Merge pull request #14164 from TomeHirata/citation-supported-text-3

Add supported text field to anthropic citation response

litellm/llms/anthropic/chat/transformation.py

@@ -804,7 +804,15 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
             if content.get("citations") is not None:
                 if citations is None:
                     citations = []
-                citations.append(content["citations"])
+                citations.append(
+                    [
+                        {
+                            **citation,
+                            "supported_text": content.get("text", ""),
+                        }
+                        for citation in content["citations"]
+                    ]
+                )
         if thinking_blocks is not None:
             reasoning_content = ""
             for block in thinking_blocks:

tests/llm_translation/test_anthropic_completion.py

@@ -256,7 +256,6 @@ def test_anthropic_tool_streaming():
     for chunk in anthropic_chunk_list:
         parsed_chunk = response_iter.chunk_parser(chunk)
         if tool_use := parsed_chunk.get("tool_use"):
-
             # We only increment when a new block starts
             if tool_use.get("id") is not None:
                 correct_tool_index += 1
@@ -920,6 +919,14 @@ def test_anthropic_citations_api():
     citations = resp.choices[0].message.provider_specific_fields["citations"]
 
     assert citations is not None
+    if citations:
+        citation = citations[0][0]
+        assert "supported_text" in citation
+        assert "cited_text" in citation
+        assert "document_index" in citation
+        assert "document_title" in citation
+        assert "start_char_index" in citation
+        assert "end_char_index" in citation
 
 
 def test_anthropic_citations_api_streaming():
@@ -955,11 +962,9 @@ def test_anthropic_citations_api_streaming():
     has_citations = False
     for chunk in resp:
         print(f"returned chunk: {chunk}")
-        if (
-            chunk.choices[0].delta.provider_specific_fields
-            and "citation" in chunk.choices[0].delta.provider_specific_fields
-        ):
-            has_citations = True
+        if provider_specific_fields := chunk.choices[0].delta.provider_specific_fields:
+            if "citation" in provider_specific_fields:
+                has_citations = True
 
     assert has_citations
 

tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py

@@ -183,7 +183,30 @@ def test_extract_response_content_with_citations():
     }
 
     _, citations, _, _, _ = config.extract_response_content(completion_response)
-    assert citations is not None
+    assert citations == [
+        [
+            {
+                "type": "char_location",
+                "cited_text": "The grass is green. ",
+                "document_index": 0,
+                "document_title": "My Document",
+                "start_char_index": 0,
+                "end_char_index": 20,
+                "supported_text": "the grass is green",
+            },
+        ],
+        [
+            {
+                "type": "char_location",
+                "cited_text": "The sky is blue.",
+                "document_index": 0,
+                "document_title": "My Document",
+                "start_char_index": 20,
+                "end_char_index": 36,
+                "supported_text": "the sky is blue",
+            },
+        ],
+    ]
 
 
 def test_map_tool_helper():