enh: inline citations

backend/open_webui/config.py

@@ -1181,21 +1181,30 @@ CHUNK_OVERLAP = PersistentConfig(
     int(os.environ.get("CHUNK_OVERLAP", "100")),
 )
 
-DEFAULT_RAG_TEMPLATE = """You are given a user query, some textual context and rules, all inside xml tags. You have to answer the query based on the context while respecting the rules.
+DEFAULT_RAG_TEMPLATE = """### Task:
+Respond to the user query using the provided context, incorporating inline citations in the format [source_id].
+
+### Guidelines:
+- If you don't know the answer, clearly state that.
+- If uncertain, ask the user for clarification.
+- Respond in the same language as the user's query.
+- If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
+- If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
+- Include inline citations using [source_id] corresponding to the sources listed in the context.
+- Do not use XML tags in your response.
+- Ensure citations are concise and directly related to the information provided.
+
+### Example of Citation:
+If the user asks about a specific topic and the information is found in "whitepaper.pdf", the response should include the citation like so:  
+* "According to the study, the proposed method increases efficiency by 20% [whitepaper.pdf]."
+
+### Output:
+Provide a clear and direct response to the user's query, including inline citations in the format [source_id] where relevant.
 
 <context>
 {{CONTEXT}}
 </context>
 
-<rules>
-- If you don't know, just say so.
-- If you are not sure, ask for clarification.
-- Answer in the same language as the user query.
-- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
-- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
-- Answer directly and without using xml tags.
-</rules>
-
 <user_query>
 {{QUERY}}
 </user_query>

backend/open_webui/main.py

@@ -679,7 +679,13 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
 
         # If context is not empty, insert it into the messages
         if len(contexts) > 0:
-            context_string = "/n".join(contexts).strip()
+            context_string = ""
+            for context_idx, context in enumerate(contexts):
+                print(context)
+                source_id = citations[context_idx].get("source", {}).get("name", "")
+                context_string += f"<source><source_id>{source_id}</source_id><source_context>{context}</source_context></source>\n"
+
+            context_string = context_string.strip()
             prompt = get_last_user_message(body["messages"])
 
             if prompt is None: