alihan/MemGPT-llm
1
0
Fork 0
mirror of https://github.com/cpacker/MemGPT.git synced 2023-10-17 01:28:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Vivian Fang
2023-10-15 17:18:31 -07:00
committed by GitHub
parent 214364684a
commit e4662e2a3e
1 changed files with 25 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
memgpt/personas/examples/docqa/README.md
View File

@@ -1,8 +1,17 @@
# MemGPT Search over LlamaIndex API Docs
# MemGPT over LlamaIndex API Docs
MemGPT enables you to chat with your data -- try running this example to talk to the LlamaIndex API docs!
1.
a. Download embeddings and docs index from XYZ.
-- OR --
a. Download embeddings and docs index from [HuggingFace](https://huggingface.co/datasets/MemGPT/llamaindex-api-docs).
```bash
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/datasets/MemGPT/llamaindex-api-docs
```
**-- OR --**
b. Build the index:
1. Build llama_index API docs with `make text`. Instructions [here](https://github.com/run-llama/llama_index/blob/main/docs/DOCS_README.md). Copy over the generated `_build/text` folder to this directory.
2. Generate embeddings and FAISS index.
@@ -10,4 +19,16 @@
python3 scrape_docs.py
python3 generate_embeddings_for_docs.py all_docs.jsonl
python3 build_index.py --embedding_files all_docs.embeddings.jsonl --output_index_file all_docs.index
```
```
2. In the root `MemGPT` directory, run
```bash
python3 main.py --archival_storage_faiss_path=<ARCHIVAL_STORAGE_FAISS_PATH> --persona=memgpt_doc --human=basic
```
where `ARCHIVAL_STORAGE_FAISS_PATH` is the directory where `all_docs.jsonl` and `all_docs.index` are located.
If you downloaded from HuggingFace, it will be `memgpt/personas/docqa/llamaindex-api-docs`.
## Demo
<div align="center">
<img src="https://memgpt.ai/assets/img/docqa_demo.gif" alt="MemGPT demo video for llamaindex api docs search" width="800">
</div>