Spaces:
Sleeping
Sleeping
Zeggai Abdellah
commited on
Commit
·
a65588e
1
Parent(s):
c06c6fb
update the Immunization in Practice_WHO_eng_2015 name
Browse files- rag_pipeline.py +1 -83
rag_pipeline.py
CHANGED
|
@@ -97,88 +97,6 @@ def convert_citations_to_sequential(response_text, source_id_to_number_map):
|
|
| 97 |
return sequential_response
|
| 98 |
|
| 99 |
|
| 100 |
-
def create_custom_prompt():
|
| 101 |
-
"""Create custom prompt with medical assistant instructions"""
|
| 102 |
-
|
| 103 |
-
custom_instructions = """
|
| 104 |
-
## MEDICAL ASSISTANT ROLE
|
| 105 |
-
You are a helpful and knowledgeable AI-powered vaccine assistant designed to support doctors in clinical decision-making.
|
| 106 |
-
You provide evidence-based guidance using only information from official vaccine medical documents.
|
| 107 |
-
Answer the doctor's question accurately and concisely using only the provided information.
|
| 108 |
-
|
| 109 |
-
## IMPORTANT REQUIREMENTS
|
| 110 |
-
|
| 111 |
-
### Citation and Sourcing
|
| 112 |
-
1. For each fact in your response, include an inline citation in the format [Source] immediately following the information, e.g., [e795ebd28318886c0b1a5395ac30ad90].
|
| 113 |
-
2. Do NOT use 'Source:' in the citation format; use only the Source in square brackets.
|
| 114 |
-
3. If a fact is supported by multiple sources, use the following format:
|
| 115 |
-
- Use adjacent citations: [e795ebd28318886c0b1a5395ac30ad90][21a932b2340bb16707763f57f0ad2]
|
| 116 |
-
4. Use ONLY the provided information and never include facts from your general knowledge.
|
| 117 |
-
|
| 118 |
-
### Content Formatting
|
| 119 |
-
1. When rendering tables:
|
| 120 |
-
- Convert HTML tables into clean Markdown format
|
| 121 |
-
- Preserve all original headers and data rows exactly
|
| 122 |
-
- Include the citation in the table caption, e.g., 'Table: Vaccination Schedule [Source]'
|
| 123 |
-
2. For lists, maintain the original bullet points/numbering and include citations.
|
| 124 |
-
3. Present information concisely but ensure clinical accuracy is never compromised.
|
| 125 |
-
|
| 126 |
-
## Tools
|
| 127 |
-
|
| 128 |
-
You have access to a wide variety of tools. You are responsible for using the tools in any sequence you deem appropriate to complete the task at hand.
|
| 129 |
-
This may require breaking the task into subtasks and using different tools to complete each subtask.
|
| 130 |
-
|
| 131 |
-
You have access to the following tools:
|
| 132 |
-
{tool_desc}
|
| 133 |
-
|
| 134 |
-
## Output Format
|
| 135 |
-
|
| 136 |
-
Please answer in the same language as the question and use the following format:
|
| 137 |
-
|
| 138 |
-
```
|
| 139 |
-
Thought: The current language of the user is: (user's language). I need to use a tool to help me answer the question.
|
| 140 |
-
Action: tool name (one of {tool_names}) if using a tool.
|
| 141 |
-
Action Input: the input to the tool, in a JSON format representing the kwargs (e.g. {{"input": "hello world", "num_beams": 5}})
|
| 142 |
-
```
|
| 143 |
-
|
| 144 |
-
Please ALWAYS start with a Thought.
|
| 145 |
-
|
| 146 |
-
NEVER surround your response with markdown code markers. You may use code markers within your response if you need to.
|
| 147 |
-
|
| 148 |
-
Please use a valid JSON format for the Action Input. Do NOT do this {{"input": "hello world", "num_beams": 5}}.
|
| 149 |
-
|
| 150 |
-
If this format is used, the tool will respond in the following format:
|
| 151 |
-
|
| 152 |
-
```
|
| 153 |
-
Observation: tool response
|
| 154 |
-
```
|
| 155 |
-
|
| 156 |
-
You should keep repeating the above format till you have enough information to answer the question without using any more tools. At that point, you MUST respond in one of the following two formats:
|
| 157 |
-
|
| 158 |
-
```
|
| 159 |
-
Thought: I can answer without using any more tools. I'll use the user's language to answer. Remember to include proper citations
|
| 160 |
-
Answer: [your answer here with proper citations (In the same language as the user's question)]
|
| 161 |
-
```
|
| 162 |
-
|
| 163 |
-
```
|
| 164 |
-
Thought: I cannot answer the question with the provided tools.
|
| 165 |
-
Answer: [your answer here (In the same language as the user's question)]
|
| 166 |
-
```
|
| 167 |
-
|
| 168 |
-
## Current Conversation
|
| 169 |
-
|
| 170 |
-
Below is the current conversation consisting of interleaving human and assistant messages.
|
| 171 |
-
"""
|
| 172 |
-
|
| 173 |
-
try:
|
| 174 |
-
custom_prompt = PromptTemplate(
|
| 175 |
-
template=custom_instructions,
|
| 176 |
-
template_vars=["tool_desc", "tool_names"]
|
| 177 |
-
)
|
| 178 |
-
return custom_prompt
|
| 179 |
-
except:
|
| 180 |
-
# Fallback to simple template
|
| 181 |
-
return PromptTemplate(template=custom_instructions)
|
| 182 |
|
| 183 |
def create_safe_custom_prompt(tools, llm):
|
| 184 |
"""Create a safe version that won't have formatting conflicts"""
|
|
@@ -338,7 +256,7 @@ def process_question_with_sequential_citations(agent, question: str, chunks_dire
|
|
| 338 |
# Load all chunks data to find cited elements
|
| 339 |
all_chunks_data = []
|
| 340 |
min_chunks_files = ["Guide-pratique-de-mise-en-oeuvre-du-calendrier-national-de-vaccination-2023.json",
|
| 341 |
-
"
|
| 342 |
|
| 343 |
for json_file in min_chunks_files:
|
| 344 |
json_path = os.path.join(chunks_directory, json_file)
|
|
|
|
| 97 |
return sequential_response
|
| 98 |
|
| 99 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
|
| 101 |
def create_safe_custom_prompt(tools, llm):
|
| 102 |
"""Create a safe version that won't have formatting conflicts"""
|
|
|
|
| 256 |
# Load all chunks data to find cited elements
|
| 257 |
all_chunks_data = []
|
| 258 |
min_chunks_files = ["Guide-pratique-de-mise-en-oeuvre-du-calendrier-national-de-vaccination-2023.json",
|
| 259 |
+
"Immunization in Practice_WHO_eng_2015.json"]
|
| 260 |
|
| 261 |
for json_file in min_chunks_files:
|
| 262 |
json_path = os.path.join(chunks_directory, json_file)
|