Spaces:
Runtime error
Runtime error
Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,45 @@ sdk: streamlit
|
|
7 |
sdk_version: 1.21.0
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
sdk_version: 1.21.0
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
+
---
|
11 |
+
|
12 |
+
# What would mother say?
|
13 |
+
|
14 |
+
This app includes a Haystack agent with access to 2 tools:
|
15 |
+
- TweetRetriever: Useful for when you need to retrive the latest tweets from a username to get an understanding of their style
|
16 |
+
- WebSearch:Uesful for when you need to research the latest about a new topic
|
17 |
+
|
18 |
+
We build an Agent that aims to first understand the style in which a username tweets. Then, it uses the WebSearch tool to gain knowledge on a topic that the LLM may not have info on, to generate a tweet in the users style about that topic.
|
19 |
+
### Try it out on [🤗 Spaces](https://huggingface.co/spaces/Tuana/what-would-mother-say)
|
20 |
+
|
21 |
+
##### A showcase of a Haystack Agent with a custom `TwitterRetriever` Node and a `WebQAPipeline` as tools.
|
22 |
+
|
23 |
+
**Custom Haystack Node**
|
24 |
+
|
25 |
+
This repo contains a streamlit application that given a query about what a certain twitter username would post on a given topic, generates a tweet in their style (or tries to). It does so by using a custom Haystack node I've built called the [`TweetRetriever`](/custom_nodes/tweet_retriever.py)
|
26 |
+
|
27 |
+
**Custom PromptTemplates**
|
28 |
+
|
29 |
+
It's been built with [Haystack](https://haystack.deepset.ai) using the [`Agent`](https://docs.haystack.deepset.ai/docs/agent) and by creating a custom [`PromptTemplate`](https://docs.haystack.deepset.ai/docs/prompt_node#templates)
|
30 |
+
|
31 |
+
All the prompt templates used in this demo, both for the `WebQAPipeline` and the `Agent` can be found in `./prompts`.
|
32 |
+
|
33 |
+
<img width="867" alt="image" src="https://github.com/TuanaCelik/what-would-mother-say/assets/15802862/b05f8bde-8fd5-4c6f-beac-1578437a145b">
|
34 |
+
|
35 |
+
## To learn more about the Agent
|
36 |
+
|
37 |
+
Check out our tutorial on the Conversational Agent [here](https://haystack.deepset.ai/tutorials/24_building_chat_app)
|
38 |
+
|
39 |
+
## Installation and Running
|
40 |
+
1. Install requirements:
|
41 |
+
`pip install -r requirements.txt`
|
42 |
+
2. Run the streamlit app:
|
43 |
+
`streamlit run app.py`
|
44 |
+
3. Createa a `.env` and add your Twitter Bearer token, OpenAI Key, and SerperDev Key:
|
45 |
+
`TWITTER_BEARER_TOKEN`
|
46 |
+
`SERPER_KEY`
|
47 |
+
`OPENAI_API_KEY`
|
48 |
+
|
49 |
+
This will start up the app on `localhost:8501` where you will find a simple search bar
|
50 |
+
|
51 |
+
#### The Haystack Community is on [Discord](https://discord.com/invite/VBpFzsgRVF)
|