Optimize prompts for cost-efficiency #70
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Optimize prompts for cost-efficiency across multiple files. * **`computer_use_demo/gui_agent/anthropic_agent.py`** - Remove unnecessary print statement. * **`computer_use_demo/gui_agent/planner/api_vlm_planner.py`** - Remove unnecessary newline. * **`computer_use_demo/gui_agent/planner/local_vlm_planner.py`** - Correct syntax error in dictionary. - Remove unnecessary newline. * **`computer_use_demo/gui_agent/llm_utils/oai.py`** - Remove unnecessary comments and debug statements. - Optimize prompt structure to minimize token usage. * **`computer_use_demo/gui_agent/llm_utils/qwen.py`** - Remove unnecessary comments and debug statements. - Optimize prompt structure to minimize token usage. - Implement `is_image_path` and `encode_image` functions. * **`computer_use_demo/gui_agent/llm_utils/run_llm.py`** - Add `optimize_prompt` function to minimize token usage. - Integrate `optimize_prompt` function into the main logic. * **`computer_use_demo/gui_agent/showui_agent.py`** - Remove unnecessary newline. * **`computer_use_demo/loop.py`** - Remove commented-out code and unnecessary newlines.
* **Tasks** - Define test task using pytest - Define build task to install requirements - Define launch task to run app.py
* **`computer_use_demo/gui_agent/llm_utils/run_llm.py`** - Import `run_qwen` from `.qwen` - Add `qwen` series support in `run_llm` function * **`app.py`** - Add new logic for LLM to control handhelds - Add more models from big tech companies - Add SOTA features - Fix indentation error at line 599 * **`pyproject.toml`** - Add `testpaths` configuration * **`tests`** - Add example test cases
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Optimize prompts for cost-efficiency across multiple files.
computer_use_demo/gui_agent/anthropic_agent.pycomputer_use_demo/gui_agent/planner/api_vlm_planner.pycomputer_use_demo/gui_agent/planner/local_vlm_planner.pycomputer_use_demo/gui_agent/llm_utils/oai.pycomputer_use_demo/gui_agent/llm_utils/qwen.pyis_image_pathandencode_imagefunctions.computer_use_demo/gui_agent/llm_utils/run_llm.pyoptimize_promptfunction to minimize token usage.optimize_promptfunction into the main logic.computer_use_demo/gui_agent/showui_agent.pycomputer_use_demo/loop.py