forked from phoenix-oss/llama-stack-mirror
8e316c9b1e
# What does this PR do? This is a combination of what was previously 3 separate PRs - #2069, #2075, and #2083. It turns out all 3 of those are needed to land a working function calling Responses implementation. The web search builtin tool was already working, but this wires in support for custom function calling. I ended up combining all three into one PR because they all had lots of merge conflicts, both with each other but also with #1806 that just landed. And, because landing any of them individually would have only left a partially working implementation merged. The new things added here are: * Storing of input items from previous responses and restoring of those input items when adding previous responses to the conversation state * Handling of multiple input item messages roles, not just "user" messages. * Support for custom tools passed into the Responses API to enable function calling outside of just the builtin websearch tool. Closes #2074 Closes #2080 ## Test Plan ### Unit Tests Several new unit tests were added, and they all pass. Ran via: ``` python -m pytest -s -v tests/unit/providers/agents/meta_reference/test_openai_responses.py ``` ### Responses API Verification Tests I ran our verification run.yaml against multiple providers to ensure we were getting a decent pass rate. Specifically, I ensured the new custom tool verification test passed across multiple providers and that the multi-turn examples passed across at least some of the providers (some providers struggle with the multi-turn workflows still). Running the stack setup for verification testing: ``` llama stack run --image-type venv tests/verifications/openai-api-verification-run.yaml ``` Together, passing 100% as an example: ``` pytest -s -v 'tests/verifications/openai_api/test_responses.py' --provider=together-llama-stack ``` ## Documentation We will need to start documenting the OpenAI APIs, but for now the Responses stuff is still rapidly evolving so delaying that. --------- Signed-off-by: Derek Higgins <derekh@redhat.com> Signed-off-by: Ben Browning <bbrownin@redhat.com> Co-authored-by: Derek Higgins <derekh@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
85 lines
2.6 KiB
YAML
85 lines
2.6 KiB
YAML
test_response_basic:
|
|
test_name: test_response_basic
|
|
test_params:
|
|
case:
|
|
- case_id: "earth"
|
|
input: "Which planet do humans live on?"
|
|
output: "earth"
|
|
- case_id: "saturn"
|
|
input: "Which planet has rings around it with a name starting with letter S?"
|
|
output: "saturn"
|
|
|
|
test_response_multi_turn:
|
|
test_name: test_response_multi_turn
|
|
test_params:
|
|
case:
|
|
- case_id: "earth"
|
|
turns:
|
|
- input: "Which planet do humans live on?"
|
|
output: "earth"
|
|
- input: "What is the name of the planet from your previous response?"
|
|
output: "earth"
|
|
|
|
test_response_web_search:
|
|
test_name: test_response_web_search
|
|
test_params:
|
|
case:
|
|
- case_id: "llama_experts"
|
|
input: "How many experts does the Llama 4 Maverick model have?"
|
|
tools:
|
|
- type: web_search
|
|
search_context_size: "low"
|
|
output: "128"
|
|
|
|
test_response_custom_tool:
|
|
test_name: test_response_custom_tool
|
|
test_params:
|
|
case:
|
|
- case_id: "sf_weather"
|
|
input: "What's the weather like in San Francisco?"
|
|
tools:
|
|
- type: function
|
|
name: get_weather
|
|
description: Get current temperature for a given location.
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
location:
|
|
description: "City and country e.g. Bogot\xE1, Colombia"
|
|
type: string
|
|
required:
|
|
- location
|
|
type: object
|
|
|
|
test_response_image:
|
|
test_name: test_response_image
|
|
test_params:
|
|
case:
|
|
- case_id: "llama_image"
|
|
input:
|
|
- role: user
|
|
content:
|
|
- type: input_text
|
|
text: "Identify the type of animal in this image."
|
|
- type: input_image
|
|
image_url: "https://upload.wikimedia.org/wikipedia/commons/f/f7/Llamas%2C_Vernagt-Stausee%2C_Italy.jpg"
|
|
output: "llama"
|
|
|
|
test_response_multi_turn_image:
|
|
test_name: test_response_multi_turn_image
|
|
test_params:
|
|
case:
|
|
- case_id: "llama_image_search"
|
|
turns:
|
|
- input:
|
|
- role: user
|
|
content:
|
|
- type: input_text
|
|
text: "What type of animal is in this image? Please respond with a single word that starts with the letter 'L'."
|
|
- type: input_image
|
|
image_url: "https://upload.wikimedia.org/wikipedia/commons/f/f7/Llamas%2C_Vernagt-Stausee%2C_Italy.jpg"
|
|
output: "llama"
|
|
- input: "Search the web using the search tool for the animal from the previous response. Your search query should be a single phrase that includes the animal's name and the words 'maverick' and 'scout'."
|
|
tools:
|
|
- type: web_search
|
|
output: "model"
|