mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-06-02 19:35:12 +02:00
Update to add streaming tests (#600)
This commit is contained in:
cybermaggedon
GitHub
parent
f0c95a4c5e
commit
f79d0603f7
9 changed files with 1062 additions and 57 deletions
|
|
@ -480,11 +480,15 @@ def streaming_chunk_collector():
|
|||
class ChunkCollector:
|
||||
def __init__(self):
|
||||
self.chunks = []
|
||||
self.end_of_stream_flags = []
|
||||
self.complete = False
|
||||
|
||||
async def collect(self, chunk):
|
||||
"""Async callback to collect chunks"""
|
||||
async def collect(self, chunk, end_of_stream=False):
|
||||
"""Async callback to collect chunks with end_of_stream flag"""
|
||||
self.chunks.append(chunk)
|
||||
self.end_of_stream_flags.append(end_of_stream)
|
||||
if end_of_stream:
|
||||
self.complete = True
|
||||
|
||||
def get_full_text(self):
|
||||
"""Concatenate all chunk content"""
|
||||
|
|
@ -496,6 +500,14 @@ def streaming_chunk_collector():
|
|||
return [c.get("chunk_type") for c in self.chunks]
|
||||
return []
|
||||
|
||||
def verify_streaming_protocol(self):
|
||||
"""Verify that streaming protocol is correct"""
|
||||
assert len(self.chunks) > 0, "Should have received at least one chunk"
|
||||
assert len(self.chunks) == len(self.end_of_stream_flags), "Each chunk should have an end_of_stream flag"
|
||||
assert self.end_of_stream_flags.count(True) == 1, "Exactly one chunk should have end_of_stream=True"
|
||||
assert self.end_of_stream_flags[-1] is True, "Last chunk should have end_of_stream=True"
|
||||
assert self.complete is True, "Should be marked complete after final chunk"
|
||||
|
||||
return ChunkCollector
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -46,9 +46,16 @@ class TestDocumentRagStreaming:
|
|||
full_text = "Machine learning is a subset of artificial intelligence that focuses on algorithms that learn from data."
|
||||
|
||||
if streaming and chunk_callback:
|
||||
# Simulate streaming chunks
|
||||
# Simulate streaming chunks with end_of_stream flags
|
||||
chunks = []
|
||||
async for chunk in mock_streaming_llm_response():
|
||||
await chunk_callback(chunk)
|
||||
chunks.append(chunk)
|
||||
|
||||
# Send all chunks with end_of_stream=False except the last
|
||||
for i, chunk in enumerate(chunks):
|
||||
is_final = (i == len(chunks) - 1)
|
||||
await chunk_callback(chunk, is_final)
|
||||
|
||||
return full_text
|
||||
else:
|
||||
# Non-streaming response - same text
|
||||
|
|
@ -89,6 +96,9 @@ class TestDocumentRagStreaming:
|
|||
assert_streaming_chunks_valid(collector.chunks, min_chunks=1)
|
||||
assert_callback_invoked(AsyncMock(call_count=len(collector.chunks)), min_calls=1)
|
||||
|
||||
# Verify streaming protocol compliance
|
||||
collector.verify_streaming_protocol()
|
||||
|
||||
# Verify full response matches concatenated chunks
|
||||
full_from_chunks = collector.get_full_text()
|
||||
assert result == full_from_chunks
|
||||
|
|
@ -117,7 +127,7 @@ class TestDocumentRagStreaming:
|
|||
# Act - Streaming
|
||||
streaming_chunks = []
|
||||
|
||||
async def collect(chunk):
|
||||
async def collect(chunk, end_of_stream):
|
||||
streaming_chunks.append(chunk)
|
||||
|
||||
streaming_result = await document_rag_streaming.query(
|
||||
|
|
|
|||
|
|
@ -59,9 +59,16 @@ class TestGraphRagStreaming:
|
|||
full_text = "Machine learning is a subset of artificial intelligence that focuses on algorithms that learn from data."
|
||||
|
||||
if streaming and chunk_callback:
|
||||
# Simulate streaming chunks
|
||||
# Simulate streaming chunks with end_of_stream flags
|
||||
chunks = []
|
||||
async for chunk in mock_streaming_llm_response():
|
||||
await chunk_callback(chunk)
|
||||
chunks.append(chunk)
|
||||
|
||||
# Send all chunks with end_of_stream=False except the last
|
||||
for i, chunk in enumerate(chunks):
|
||||
is_final = (i == len(chunks) - 1)
|
||||
await chunk_callback(chunk, is_final)
|
||||
|
||||
return full_text
|
||||
else:
|
||||
# Non-streaming response - same text
|
||||
|
|
@ -102,6 +109,9 @@ class TestGraphRagStreaming:
|
|||
assert_streaming_chunks_valid(collector.chunks, min_chunks=1)
|
||||
assert_callback_invoked(AsyncMock(call_count=len(collector.chunks)), min_calls=1)
|
||||
|
||||
# Verify streaming protocol compliance
|
||||
collector.verify_streaming_protocol()
|
||||
|
||||
# Verify full response matches concatenated chunks
|
||||
full_from_chunks = collector.get_full_text()
|
||||
assert result == full_from_chunks
|
||||
|
|
@ -128,7 +138,7 @@ class TestGraphRagStreaming:
|
|||
# Act - Streaming
|
||||
streaming_chunks = []
|
||||
|
||||
async def collect(chunk):
|
||||
async def collect(chunk, end_of_stream):
|
||||
streaming_chunks.append(chunk)
|
||||
|
||||
streaming_result = await graph_rag_streaming.query(
|
||||
|
|
|
|||
351
tests/integration/test_rag_streaming_protocol.py
Normal file
351
tests/integration/test_rag_streaming_protocol.py
Normal file
|
|
@ -0,0 +1,351 @@
|
|||
"""
|
||||
Integration tests for RAG service streaming protocol compliance.
|
||||
|
||||
These tests verify that RAG services correctly forward end_of_stream flags
|
||||
and don't duplicate final chunks, ensuring proper streaming semantics.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import AsyncMock, MagicMock, call
|
||||
from trustgraph.retrieval.graph_rag.graph_rag import GraphRag
|
||||
from trustgraph.retrieval.document_rag.document_rag import DocumentRag
|
||||
|
||||
|
||||
class TestGraphRagStreamingProtocol:
|
||||
"""Integration tests for GraphRAG streaming protocol"""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_embeddings_client(self):
|
||||
"""Mock embeddings client"""
|
||||
client = AsyncMock()
|
||||
client.embed.return_value = [[0.1, 0.2, 0.3]]
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def mock_graph_embeddings_client(self):
|
||||
"""Mock graph embeddings client"""
|
||||
client = AsyncMock()
|
||||
client.query.return_value = ["entity1", "entity2"]
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def mock_triples_client(self):
|
||||
"""Mock triples client"""
|
||||
client = AsyncMock()
|
||||
client.query.return_value = []
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def mock_streaming_prompt_client(self):
|
||||
"""Mock prompt client that simulates realistic streaming with end_of_stream flags"""
|
||||
client = AsyncMock()
|
||||
|
||||
async def kg_prompt_side_effect(query, kg, timeout=600, streaming=False, chunk_callback=None):
|
||||
if streaming and chunk_callback:
|
||||
# Simulate realistic streaming: chunks with end_of_stream=False, then final with end_of_stream=True
|
||||
await chunk_callback("The", False)
|
||||
await chunk_callback(" answer", False)
|
||||
await chunk_callback(" is here.", False)
|
||||
await chunk_callback("", True) # Empty final chunk with end_of_stream=True
|
||||
return "" # Return value not used since callback handles everything
|
||||
else:
|
||||
return "The answer is here."
|
||||
|
||||
client.kg_prompt.side_effect = kg_prompt_side_effect
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def graph_rag(self, mock_embeddings_client, mock_graph_embeddings_client,
|
||||
mock_triples_client, mock_streaming_prompt_client):
|
||||
"""Create GraphRag instance with mocked dependencies"""
|
||||
return GraphRag(
|
||||
embeddings_client=mock_embeddings_client,
|
||||
graph_embeddings_client=mock_graph_embeddings_client,
|
||||
triples_client=mock_triples_client,
|
||||
prompt_client=mock_streaming_prompt_client,
|
||||
verbose=False
|
||||
)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_callback_receives_end_of_stream_parameter(self, graph_rag):
|
||||
"""Test that callback receives end_of_stream parameter"""
|
||||
# Arrange
|
||||
callback = AsyncMock()
|
||||
|
||||
# Act
|
||||
await graph_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=callback
|
||||
)
|
||||
|
||||
# Assert - callback should receive (chunk, end_of_stream) signature
|
||||
assert callback.call_count == 4
|
||||
# All calls should have 2 arguments
|
||||
for call_args in callback.call_args_list:
|
||||
assert len(call_args.args) == 2, "Callback should receive (chunk, end_of_stream)"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_end_of_stream_flag_forwarded_correctly(self, graph_rag):
|
||||
"""Test that end_of_stream flags are forwarded correctly"""
|
||||
# Arrange
|
||||
chunks_with_flags = []
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
chunks_with_flags.append((chunk, end_of_stream))
|
||||
|
||||
# Act
|
||||
await graph_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert
|
||||
assert len(chunks_with_flags) == 4
|
||||
|
||||
# First three chunks should have end_of_stream=False
|
||||
assert chunks_with_flags[0] == ("The", False)
|
||||
assert chunks_with_flags[1] == (" answer", False)
|
||||
assert chunks_with_flags[2] == (" is here.", False)
|
||||
|
||||
# Final chunk should have end_of_stream=True
|
||||
assert chunks_with_flags[3] == ("", True)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_no_duplicate_final_chunk(self, graph_rag):
|
||||
"""Test that final chunk is not duplicated"""
|
||||
# Arrange
|
||||
chunks = []
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
chunks.append(chunk)
|
||||
|
||||
# Act
|
||||
await graph_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert - should have exactly 4 chunks, no duplicates
|
||||
assert len(chunks) == 4
|
||||
assert chunks == ["The", " answer", " is here.", ""]
|
||||
|
||||
# The last chunk appears exactly once
|
||||
assert chunks.count("") == 1
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_exactly_one_end_of_stream_true(self, graph_rag):
|
||||
"""Test that exactly one message has end_of_stream=True"""
|
||||
# Arrange
|
||||
end_of_stream_flags = []
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
end_of_stream_flags.append(end_of_stream)
|
||||
|
||||
# Act
|
||||
await graph_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert - exactly one True
|
||||
assert end_of_stream_flags.count(True) == 1
|
||||
assert end_of_stream_flags.count(False) == 3
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_empty_final_chunk_preserved(self, graph_rag):
|
||||
"""Test that empty final chunks are preserved and forwarded"""
|
||||
# Arrange
|
||||
final_chunk = None
|
||||
final_flag = None
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
nonlocal final_chunk, final_flag
|
||||
if end_of_stream:
|
||||
final_chunk = chunk
|
||||
final_flag = end_of_stream
|
||||
|
||||
# Act
|
||||
await graph_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert
|
||||
assert final_flag is True
|
||||
assert final_chunk == "", "Empty final chunk should be preserved"
|
||||
|
||||
|
||||
class TestDocumentRagStreamingProtocol:
|
||||
"""Integration tests for DocumentRAG streaming protocol"""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_embeddings_client(self):
|
||||
"""Mock embeddings client"""
|
||||
client = AsyncMock()
|
||||
client.embed.return_value = [[0.1, 0.2, 0.3]]
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def mock_doc_embeddings_client(self):
|
||||
"""Mock document embeddings client"""
|
||||
client = AsyncMock()
|
||||
client.query.return_value = ["doc1", "doc2"]
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def mock_streaming_prompt_client(self):
|
||||
"""Mock prompt client with streaming support"""
|
||||
client = AsyncMock()
|
||||
|
||||
async def document_prompt_side_effect(query, documents, timeout=600, streaming=False, chunk_callback=None):
|
||||
if streaming and chunk_callback:
|
||||
# Simulate streaming with non-empty final chunk (some LLMs do this)
|
||||
await chunk_callback("Document", False)
|
||||
await chunk_callback(" summary", False)
|
||||
await chunk_callback(".", True) # Non-empty final chunk
|
||||
return ""
|
||||
else:
|
||||
return "Document summary."
|
||||
|
||||
client.document_prompt.side_effect = document_prompt_side_effect
|
||||
return client
|
||||
|
||||
@pytest.fixture
|
||||
def document_rag(self, mock_embeddings_client, mock_doc_embeddings_client,
|
||||
mock_streaming_prompt_client):
|
||||
"""Create DocumentRag instance with mocked dependencies"""
|
||||
return DocumentRag(
|
||||
embeddings_client=mock_embeddings_client,
|
||||
doc_embeddings_client=mock_doc_embeddings_client,
|
||||
prompt_client=mock_streaming_prompt_client,
|
||||
verbose=False
|
||||
)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_callback_receives_end_of_stream_parameter(self, document_rag):
|
||||
"""Test that callback receives end_of_stream parameter"""
|
||||
# Arrange
|
||||
callback = AsyncMock()
|
||||
|
||||
# Act
|
||||
await document_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=callback
|
||||
)
|
||||
|
||||
# Assert
|
||||
assert callback.call_count == 3
|
||||
for call_args in callback.call_args_list:
|
||||
assert len(call_args.args) == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_non_empty_final_chunk_preserved(self, document_rag):
|
||||
"""Test that non-empty final chunks are preserved with correct flag"""
|
||||
# Arrange
|
||||
chunks_with_flags = []
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
chunks_with_flags.append((chunk, end_of_stream))
|
||||
|
||||
# Act
|
||||
await document_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert
|
||||
assert len(chunks_with_flags) == 3
|
||||
assert chunks_with_flags[0] == ("Document", False)
|
||||
assert chunks_with_flags[1] == (" summary", False)
|
||||
assert chunks_with_flags[2] == (".", True) # Non-empty final chunk
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_no_duplicate_final_chunk(self, document_rag):
|
||||
"""Test that final chunk is not duplicated"""
|
||||
# Arrange
|
||||
chunks = []
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
chunks.append(chunk)
|
||||
|
||||
# Act
|
||||
await document_rag.query(
|
||||
query="test query",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert - final "." appears exactly once
|
||||
assert chunks.count(".") == 1
|
||||
assert chunks == ["Document", " summary", "."]
|
||||
|
||||
|
||||
class TestStreamingProtocolEdgeCases:
|
||||
"""Test edge cases in streaming protocol"""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_multiple_empty_chunks_before_final(self):
|
||||
"""Test handling of multiple empty chunks (edge case)"""
|
||||
# Arrange
|
||||
client = AsyncMock()
|
||||
|
||||
async def kg_prompt_with_empties(query, kg, timeout=600, streaming=False, chunk_callback=None):
|
||||
if streaming and chunk_callback:
|
||||
await chunk_callback("text", False)
|
||||
await chunk_callback("", False) # Empty but not final
|
||||
await chunk_callback("more", False)
|
||||
await chunk_callback("", True) # Empty and final
|
||||
return ""
|
||||
else:
|
||||
return "textmore"
|
||||
|
||||
client.kg_prompt.side_effect = kg_prompt_with_empties
|
||||
|
||||
rag = GraphRag(
|
||||
embeddings_client=AsyncMock(embed=AsyncMock(return_value=[[0.1]])),
|
||||
graph_embeddings_client=AsyncMock(query=AsyncMock(return_value=[])),
|
||||
triples_client=AsyncMock(query=AsyncMock(return_value=[])),
|
||||
prompt_client=client,
|
||||
verbose=False
|
||||
)
|
||||
|
||||
chunks_with_flags = []
|
||||
|
||||
async def collect(chunk, end_of_stream):
|
||||
chunks_with_flags.append((chunk, end_of_stream))
|
||||
|
||||
# Act
|
||||
await rag.query(
|
||||
query="test",
|
||||
streaming=True,
|
||||
chunk_callback=collect
|
||||
)
|
||||
|
||||
# Assert
|
||||
assert len(chunks_with_flags) == 4
|
||||
assert chunks_with_flags[-1] == ("", True) # Final empty chunk
|
||||
end_of_stream_flags = [f for c, f in chunks_with_flags]
|
||||
assert end_of_stream_flags.count(True) == 1
|
||||
Loading…
Add table
Add a link
Reference in a new issue