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

Rag-instead-docsum #46

Merged
merged 8 commits into from
Nov 23, 2023
Merged

Rag-instead-docsum #46

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
4b2c9d7
move from 'document summarisation' to 'retrieval ..
slobentanzer Nov 23, 2023
99a8de3
update readme
slobentanzer Nov 23, 2023
d550f8e
update biochatter `0.3.0`
slobentanzer Nov 23, 2023
7d0d1fe
update biochatter once more
slobentanzer Nov 23, 2023
53a3fe6
comment
slobentanzer Nov 23, 2023
9259eb0
update streamlit
slobentanzer Nov 23, 2023
9309582
adjust rag agent syntax to new biochatter
slobentanzer Nov 23, 2023
d0085d5
update biochatter again
slobentanzer Nov 23, 2023
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
17 changes: 9 additions & 8 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ and are looking for a way to connect it to the world of LLMs!
## 🤝 Get involved!
To stay up to date with the project, please star the repository and watch the
zulip community chat (free to join) at https://biocypher.zulipchat.com.
ChatGSE-related discussion happens in the `#chatgse` stream.
ChatGSE-related discussion happens in the `#biochatter and chatgse` stream.

We are very happy about contributions from the community, large and small!
If you would like to contribute to the platform's development, please refer to
Expand All @@ -36,12 +36,13 @@ files in the discussion
for things the model can do, such as creating formatted markdown output to
create mindmaps or other visualisations.

## 📑 Document summarisation / In-context learning
You can use the document summarisation feature to upload documents and use
similarity search to inject context into your prompts. The document
summarisation feature is currently only available on local builds of ChatGSE
(see below). It requires a connection to a vector database (currently only
[Milvus](https://milvus.io/) is supported). We follow [these
## 📑 Retrieval Augmented Generation / In-context learning

You can use the Retrieval Augmented Generation (RAG) feature to upload documents
and use similarity search to inject context into your prompts. The RAG feature
is currently only available on local builds of ChatGSE (see below). It requires
a connection to a vector database (currently only [Milvus](https://milvus.io/)
is supported). We follow [these
instructions](https://milvus.io/docs/install_standalone-docker.md) to mount a
Docker instance on your machine (using the standard ports). We provide a Docker
compose setup to mount the Milvus containers and the ChatGSE container together:
Expand Down Expand Up @@ -146,7 +147,7 @@ configuration similar to this one to your launch.json:

```

Note that if you want to use the document summarisation feature or other
Note that if you want to use the Retrieval Augmented Generation feature or other
connected services, you will still need to start these separately. For the
vector DB component of the `docker-compose.yml` file, you can do it like so:

Expand Down
Loading