Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -189,6 +189,9 @@ cython_debug/
# you could uncomment the following to ignore the enitre vscode folder
.vscode/

# Emacs backup files
*~

# Ruff stuff:
.ruff_cache/

Expand Down
2 changes: 1 addition & 1 deletion docs/deep-dive/birds-eye-view.md
Original file line number Diff line number Diff line change
Expand Up @@ -496,7 +496,7 @@ flowchart TD
Continuous learning keeps the algorithm loop running while runners report tasks and spans opportunistically. Key differences from batch mode:

1. The algorithm does not enqueue rollouts from a fixed dataset. Runners report tasks/rollouts and spans spontaneously.
2. The algorithm can wait for rollouts with a expected set of rollout IDs, but more oftenly polls for new rollouts and spans or waits for a count to arrive.
2. The algorithm can wait for rollouts with a expected set of rollout IDs, but more often polls for new rollouts and spans or waits for a count to arrive.
3. The [`Runner`][agentlightning.Runner] processes one rollout at a time via [`step(task)`][agentlightning.Runner.step] instead of exhausting a task queue. It notifies the store when starting a rollout so the store records it.
4. A user or higher-level loop controls which resources the next step uses and when to retry.

Expand Down
2 changes: 1 addition & 1 deletion examples/apo/apo_custom_algorithm.py
Original file line number Diff line number Diff line change
Expand Up @@ -141,7 +141,7 @@ async def llm_judge(task: str, output: Optional[str]) -> float:
try:
content = result.choices[0].message.content
if content is None:
console.print(f"[bold blue][Judge][/bold blue] Judge retured no content: {result}")
console.print(f"[bold blue][Judge][/bold blue] Judge returned no content: {result}")
return 0.0
score = float(content)
console.print(f"[bold blue][Judge][/bold blue] Judge returned score: {score}")
Expand Down
2 changes: 1 addition & 1 deletion examples/spider/spider_eval/exec_eval.py
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@ def replace_cur_year(query: str) -> str:
def get_cursor_from_path(sqlite_path: str):
try:
if not os.path.exists(sqlite_path):
print("Openning a new connection %s" % sqlite_path)
print("Opening a new connection %s" % sqlite_path)
connection = sqlite3.connect(sqlite_path)
except Exception as e:
print(sqlite_path)
Expand Down