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

Support Parquet data for HNSWDenseVector #2582

Merged
merged 8 commits into from
Sep 10, 2024
Merged

Support Parquet data for HNSWDenseVector #2582

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
1acfd86
json to parquet conversion working
valamuri2020 Aug 28, 2024
5e6c884
initial impl for collection and generator, dependencies compiling
valamuri2020 Aug 29, 2024
5acb4eb
indexing and retrieval works end-to-end
valamuri2020 Aug 29, 2024
8a6a715
added requirements.txt
valamuri2020 Aug 29, 2024
fe317ce
cleanup
valamuri2020 Aug 29, 2024
3a56a0a
cleanup
valamuri2020 Aug 29, 2024
7ae1038
added exclusion tags for pom.xml and removed contents field
valamuri2020 Aug 30, 2024
7cbf850
reducing dependency bloat
valamuri2020 Sep 1, 2024
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
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,3 +80,4 @@ tools/topics-and-qrels/qrels.covid-round2-cumulative.txt
/src/main/frontend/*.tsbuildinfo
/src/main/frontend/next-env.d.ts
/src/main/python/onnx/models/*.onnx
/src/main/python/parquet/venv*
168 changes: 168 additions & 0 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,6 +535,174 @@
<artifactId>spring-boot-starter-logging</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- Apache Parquet Dependencies -->
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
<version>1.12.3</version>
<exclusions>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-yarn-common</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-common</artifactId>
<version>1.12.3</version>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-column</artifactId>
<version>1.12.3</version>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-format</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-encoding</artifactId>
<version>1.12.3</version>
</dependency>

<!-- Necessary Hadoop Modules for Parquet -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>3.3.1</version>
<exclusions>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-yarn-common</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-yarn-server-common</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-annotations</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</exclusion>
<exclusion>
<groupId>org.eclipse.jetty</groupId>
<artifactId>jetty-server</artifactId>
</exclusion>
<exclusion>
<groupId>org.eclipse.jetty</groupId>
<artifactId>jetty-servlet</artifactId>
</exclusion>
<exclusion>
<groupId>org.eclipse.jetty</groupId>
<artifactId>jetty-webapp</artifactId>
</exclusion>
<exclusion>
<groupId>org.eclipse.jetty</groupId>
<artifactId>jetty-util</artifactId>
</exclusion>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>javax.servlet-api</artifactId>
</exclusion>
<exclusion>
<groupId>commons-beanutils</groupId>
<artifactId>commons-beanutils</artifactId>
</exclusion>
<exclusion>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
</exclusion>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
<exclusion>
<groupId>com.google.protobuf</groupId>
<artifactId>protobuf-java</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.curator</groupId>
<artifactId>curator-client</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.curator</groupId>
<artifactId>curator-recipes</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.kerby</groupId>
<artifactId>kerb-core</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.kerby</groupId>
<artifactId>kerb-simplekdc</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper-jute</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.kerby</groupId>
<artifactId>kerby-pkix</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.kerby</groupId>
<artifactId>kerb-admin</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client-api</artifactId>
<version>3.3.1</version>
<exclusions>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
</project>
Loading
Loading