andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-07-23 07:45:10 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Unify flow streaming frame items

Browse Source
This commit is contained in:
lorenzejay
2026-06-29 14:50:17 -07:00
parent a48f45c917
commit 90b06a4523
15 changed files with 739 additions and 220 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
docs/edge/en/learn/streaming-flow-execution.mdx
View File

@@ -52,7 +52,7 @@ class ResearchFlow(Flow):
## Synchronous Streaming
When you call `kickoff()` on a flow with streaming enabled, it returns a `FlowStreamingOutput` object that you can iterate over:
When you call `kickoff()` on a flow with streaming enabled, it returns a stream session that yields ordered `StreamFrame` items:
```python Code
flow = ResearchFlow()
@@ -60,44 +60,43 @@ flow = ResearchFlow()
# Start streaming execution
streaming = flow.kickoff()
# Iterate over chunks as they arrive
for chunk in streaming:
print(chunk.content, end="", flush=True)
# Iterate over stream items as they arrive
for item in streaming:
print(item.content, end="", flush=True)
# Access the final result after streaming completes
result = streaming.result
print(f"\n\nFinal output: {result}")
```
### Stream Chunk Information
### Stream Item Information
Each chunk provides context about where it originated in the flow:
Each item provides both printable content and structured event data:
```python Code
streaming = flow.kickoff()
for chunk in streaming:
print(f"Agent: {chunk.agent_role}")
print(f"Task: {chunk.task_name}")
print(f"Content: {chunk.content}")
print(f"Type: {chunk.chunk_type}") # TEXT or TOOL_CALL
for item in streaming:
print(f"Channel: {item.channel}")
print(f"Type: {item.type}")
print(f"Content: {item.content}")
print(f"Event payload: {item.event}")
```
### Accessing Streaming Properties
The `FlowStreamingOutput` object provides useful properties and methods:
The stream session provides useful properties and methods:
```python Code
streaming = flow.kickoff()
# Iterate and collect chunks
for chunk in streaming:
print(chunk.content, end="", flush=True)
# Iterate and collect items
for item in streaming:
print(item.content, end="", flush=True)
# After iteration completes
print(f"\nCompleted: {streaming.is_completed}")
print(f"Full text: {streaming.get_full_text()}")
print(f"Total chunks: {len(streaming.chunks)}")
print(f"Total frames: {len(streaming.frames)}")
print(f"Final result: {streaming.result}")
```
@@ -114,9 +113,9 @@ async def stream_flow():
# Start async streaming
streaming = await flow.kickoff_async()
# Async iteration over chunks
async for chunk in streaming:
print(chunk.content, end="", flush=True)
# Async iteration over stream items
async for item in streaming:
print(item.content, end="", flush=True)
# Access final result
result = streaming.result
@@ -422,7 +421,7 @@ except Exception as e:
## Cancellation and Resource Cleanup
`FlowStreamingOutput` supports graceful cancellation so that in-flight work stops promptly when the consumer disconnects.
The stream session supports graceful cancellation so that in-flight work stops promptly when the consumer disconnects.
### Async Context Manager
@@ -430,8 +429,8 @@ except Exception as e:
streaming = await flow.kickoff_async()
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
async for item in streaming:
print(item.content, end="", flush=True)
```
### Explicit Cancellation
@@ -439,8 +438,8 @@ async with streaming:
```python Code
streaming = await flow.kickoff_async()
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
async for item in streaming:
print(item.content, end="", flush=True)
finally:
await streaming.aclose() # async
# streaming.close() # sync equivalent
@@ -451,7 +450,7 @@ After cancellation, `streaming.is_cancelled` and `streaming.is_completed` are bo
## Important Notes
- Streaming automatically enables LLM streaming for any crews used within the flow
- You must iterate through all chunks before accessing the `.result` property
- You must iterate through all stream items before accessing the `.result` property
- Streaming works with both structured and unstructured flow state
- Flow streaming captures output from all crews and LLM calls in the flow
- Each chunk includes context about which agent and task generated it
@@ -475,4 +474,4 @@ result = streaming.result
print(f"\nFlow complete! View structure at: research_flow.html")
```
By leveraging flow streaming, you can build sophisticated, responsive applications that provide users with real-time visibility into complex multi-stage workflows, making your AI automations more transparent and engaging.
By leveraging flow streaming, you can build sophisticated, responsive applications that provide users with real-time visibility into complex multi-stage workflows, making your AI automations more transparent and engaging.

46
docs/edge/en/learn/streaming-runtime-contract.mdx
View File

@@ -28,6 +28,8 @@ frame.timestamp # event timestamp
frame.parent_id # parent event id, when available
frame.previous_id # previous event id, when available
frame.data # event payload
frame.event # alias for frame.data
frame.content # printable text for token-like frames, otherwise ""
```
The `channel` field is the fastest way to route frames in consumers:
@@ -45,7 +47,7 @@ The `channel` field is the fastest way to route frames in consumers:
## Stream a Flow
Use `stream_events()` to run a Flow and iterate over all frames:
Set `stream=True` on a Flow to make `kickoff()` return a stream session:
```python
from crewai.flow import Flow, start
@@ -57,18 +59,22 @@ class ReportFlow(Flow):
return "done"
flow = ReportFlow()
stream = flow.stream_events()
flow = ReportFlow(stream=True)
stream = flow.kickoff()
with stream:
for frame in stream.events:
print(frame.seq, frame.channel, frame.type, frame.data)
for chunk in stream:
print(chunk.content, end="", flush=True)
if chunk.type == "tool_usage_started":
print(chunk.event["tool_name"])
result = stream.result
```
You must consume the stream before reading `stream.result`. Accessing the result early raises a `RuntimeError` so consumers do not accidentally treat a partial run as complete.
You can also call `flow.stream_events(...)` directly when you want streaming for a single invocation without setting `stream=True` on the Flow instance.
## Filter by Channel
`StreamSession` exposes channel projections that preserve global frame order within the selected channel:
@@ -78,7 +84,7 @@ stream = flow.stream_events()
with stream:
for frame in stream.llm:
print(frame.data.get("chunk", ""), end="", flush=True)
print(frame.content, end="", flush=True)
result = stream.result
```
@@ -105,8 +111,8 @@ flow = ReportFlow()
stream = flow.astream()
async with stream:
async for frame in stream.events:
print(frame.channel, frame.type)
async for chunk in stream.events:
print(chunk.channel, chunk.type, chunk.content)
result = stream.result
```
@@ -115,14 +121,14 @@ The async session has the same projections as the sync session.
## Stream a Direct LLM Call
`llm.call(...)` still returns the final assembled result. Use `llm.stream_call(...)` when you want to iterate over chunks as they arrive:
`llm.call(...)` still returns the final assembled result. Use `llm.stream_events(...)` when you want to iterate over chunks as they arrive while keeping the structured event payload:
```python
from crewai import LLM
llm = LLM(model="gpt-4o-mini")
chunks = llm.stream_call(
stream = llm.stream_events(
messages=[
{
"role": "user",
@@ -131,26 +137,14 @@ chunks = llm.stream_call(
]
)
for chunk in chunks:
print(chunk.content, end="", flush=True)
result = chunks.result
```
Use `llm.stream_events(...)` when a runtime needs the full `StreamFrame` envelope rather than text chunks:
```python
stream = llm.stream_events("Explain CrewAI streaming in two short sentences.")
with stream:
for frame in stream.llm:
if frame.type == "llm_stream_chunk":
print(frame.data.get("chunk", ""), end="", flush=True)
for chunk in stream:
print(chunk.content, end="", flush=True)
result = stream.result
```
Both methods temporarily enable streaming for the wrapped call and restore the LLM's previous `stream` setting afterward. Provider integrations continue to emit the underlying LLM stream events; these helpers provide a common iterator API over those events for every LLM provider.
`llm.stream_events(...)` temporarily enables streaming for the wrapped call and restores the LLM's previous `stream` setting afterward. Provider integrations continue to emit the underlying LLM stream events; this helper provides a common iterator API over those events for every LLM provider.
## Conversational Turns
@@ -172,7 +166,7 @@ stream = flow.stream_turn("What can you help me with?", session_id="session-1")
with stream:
for frame in stream.events:
if frame.channel == "llm" and frame.type == "llm_stream_chunk":
print(frame.data.get("chunk", ""), end="", flush=True)
print(frame.content, end="", flush=True)
reply = stream.result
```