Spaces:
Running
Running
Fangrui Liu
commited on
Commit
β’
0eab447
1
Parent(s):
a796108
update README.md
Browse files
README.md
CHANGED
@@ -1,108 +1,13 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
- π **We just opened a FREE pod hosting data for ArXiv paper.** Anyone can try their own SQL with vector search!!! Feel the power when SQL meets vector search! See how to access the pod [here](#data-service).
|
15 |
-
- π We collected **1.67 million papers on arxiv**! We are collecting more and we need your advice!
|
16 |
-
- More coming...
|
17 |
-
|
18 |
-
## Quickstart
|
19 |
-
|
20 |
-
1. Create an virtual environment
|
21 |
-
|
22 |
-
```bash
|
23 |
-
python3 -m venv .venv
|
24 |
-
source .venv/bin/activate
|
25 |
-
```
|
26 |
-
|
27 |
-
2. Install dependencies
|
28 |
-
|
29 |
-
> This app is currently using [MyScale's fork of LangChain](https://github.com/myscale/langchain/tree/master). It contains [improved prompts](https://github.com/hwchase17/langchain/pull/6737#discussion_r1243527112) for comparators `LIKE` and `CONTAIN` in [MyScale self-query retriever](https://github.com/hwchase17/langchain/pull/6143).
|
30 |
-
|
31 |
-
```bash
|
32 |
-
python3 -m pip install -r requirements.txt
|
33 |
-
```
|
34 |
-
|
35 |
-
3. Run the app!
|
36 |
-
|
37 |
-
```python
|
38 |
-
# fill you OpenAI key in .streamlit/secrets.toml
|
39 |
-
cp .streamlit/secrets.example.toml .streamlit/secrets.toml
|
40 |
-
# start the app
|
41 |
-
python3 -m streamlit run app.py
|
42 |
-
```
|
43 |
-
|
44 |
-
## Quick Navigator π§
|
45 |
-
|
46 |
-
- [How can I run this app?](README.md#how-to-run)
|
47 |
-
|
48 |
-
- [How this app is built?](docs/self-query.md)
|
49 |
-
|
50 |
-
- [What is the overview pipeline?](docs/self-query.md#query-pipeline-design)
|
51 |
-
|
52 |
-
- [How did LangChain and MyScale convert natural language to structured filters?](docs/self-query.md#selfqueryretriever-defines-interaction-between-vectorstore-and-your-app)
|
53 |
-
|
54 |
-
- [How to make chain execution more responsive in LangChain?](docs/self-query.md#not-responsive-add-callbacks)
|
55 |
-
|
56 |
-
- Where can I get those arxiv data?
|
57 |
-
- [From parquet files on S3](docs/self-query.md#insert-data)
|
58 |
-
- <a name="data-service"></a>Or directly use MyScale database as service... for **FREE** β¨
|
59 |
-
```python
|
60 |
-
import clickhouse_connect
|
61 |
-
|
62 |
-
client = clickhouse_connect.get_client(
|
63 |
-
host='msc-1decbcc9.us-east-1.aws.staging.myscale.cloud',
|
64 |
-
port=443,
|
65 |
-
username='chatdata',
|
66 |
-
password='myscale_rocks'
|
67 |
-
)
|
68 |
-
```
|
69 |
-
Or put these settings in `.streamlit/secrets.toml`
|
70 |
-
|
71 |
-
```toml
|
72 |
-
MYSCALE_HOST = "msc-1decbcc9.us-east-1.aws.staging.myscale.cloud"
|
73 |
-
MYSCALE_PORT = 443
|
74 |
-
MYSCALE_USER = "chatdata"
|
75 |
-
MYSCALE_PASSWORD = "myscale_rocks"
|
76 |
-
```
|
77 |
-
|
78 |
-
## Introduction
|
79 |
-
|
80 |
-
ChatData brings millions of papers into your knowledge base. We imported 1.67 million papers with metadata info (continuously updating), which contains:
|
81 |
-
|
82 |
-
1. `metadata.authors`: paper's authors in *list of strings*
|
83 |
-
2. `metadata.abstract`: paper's abstracts used as ranking criterion (with InstructXL)
|
84 |
-
3. `metadata.titles`: papers's titles
|
85 |
-
4. `metadata.categories`: paper's categories in *list of strings* like ["cs.CV"]
|
86 |
-
5. `metadata.pubdate`: paper's date of publication in *ISO 8601 formated strings*
|
87 |
-
6. `metadata.primary_category`: paper's primary category in *strings* defined by ArXiv
|
88 |
-
7. `metadata.comment`: some additional comment to the paper
|
89 |
-
|
90 |
-
And for overall table schema, please refer to [table creation section in docs/self-query.md](docs/self-query.md#table-creation).
|
91 |
-
|
92 |
-
## How to run π
|
93 |
-
|
94 |
-
```bash
|
95 |
-
python3 -m pip install requirements.txt
|
96 |
-
python3 -m streamlit run app.py
|
97 |
-
```
|
98 |
-
|
99 |
-
## How to build? π§±
|
100 |
-
|
101 |
-
See [docs/self-query.md](docs/self-query.md)
|
102 |
-
|
103 |
-
## Special Thanks π (Ordered Alphabetically)
|
104 |
-
|
105 |
-
- [ArXiv API](https://info.arxiv.org/help/api/index.html) for its open access interoperability to pre-printed papers.
|
106 |
-
- [InstructorXL](https://huggingface.co/hkunlp/instructor-xl) for its promptable embeddings that improves retrieve performance.
|
107 |
-
- [LangChainπ¦οΈπ](https://github.com/hwchase17/langchain/) for its easy-to-use and composable API designs and prompts.
|
108 |
-
- [The Alexandria Index](https://alex.macrocosm.so/download) for providing arXiv data index to the public.
|
|
|
1 |
+
---
|
2 |
+
title: ChatData
|
3 |
+
emoji: π π
|
4 |
+
colorFrom: pink
|
5 |
+
colorTo: purple
|
6 |
+
sdk: streamlit
|
7 |
+
sdk_version: 1.20.0
|
8 |
+
app_file: app.py
|
9 |
+
pinned: true
|
10 |
+
license: mit
|
11 |
+
---
|
12 |
+
|
13 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|