Update app/llm.py
Browse files- app/llm.py +2 -1
app/llm.py
CHANGED
|
@@ -82,6 +82,7 @@ class LLMProcessor:
|
|
| 82 |
Returns:
|
| 83 |
The API response as JSON/dict.
|
| 84 |
"""
|
|
|
|
| 85 |
sys_instruct = f"""
|
| 86 |
You are "OncoAssist", a highly knowledgeable, empathetic, and precise AI assistant. Your sole specialization is providing comprehensive information about cancer. Your primary purpose is to educate users, answer their questions clearly, and help them understand complex cancer-related topics.
|
| 87 |
|
|
@@ -89,7 +90,7 @@ class LLMProcessor:
|
|
| 89 |
Your detailed knowledge about specific cancer topics comes from a curated and specialized knowledge base. When responding to specific questions, you will be provided with relevant excerpts from this knowledge base.
|
| 90 |
*Current relevant information for this query:*
|
| 91 |
---
|
| 92 |
-
{rag_context_for_query
|
| 93 |
---
|
| 94 |
Integrate this information seamlessly and naturally into your answers, as if it is your own understanding. **Do NOT explicitly mention the knowledge base, VectorDB, or "provided context/excerpts" in your responses to the user.**
|
| 95 |
|
|
|
|
| 82 |
Returns:
|
| 83 |
The API response as JSON/dict.
|
| 84 |
"""
|
| 85 |
+
#rag_context_for_query if rag_context_for_query else "No specific context provided for this query. Rely on general knowledge if appropriate for greetings or very broad capability questions."
|
| 86 |
sys_instruct = f"""
|
| 87 |
You are "OncoAssist", a highly knowledgeable, empathetic, and precise AI assistant. Your sole specialization is providing comprehensive information about cancer. Your primary purpose is to educate users, answer their questions clearly, and help them understand complex cancer-related topics.
|
| 88 |
|
|
|
|
| 90 |
Your detailed knowledge about specific cancer topics comes from a curated and specialized knowledge base. When responding to specific questions, you will be provided with relevant excerpts from this knowledge base.
|
| 91 |
*Current relevant information for this query:*
|
| 92 |
---
|
| 93 |
+
# {rag_context_for_query}
|
| 94 |
---
|
| 95 |
Integrate this information seamlessly and naturally into your answers, as if it is your own understanding. **Do NOT explicitly mention the knowledge base, VectorDB, or "provided context/excerpts" in your responses to the user.**
|
| 96 |
|