support [chatglm](https://github.com/THUDM/ChatGLM-6B), which was
mentioned in #267 .
[chatglm2](https://github.com/THUDM/ChatGLM2-6B) and
[chatglm3](https://github.com/THUDM/ChatGLM3) api are compatible with
openai, so It is enough to support chatglm.
because chatglm does not have official docker image, so I don't know how
to use `Testcontainers` to do test. (I'm not familiar with
`Testcontainers`, so for now I have to copy test from the other modules,
lol). The test will update using `Testcontainers` after I learn about it
in few days.
Allow the organizationId to be specified in the configuration. See
https://platform.openai.com/docs/api-reference/organization-optional
Right now there is no way to specify this.
I added a `.organizationId(System.getenv("OPENAI_ORGANIZATION_ID"))` to
the builders in a bunch of the tests. They should have no effect other
than if you want to run the tests to pass an organizationId, you can
just set the `OPENAI_ORGANIZATION_ID` environment variable. The
`OpenAiClient` won't do anything if the `organizationId` is `null`.
Happy for questions/comments.
Fixes#344
Azure OpenAI 1.0.0-beta.6 is out:
- [x] Update to the new SDK
- [x] Add unit tests
- [x] Do integration tests on my account (as I have access to Azure
OpenAI)
By adding an optional dependency on the
spring-boot-configuration-processor, a
`META-INF/spring-configuration-metadata.json` file will be created for
all `@ConfigurationProperties`-annoted types to support autocompletion
within IDEs. Since nested beans are used, the bound fields for those
beans need to be annotated with `@NestedConfigurationProperty`. (purely
for this tool, this does not affect runtime behavior in any way)
Adding two separate loaders that load a single document or multiple
documents from S3 respectively. They also contain different parameters
to support different configurations. However, the document type is
dependent on the current parsers that langchain4j supports, but I am
planning to help in adding more parsers in the future.
Add the Spring Boot Configuration Processor dependency to the Spring
Boot starter to generate metadata
about the LangChain4J custom properties.
Fixes gh-250
This PR contains the implementation of an integration with
[OpenSearch](https://opensearch.org/). As one of the growing vector
databases in the open source world, adding support for it to this
project makes total sense. This implementation includes:
1. A complete implementation of the `EmbeddingStore` interface.
2. Unit tests for the major use cases a store must implement correctly.
3. Usage of [TestContainers](https://testcontainers.com/) to automate
the execution of backends.
Using 1.8.28 results in
` java: java.lang.NoSuchFieldError: Class
com.sun.tools.javac.tree.JCTree$JCImport does not have member field
'com.sun.tools.javac.tree.JCTree qualid'`
I've done integration with Elastic and do some local test to ensure it's
right!（some logic is translated from LangChain Python to Java）.
Elasticsearch do not support `Gson`. So we must have `Jackson`
dependency.
Note that the declaration of license in dashscope-sdk-java:pom.xml is:
<licenses>
<license>
<name>The Apache License, Version 2.0</name>
<url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
<distribution>repo</distribution>
</license>
</licenses>
(There is a "The " prefix in its name.)
Qwen series models are provided by Alibaba Cloud. They are much better
in Asia languages then other LLMs.
DashScope is a model service platform. Qwen models are its primary
supported models. But it also supports other series like LLaMA2, Dolly,
ChatGLM, BiLLa(based on LLaMA)...These may be integrated sometime in the
future.
LangChain4j