phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 05:00:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: more code-interpreter removal

Browse source 
Final removal piece of code-interpreter provider.

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-05-12 20:36:44 +02:00
parent e3ad17ec5e
commit c1f53ddc16
No known key found for this signature in database
25 changed files with 7 additions and 346 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/models/llama/llama3_2/prompts_text.py
View file

@ -17,7 +17,6 @@ from llama_stack.models.llama.datatypes import (
from ..prompt_format import (
TextCompletionContent,
UseCase,
llama3_1_builtin_code_interpreter_dialog,
)
@ -157,22 +156,6 @@ def usecases():
"""
),
),
UseCase(
title="Code Interpreter",
description=textwrap.dedent(
"""
Code Interpreter continues to work in 3.2 text models similar to Llama 3.1 model family.
Here is an example,
"""
),
dialogs=[llama3_1_builtin_code_interpreter_dialog()],
notes=textwrap.dedent(
"""
- Note `Environment: ipython` in the system prompt.
- Note that the response starts with `<|python_tag|>` and ends with `<|eom_id|>`
"""
),
),
UseCase(
title="Zero shot function calling E2E format",
description=textwrap.dedent(

2
llama_stack/models/llama/llama3_2/prompts_vision.py
View file

@ -62,7 +62,6 @@ def usecases():
Use `Environment: ipython` to enable tools.
Add `Tools: {{tool_name1}},{{tool_name2}}` for each of the builtin tools.
The same builtin tools as Llama3.1 are available,
- code_interpreter (for executing python code)
- brave_search (to search the web)
- wolfram_alpha (for querying wolfram alpha for mathematical questions)
""",
@ -72,7 +71,6 @@ def usecases():
"""
- Note the `<|python_tag|>` before `brave_search` function call.
- The `<|eom_id|>` tag is used to indicate the end of the message.
- Similar to Llama3.1, code_interpreter is not explicitly mentioned but is enabled via `Environment: ipython`.
- Tool Calling does NOT work with images in the prompt as of now.
"""
),

2
llama_stack/models/llama/llama3_2/vision_prompt_format.md
View file

@ -62,7 +62,6 @@ Llama3.2 vision models follow the same tool calling format as Llama3.1 models wh
Use `Environment: ipython` to enable tools.
Add `Tools: {{tool_name1}},{{tool_name2}}` for each of the builtin tools.
The same builtin tools as Llama3.1 are available,
- code_interpreter (for executing python code)
- brave_search (to search the web)
- wolfram_alpha (for querying wolfram alpha for mathematical questions)
@ -94,7 +93,6 @@ Search the web for the latest price of 1oz gold?<|eot_id|><|start_header_id|>ass
- Note the `<|python_tag|>` before `brave_search` function call.
- The `<|eom_id|>` tag is used to indicate the end of the message.
- Similar to Llama3.1, code_interpreter is not explicitly mentioned but is enabled via `Environment: ipython`.
- Tool Calling does NOT work with images in the prompt as of now.