1 o1 object_oriented_agentic_approach object_oriented_agentic_approach responses_api responses_api third_party third_party utils utils vector_databases vector_databases voice_solutions voice_solutions Assistants_API_overview_python.ipynb Assistants_API_overview_python.ipynb Chat_finetuning_data_prep.ipynb Chat_finetuning_data_prep.ipynb Classification_using_embeddings.ipynb Classification_using_embeddings.ipynb Clustering.ipynb Clustering.ipynb Clustering_for_transaction_classification.ipynb Clustering_for_transaction_classification.ipynb Code_search_using_embeddings.ipynb Code_search_using_embeddings.ipynb Creating_slides_with_Assistants_API_and_DALL-E3.ipynb Creating_slides_with_Assistants_API_and_DALL-E3.ipynb Custom-LLM-as-a-Judge.ipynb Custom-LLM-as-a-Judge.ipynb Customizing_embeddings.ipynb Customizing_embeddings.ipynb Data_extraction_transformation.ipynb Data_extraction_transformation.ipynb Developing_hallucination_guardrails.ipynb Developing_hallucination_guardrails.ipynb Embedding_Wikipedia_articles_for_search.ipynb Embedding_Wikipedia_articles_for_search.ipynb Embedding_long_inputs.ipynb Embedding_long_inputs.ipynb Enhance_your_prompts_with_meta_prompting.ipynb Enhance_your_prompts_with_meta_prompting.ipynb Entity_extraction_for_long_documents.ipynb Entity_extraction_for_long_documents.ipynb File_Search_Responses.ipynb File_Search_Responses.ipynb Fine-tuned_classification.ipynb Fine-tuned_classification.ipynb Fine_tuning_for_function_calling.ipynb Fine_tuning_for_function_calling.ipynb Function_calling_finding_nearby_places.ipynb Function_calling_finding_nearby_places.ipynb Function_calling_with_an_OpenAPI_spec.ipynb Function_calling_with_an_OpenAPI_spec.ipynb GPT_with_vision_for_video_understanding.ipynb GPT_with_vision_for_video_understanding.ipynb Get_embeddings_from_dataset.ipynb Get_embeddings_from_dataset.ipynb How_to_build_a_tool-using_agent_with_Langchain.ipynb How_to_build_a_tool-using_agent_with_Langchain.ipynb How_to_build_an_agent_with_the_node_sdk.mdx How_to_build_an_agent_with_the_node_sdk.mdx How_to_call_functions_for_knowledge_retrieval.ipynb How_to_call_functions_for_knowledge_retrieval.ipynb How_to_call_functions_with_chat_models.ipynb How_to_call_functions_with_chat_models.ipynb How_to_combine_GPT4o_with_RAG_Outfit_Assistant.ipynb How_to_combine_GPT4o_with_RAG_Outfit_Assistant.ipynb How_to_count_tokens_with_tiktoken.ipynb How_to_count_tokens_with_tiktoken.ipynb How_to_finetune_chat_models.ipynb How_to_finetune_chat_models.ipynb How_to_format_inputs_to_ChatGPT_models.ipynb How_to_format_inputs_to_ChatGPT_models.ipynb How_to_handle_rate_limits.ipynb How_to_handle_rate_limits.ipynb How_to_stream_completions.ipynb How_to_stream_completions.ipynb How_to_use_guardrails.ipynb How_to_use_guardrails.ipynb How_to_use_moderation.ipynb How_to_use_moderation.ipynb Leveraging_model_distillation_to_fine-tune_a_model.ipynb Leveraging_model_distillation_to_fine-tune_a_model.ipynb Multiclass_classification_for_transactions.ipynb Multiclass_classification_for_transactions.ipynb Named_Entity_Recognition_to_enrich_text.ipynb Named_Entity_Recognition_to_enrich_text.ipynb Orchestrating_agents.ipynb Orchestrating_agents.ipynb Parse_PDF_docs_for_RAG.ipynb Parse_PDF_docs_for_RAG.ipynb Prompt_Caching101.ipynb Prompt_Caching101.ipynb Question_answering_using_a_search_API.ipynb Question_answering_using_a_search_API.ipynb Question_answering_using_embeddings.ipynb Question_answering_using_embeddings.ipynb RAG_with_graph_db.ipynb RAG_with_graph_db.ipynb Recommendation_using_embeddings.ipynb Recommendation_using_embeddings.ipynb Regression_using_embeddings.ipynb Regression_using_embeddings.ipynb Reproducible_outputs_with_the_seed_parameter.ipynb Reproducible_outputs_with_the_seed_parameter.ipynb SDG1.ipynb SDG1.ipynb Search_reranking_with_cross-encoders.ipynb Search_reranking_with_cross-encoders.ipynb Semantic_text_search_using_embeddings.ipynb Semantic_text_search_using_embeddings.ipynb Structured_Outputs_Intro.ipynb Structured_Outputs_Intro.ipynb Structured_outputs_multi_agent.ipynb Structured_outputs_multi_agent.ipynb Summarizing_long_documents.ipynb Summarizing_long_documents.ipynb Tag_caption_images_with_GPT4V.ipynb Tag_caption_images_with_GPT4V.ipynb Unit_test_writing_using_a_multi-step_prompt.ipynb Unit_test_writing_using_a_multi-step_prompt.ipynb Unit_test_writing_using_a_multi-step_prompt_with_older_completions_API.ipynb Unit_test_writing_using_a_multi-step_prompt_with_older_completions_API.ipynb User_and_product_embeddings.ipynb User_and_product_embeddings.ipynb Using_embeddings.ipynb Using_embeddings.ipynb Using_logprobs.ipynb Using_logprobs.ipynb Using_tool_required_for_customer_service.ipynb Using_tool_required_for_customer_service.ipynb Visualizing_embeddings_in_2D.ipynb Visualizing_embeddings_in_2D.ipynb Visualizing_embeddings_in_3D.ipynb Visualizing_embeddings_in_3D.ipynb Whisper_correct_misspelling.ipynb Whisper_correct_misspelling.ipynb Whisper_processing_guide.ipynb Whisper_processing_guide.ipynb Whisper_prompting_guide.ipynb Whisper_prompting_guide.ipynb Zero-shot_classification_with_embeddings.ipynb Zero-shot_classification_with_embeddings.ipynb api_request_parallel_processor.py api_request_parallel_processor.py batch_processing.ipynb batch_processing.ipynb completions_usage_api.ipynb completions_usage_api.ipynb custom_image_embedding_search.ipynb custom_image_embedding_search.ipynb images images .gitignore .gitignore CONTRIBUTING.md CONTRIBUTING.md LICENSE LICENSE README.md README.md authors.yaml authors.yaml registry.yaml registry.yaml / / Copy path Blame Blame Blame Blame Typo fixes - Update Orchestrating_agents.ipynb (#1640) Feb 14, 2025 347811f · Feb 14, 2025 History History History 887 lines (887 loc) · 30.4 KB / / Top Top Preview Code Blame 887 lines (887 loc) · 30.4 KB Raw Raw Loading Loading © 2025 GitHub, Inc. We read every piece of feedback, and take your input very seriously. To see all available qualifiers, see our documentation.