run-llama/create_llama_projects
1
0
Fork 0
mirror of https://github.com/run-llama/create_llama_projects.git synced 2026-07-01 20:54:24 -04:00
Code Issues 7 Packages Projects Releases Wiki Activity

cr

Browse Source
This commit is contained in:
Jerry Liu
2023-11-15 15:59:35 -08:00
parent e178305c1c
commit df872670ee
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -2,4 +2,4 @@
Here's some fun projects created with the `create-llama` command.
- [`embedded-tables`](embedded-tables/README.md): This project builds an agent that can analyze different data items wtihin the 2021 Tesla 10Q document, including embedded tables.
- [`embedded-tables`](embedded-tables/README.md): This project builds an agent that can analyze different data items wtihin the 2021+2020 Tesla 10Q document, including embedded tables.
embedded-tables/README.md
+12
View File
@@ -1,5 +1,17 @@
# RAG over Tesla 10-K's (with Embedded Tables)
This is a [LlamaIndex](https://www.llamaindex.ai/) project bootstrapped with [`create-llama`](https://github.com/run-llama/LlamaIndexTS/tree/main/packages/create-llama).
We use our recursive retriever, combined with an OpenAI Agent, to create a bot capable of tabular/semi-structured/unstructured analysis within complex docs.
This also streams the intermediate results from the agent via a custom Callback handler
## Main Files to Look At
This extends beyond the simple `create-llama` example. To see changes, look at the following files:
- `backend/app/utils/index.py` - contains core logic for constructing + getting agent
- `backend/app/api/routers/chat.py` - contains implementation of chat endpoint
## Getting Started
First, startup the backend as described in the [backend README](./backend/README.md).