[pull] main from meta-llama:main #2
Open
Conversation
This file contains 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
Fixed some typo errors
Replaces `on_event` with `lifespan`
* A single distro url to rule them all * fix typo * gut out the llama_agentic_system implementation and move it to toolchain there is `llama_agentic_system` sub-directory anymore * custom tool naming * updated var names to refer to distribution; updated requirements * make test run consistently * Updated README * Remove FP8 section, since it is rolled in now * Show safety configuration * Shorter subtitle lol * kill the dev dependencies * added ollama distro details to readme * Clarify Ollama instructions --------- Co-authored-by: Hardik Shah <[email protected]> Co-authored-by: dltn <[email protected]>
small updates to readme
1. and extra $ sign was there which caused problem if someone directly copies it 2. it is local-ollama not ollama-local
added note that installation of distributions requires conda.
Co-authored-by: Hardik Shah <[email protected]>
* update tool imports * system_id -> agent_id * Use the updated agentic system utilities * add a RAG script * Show two ways to run RAG * Update README for the new "llama stack" stuff * Add common/client_utils and restructure the scripts Push configuration to the very top so it is very clear * Update the RAG scripts * Fixed RAG scripts * update tests * Update README with updated `llama stack` commands * stack start -> stack run * Change build name --------- Co-authored-by: Hardik Shah <[email protected]> Co-authored-by: Ashwin Bharambe <[email protected]>
Updated docs for new repo name and purpose
* add safety sdk * more messages
# What does this PR do? Add demo app using Kotlin SDK v0.0.54 ## Feature/Issue validation/testing/test plan Tested in Android Studio emulator and real Android devices such as S24, OnePlus ## Sources Details in readme ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [X] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [X] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉! --------- Co-authored-by: Chirag Modi <[email protected]>
- 0.0.54 missed out on local module dependencies 0.0.54.1 fixes it - We don't need prebuilt script in app to download ET aar, that is handled from the lib side - Update readme to latest version
Make DocQA work again and improve it: - model names are wrong (and subtly missing a hyphen) - 5000 is a reserved port on Mac, where a lot of people will want to run this – change to 5001 - Then, propagate `LLAMA_STACK_PORT` everywhere, as 5000 is hardcoded in some places - Smarter wait loop for llama stack instead of `sleep 30` (attempted to do the same for `ollama`, but ran out of time)
# What does this PR do? Fixing a bug where getRecentSavedTextMessages() would only get CONVERSATION_HISTORY_MESSAGE_LOOKBACK - 1. Now with this fix, function will retrieve CONVERSATION_HISTORY_MESSAGE_LOOKBACK # of conversations. ## Feature/Issue validation/testing/test plan 1. Tested with Llama 3.2 3B and confirmed with logs ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [X] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉!
# What does this PR do? - async -> sync from event logger update in SDK ## Feature/Issue validation/testing/test plan <img width="1071" alt="image" src="https://github.com/user-attachments/assets/49b10279-84cd-4cb3-890f-b001236d2634" /> <img width="1065" alt="image" src="https://github.com/user-attachments/assets/7e38a8f7-4a72-46d3-9a3e-4c51dc1de477" /> ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉!
# What does this PR do? - 0.0.58 now supports streaming. Updating the app side to support that. - I am leveraging onStreamReceived() as a callback mechanism to get the data back from SDK to mainActivitiy ## Feature/Issue validation/testing/test plan https://github.com/user-attachments/assets/8f7c579c-501b-4800-8068-ab58b1f3fa98 ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉! --------- Co-authored-by: Chester Hu <[email protected]>
# What does this PR do? - Add custom tool calling for local inferencing - Handles multiple custom tool calls (example prompt: "create a calendar event for 5pm today for a dr appointment and another calendar event at 7pm today for a dinner") - Show "..." when prefill/inferencing is happening - Fix in `getRecentSavedTextMessages()` to ignore the temporary empty response ## Feature/Issue validation/testing/test plan https://github.com/user-attachments/assets/d6b2fc51-8cd9-47f1-84e1-2fe0d3b57f71 ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [X] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉!
# What does this PR do? -- see corresponding PR in meta-llama/llama-stack#638 **Why** - The scripts in `/examples` is too adhoc, and we have new Notebooks showing the same API calls. - Aim of `llama-stack-apps`: Consolidated, standalone, canonical apps in llama-stack-apps with tests - Clean up examples which we will not maintain; reduce the surface area to the minimal showcases **What** - Delete `/examples/inference` & `/examples/memory` - Move all scripts to unit tests (added in meta-llama/llama-stack#638) - SDK sync in the future will just require running pytests **Side notes** - `bwrap` not available on Mac so code_interpreter will not work ## Feature/Issue validation/testing/test plan - see meta-llama/llama-stack#638 ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉!
# What does this PR do? Fixes broken link and two typos: <img width="460" alt="Screenshot 2024-12-17 at 19 28 28" src="https://github.com/user-attachments/assets/4d7f6d00-c579-4920-8e7a-847ad56359d2" /> ## Before submitting - [x] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? --------- Co-authored-by: Aidan Do <[email protected]>
See meta-llama/llama-stack#635 in llama-stack
Summary: Ran the command only to find all-MiniLM-L6-v2 is being selected by default. ``` python -m examples.agent_store.app localhost 5000 Using model: all-MiniLM-L6-v2 * Running on local URL: http://0.0.0.0:7860 ``` Test Plan: Run the command with the change and validate that meta-llama/Llama-3.2-3B-Instruct is used instead ``` python -m examples.agent_store.app localhost 5000 Using model: meta-llama/Llama-3.2-3B-Instruct * Running on local URL: http://0.0.0.0:7860 ```
# What does this PR do? Updates for new tool def, new sampling params and other changes. Test plan: python -m examples.agents.hello $LOCALHOST $PORT python -m examples.agents.inflation $LOCALHOST $PORT python -m examples.agents.podcast_transcript $LOCALHOST $PORT python -m examples.agents.rag_as_attachments $LOCALHOST $PORT python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT --------- Co-authored-by: Ashwin Bharambe <[email protected]>
# What does this PR do? Add additional examples in Android app to support Kotlin SDK v0.1.0. From API compatibility to Agent use cases and image reasoning ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [X] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉! --------- Co-authored-by: cmodi-meta <[email protected]> Co-authored-by: Riandy Riandy <[email protected]>
#155) # What does this PR do? Added the quick iOS Llama Stack demo for using remote inference with Llama Stack 0.1.0. Closes # (issue) ## Feature/Issue validation/testing/test plan Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced. Please also list any relevant details for your test configuration or test plan. - [ ] Test A Logs for Test A - [ ] Test B Logs for Test B ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉! --------- Co-authored-by: Ashwin Bharambe <[email protected]>
I found that the model would hallucinate on the ticker symbol with the current prompt. Update to make it more stable. Co-authored-by: Eric Huang (AI Platform) <[email protected]>
Update Android README.md on compatible ET version during model export
# What does this PR do? Add clear instruction to import and build LocalInf project. Clear confusion. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [X] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉!
# What does this PR do? To work with the updated LocalInferenceImpl [here](meta-llama/llama-stack#911). Closes # (issue) ## Feature/Issue validation/testing/test plan Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced. Please also list any relevant details for your test configuration or test plan. - [ ] Test A Logs for Test A - [ ] Test B Logs for Test B ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack-apps/blob/main/CONTRIBUTING.md#pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? Thanks for contributing 🎉!
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.
See Commits and Changes for more details.
Created by
pull[bot]
Can you help keep this open source service alive? 💖 Please sponsor : )