Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for schemas in python topic producer #734

Merged
merged 1 commit into from
Nov 22, 2023
Merged

Add support for schemas in python topic producer #734

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
98 changes: 58 additions & 40 deletions ...ents/langstream-agent-grpc/src/main/java/ai/langstream/agents/grpc/AbstractGrpcAgent.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,47 +107,65 @@ public void start() throws Exception {
asyncStub.getTopicProducerRecords(
new StreamObserver<>() {
@Override
public void onNext(TopicProducerRecord topicProducerRecord) {
TopicProducer topicProducer =
topicProducers.computeIfAbsent(
topicProducerRecord.getTopic(),
topic -> {
TopicProducer tp =
agentContext
.getTopicConnectionProvider()
.createProducer(
agentContext
.getGlobalAgentId(),
topic,
Map.of());
tp.start();
return tp;
});
public void onNext(TopicProducerResponse topicProducerResponse) {
try {
topicProducer
.write(fromGrpc(topicProducerRecord.getRecord()))
.whenComplete(
(r, e) -> {
if (e != null) {
log.error("Error writing record", e);
sendTopicProducerWriteResult(
TopicProducerWriteResult
.newBuilder()
.setError(
e
.getMessage()));
} else {
sendTopicProducerWriteResult(
TopicProducerWriteResult
.newBuilder()
.setRecordId(
topicProducerRecord
.getRecord()
.getRecordId()));
}
});
} catch (IOException e) {
agentContext.criticalFailure(e);
if (topicProducerResponse.hasSchema()) {
serverSchemas.put(
topicProducerResponse.getSchema().getSchemaId(),
new org.apache.avro.Schema.Parser()
.parse(
topicProducerResponse
.getSchema()
.getValue()
.toStringUtf8()));
}
if (topicProducerResponse.hasRecord()
&& !"".equals(topicProducerResponse.getTopic())) {
TopicProducer topicProducer =
topicProducers.computeIfAbsent(
topicProducerResponse.getTopic(),
topic -> {
TopicProducer tp =
agentContext
.getTopicConnectionProvider()
.createProducer(
agentContext
.getGlobalAgentId(),
topic,
Map.of());
tp.start();
return tp;
});
topicProducer
.write(fromGrpc(topicProducerResponse.getRecord()))
.whenComplete(
(r, e) -> {
if (e != null) {
log.error(
"Error writing record", e);
sendTopicProducerWriteResult(
TopicProducerWriteResult
.newBuilder()
.setError(
e
.getMessage()));
} else {
sendTopicProducerWriteResult(
TopicProducerWriteResult
.newBuilder()
.setRecordId(
topicProducerResponse
.getRecord()
.getRecordId()));
}
});
}
} catch (Exception e) {
agentContext.criticalFailure(
new RuntimeException(
"getTopicProducerRecords: Error while processing TopicProducerResponse: %s"
.formatted(e.getMessage()),
e));
}
}

Expand Down
5 changes: 3 additions & 2 deletions langstream-agents/langstream-agent-grpc/src/main/proto/langstream_grpc/proto/agent.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ service AgentService {
rpc read(stream SourceRequest) returns (stream SourceResponse) {}
rpc process(stream ProcessorRequest) returns (stream ProcessorResponse) {}
rpc write(stream SinkRequest) returns (stream SinkResponse) {}
rpc get_topic_producer_records(stream TopicProducerWriteResult) returns (stream TopicProducerRecord) {}
rpc get_topic_producer_records(stream TopicProducerWriteResult) returns (stream TopicProducerResponse) {}
}

message InfoResponse {
Expand Down Expand Up @@ -74,8 +74,9 @@ message TopicProducerWriteResult {
optional string error = 2;
}

message TopicProducerRecord {
message TopicProducerResponse {
string topic = 1;
Schema schema = 2;
Record record = 3;
}

Expand Down
73 changes: 63 additions & 10 deletions .../langstream-agent-grpc/src/test/java/ai/langstream/agents/grpc/AbstractGrpcAgentTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,19 +23,29 @@
import ai.langstream.api.runner.topics.TopicConnectionProvider;
import ai.langstream.api.runner.topics.TopicConsumer;
import ai.langstream.api.runner.topics.TopicProducer;
import com.google.protobuf.ByteString;
import com.google.protobuf.Empty;
import io.grpc.ManagedChannel;
import io.grpc.Server;
import io.grpc.Status;
import io.grpc.inprocess.InProcessChannelBuilder;
import io.grpc.inprocess.InProcessServerBuilder;
import io.grpc.stub.StreamObserver;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.nio.file.Path;
import java.util.Map;
import java.util.concurrent.CompletableFuture;
import java.util.concurrent.LinkedBlockingQueue;
import java.util.concurrent.TimeUnit;
import lombok.extern.slf4j.Slf4j;
import org.apache.avro.Conversions;
import org.apache.avro.SchemaBuilder;
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericDatumWriter;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.io.BinaryEncoder;
import org.apache.avro.io.EncoderFactory;
import org.junit.jupiter.api.AfterEach;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
Expand All @@ -62,17 +72,47 @@ public void agentInfo(

@Override
public StreamObserver<TopicProducerWriteResult> getTopicProducerRecords(
StreamObserver<TopicProducerRecord> responseObserver) {
StreamObserver<TopicProducerResponse> responseObserver) {
org.apache.avro.Schema schema =
SchemaBuilder.record("testRecord")
.fields()
.name("testField")
.type()
.stringType()
.noDefault()
.endRecord();
GenericData.Record avroRecord = new GenericData.Record(schema);
avroRecord.put("testField", "test-string");

responseObserver.onNext(
TopicProducerRecord.newBuilder()
.setTopic("test-topic")
.setRecord(
ai.langstream.agents.grpc.Record.newBuilder()
.setRecordId(42)
TopicProducerResponse.newBuilder()
.setSchema(
Schema.newBuilder()
.setSchemaId(123)
.setValue(
Value.newBuilder()
.setStringValue("test-value1")))
ByteString.copyFromUtf8(
schema.toString()))
.build())
.build());

try {
responseObserver.onNext(
TopicProducerResponse.newBuilder()
.setTopic("test-topic")
.setRecord(
ai.langstream.agents.grpc.Record.newBuilder()
.setRecordId(42)
.setValue(
Value.newBuilder()
.setSchemaId(123)
.setAvroValue(
ByteString.copyFrom(
serializeGenericRecord(
avroRecord)))))
.build());
} catch (IOException e) {
throw new RuntimeException(e);
}
return new StreamObserver<>() {

@Override
Expand All @@ -88,7 +128,7 @@ public void onNext(TopicProducerWriteResult topicProducerWriteResult) {
responseObserver.onCompleted();
} else if (topicProducerWriteResult.getRecordId() == 42) {
responseObserver.onNext(
TopicProducerRecord.newBuilder()
TopicProducerResponse.newBuilder()
.setTopic("test-topic")
.setRecord(
ai.langstream.agents.grpc.Record
Expand Down Expand Up @@ -164,7 +204,9 @@ void testTopicProducerSuccess() throws Exception {
TestAgentContext context = new TestAgentContextSuccessful();
startProcessor(context);
LinkedBlockingQueue<Record> recordsToWrite = context.recordsToWrite;
assertEquals("test-value1", recordsToWrite.poll(5, TimeUnit.SECONDS).value().toString());
assertEquals(
"{\"testField\": \"test-string\"}",
recordsToWrite.poll(5, TimeUnit.SECONDS).value().toString());
assertEquals("test-value2", recordsToWrite.poll(5, TimeUnit.SECONDS).value().toString());
}

Expand Down Expand Up @@ -275,4 +317,15 @@ protected CompletableFuture<?> writeRecord(Record record) {
return CompletableFuture.failedFuture(new RuntimeException("test-complete"));
}
}

private static byte[] serializeGenericRecord(GenericRecord record) throws IOException {
GenericDatumWriter<GenericRecord> writer = new GenericDatumWriter<>(record.getSchema());
// enable Decimal conversion, otherwise attempting to serialize java.math.BigDecimal will
// throw ClassCastException.
writer.getData().addLogicalTypeConversion(new Conversions.DecimalConversion());
ByteArrayOutputStream oo = new ByteArrayOutputStream();
BinaryEncoder encoder = EncoderFactory.get().directBinaryEncoder(oo, null);
writer.write(record, encoder);
return oo.toByteArray();
}
}
2 changes: 1 addition & 1 deletion ...langstream-agent-grpc/src/test/java/ai/langstream/agents/grpc/GrpcAgentProcessorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@ public void onCompleted() {

@Override
public StreamObserver<TopicProducerWriteResult> getTopicProducerRecords(
StreamObserver<TopicProducerRecord> responseObserver) {
StreamObserver<TopicProducerResponse> responseObserver) {
return new StreamObserver<>() {
@Override
public void onNext(TopicProducerWriteResult topicProducerWriteResult) {}
Expand Down
2 changes: 1 addition & 1 deletion ...ents/langstream-agent-grpc/src/test/java/ai/langstream/agents/grpc/GrpcAgentSinkTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,7 +187,7 @@ public void onCompleted() {

@Override
public StreamObserver<TopicProducerWriteResult> getTopicProducerRecords(
StreamObserver<TopicProducerRecord> responseObserver) {
StreamObserver<TopicProducerResponse> responseObserver) {
return new StreamObserver<>() {
@Override
public void onNext(TopicProducerWriteResult topicProducerWriteResult) {}
Expand Down
2 changes: 1 addition & 1 deletion ...ts/langstream-agent-grpc/src/test/java/ai/langstream/agents/grpc/GrpcAgentSourceTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,7 +219,7 @@ public void onCompleted() {

@Override
public StreamObserver<TopicProducerWriteResult> getTopicProducerRecords(
StreamObserver<TopicProducerRecord> responseObserver) {
StreamObserver<TopicProducerResponse> responseObserver) {
return new StreamObserver<>() {
@Override
public void onNext(TopicProducerWriteResult topicProducerWriteResult) {}
Expand Down
9 changes: 5 additions & 4 deletions langstream-runtime/langstream-runtime-impl/src/main/python/langstream_grpc/grpc_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,8 @@
SourceResponse,
SinkRequest,
SinkResponse,
TopicProducerRecord,
TopicProducerWriteResult,
TopicProducerResponse,
)
from langstream_grpc.proto.agent_pb2_grpc import AgentServiceServicer
from .api import Source, Sink, Processor, Record, Agent, AgentContext, TopicProducer
Expand Down Expand Up @@ -91,12 +91,13 @@ async def agent_info(self, _, __):
async def poll_topic_producer_records(self, context):
while True:
topic, record, future = await self.topic_producer_records.get()
# TODO: handle schemas
_, grpc_record = self.to_grpc_record(record)
schemas, grpc_record = self.to_grpc_record(record)
for schema in schemas:
await context.write(TopicProducerResponse(schema=schema))
self.topic_producer_record_id += 1
self.topic_producer_records_pending[self.topic_producer_record_id] = future
grpc_record.record_id = self.topic_producer_record_id
await context.write(TopicProducerRecord(topic=topic, record=grpc_record))
await context.write(TopicProducerResponse(topic=topic, record=grpc_record))

async def handle_write_results(self, context):
write_result = await context.read()
Expand Down
Loading
Loading