Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -111,15 +111,14 @@ def conversation(qa_chain, message, history):
|
|
| 111 |
|
| 112 |
|
| 113 |
SPACE_TITLE = """
|
| 114 |
-
<center><h2>
|
| 115 |
-
<h3>Ask any questions about your PDF documents</h3>
|
| 116 |
"""
|
| 117 |
|
| 118 |
SPACE_INFO = """
|
| 119 |
-
<b>Description:</b> This AI assistant, using Langchain and open-source LLMs, performs retrieval-augmented generation (RAG) from your
|
| 120 |
-
The user interface
|
| 121 |
-
This chatbot
|
| 122 |
-
<br><b>Notes:</b> Updated space with more recent LLM models (Qwen 2.5, Llama 3.2, SmolLM2 series)
|
| 123 |
<br><b>Warning:</b> This space uses the free CPU Basic hardware from Hugging Face. Some steps and LLM models used below (free inference endpoints) can take some time to generate a reply.
|
| 124 |
"""
|
| 125 |
|
|
|
|
| 111 |
|
| 112 |
|
| 113 |
SPACE_TITLE = """
|
| 114 |
+
<center><h2>Corporate General Intelligence (CGI)</center></h2>
|
| 115 |
+
<h3>Ask any questions about your PDF documents.</h3>
|
| 116 |
"""
|
| 117 |
|
| 118 |
SPACE_INFO = """
|
| 119 |
+
<b>Description:</b> This AI assistant, using Langchain and open-source LLMs, performs retrieval-augmented generation (RAG) from your enterprise documents. \
|
| 120 |
+
The user interface explicitly shows multiple steps to help understand the RAG workflow.
|
| 121 |
+
This chatbot accounts for past questions when generating answers (via conversational memory), and includes document references for clarity purposes.<br>
|
|
|
|
| 122 |
<br><b>Warning:</b> This space uses the free CPU Basic hardware from Hugging Face. Some steps and LLM models used below (free inference endpoints) can take some time to generate a reply.
|
| 123 |
"""
|
| 124 |
|