lesimoes commited on
Commit
145aaf4
·
1 Parent(s): 112182e

add readme

Browse files
Files changed (2) hide show
  1. README.md +43 -3
  2. app.py +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  title: Chatbot Mistral
3
- emoji: 🐢
4
- colorFrom: red
5
  colorTo: indigo
6
  sdk: streamlit
7
  sdk_version: 1.42.0
@@ -9,4 +9,44 @@ app_file: app.py
9
  pinned: false
10
  ---
11
 
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: Chatbot Mistral
3
+ emoji: 😷
4
+ colorFrom: white
5
  colorTo: indigo
6
  sdk: streamlit
7
  sdk_version: 1.42.0
 
9
  pinned: false
10
  ---
11
 
12
+ # Symptom Diagnosis Chatbot
13
+
14
+ An interactive Python chatbot that helps users identify a possible diagnosis based on the symptoms they report. This project integrates a knowledge base stored in a `database.txt` file and utilizes HuggingFace models for generating responses and performing translations.
15
+
16
+ ## Description
17
+
18
+ This project was created to:
19
+ - **Load a Knowledge Base:** A `database.txt` file contains symptoms and their corresponding content. Each record follows the format:
20
+
21
+
22
+ - **Generate Customized Responses:** Using the `Mistral-7B-Instruct-v0.3` model from HuggingFace to interpret the user's query and the `Helsinki-NLP/opus-mt-tc-big-en-pt` model to translate responses into Portuguese.
23
+ - **Provide an Interactive Web Interface:** Built with Streamlit, allowing users to interact with the chatbot and adjust parameters via a sidebar.
24
+
25
+ ## Features
26
+
27
+ - **Knowledge Base Integration:** Reads and formats symptoms and content from an external file.
28
+ - **Response Generation:** Provides responses based on the conversation context and the knowledge base.
29
+ - **Automatic Translation:** Translates responses to Portuguese.
30
+ - **Interactive Web Interface:** Developed with Streamlit, enabling a simple and intuitive conversation with the chatbot.
31
+ - **Customizable Settings:** Allows adjustments to system messages, maximum response length, and other parameters through the interface.
32
+
33
+ ## Prerequisites
34
+
35
+ - **Python 3.8 or higher**
36
+ - **HuggingFace Access Token:** Set the environment variable `HF_TOKEN` with your HuggingFace token.
37
+ - The following Python libraries:
38
+ - `streamlit`
39
+ - `transformers`
40
+ - `langchain-huggingface`
41
+ - (Other dependencies may be listed in a `requirements.txt` file)
42
+
43
+ ## Installation
44
+
45
+ 1. **Clone the Repository**
46
+
47
+ 2. **Install requirements**
48
+ ```bash
49
+ pip install -r requirements.txt
50
+ ```
51
+
52
+ **Highly recommend use hugginface spaces**
app.py CHANGED
@@ -22,7 +22,7 @@ text_waiting_ai_response = "Pensando..."
22
  max_response_length = 256
23
  reset_button_label = "Reset Chat History"
24
  chatbot_title = "ChatBot Sintomas"
25
- chatbot_description = f"* Um chatbot de sintomas que usa os modelos {model_id} e {translation_model_id}.*"
26
  temperature = 0.1
27
 
28
  translation_pipeline = pipeline(
 
22
  max_response_length = 256
23
  reset_button_label = "Reset Chat History"
24
  chatbot_title = "ChatBot Sintomas"
25
+ chatbot_description = f"* Um chatbot de sintomas que usa os modelos {model_id} e {translation_model_id}.* Lembre-se de não confiar nesse chatbot, para casos reais um médico deverá ser consultado."
26
  temperature = 0.1
27
 
28
  translation_pipeline = pipeline(