2 files changed, 155 insertions, 0 deletions
diff --git a/.venv/lib/python3.12/site-packages/litellm/llms/together_ai/rerank/handler.py b/.venv/lib/python3.12/site-packages/litellm/llms/together_ai/rerank/handler.py
new file mode 100644
index 00000000..c5b02731
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/litellm/llms/together_ai/rerank/handler.py
@@ -0,0 +1,92 @@
+"""
+Re rank api
+
+LiteLLM supports the re rank API format, no paramter transformation occurs
+"""
+
+from typing import Any, Dict, List, Optional, Union
+
+import litellm
+from litellm.llms.base import BaseLLM
+from litellm.llms.custom_httpx.http_handler import (
+    _get_httpx_client,
+    get_async_httpx_client,
+)
+from litellm.llms.together_ai.rerank.transformation import TogetherAIRerankConfig
+from litellm.types.rerank import RerankRequest, RerankResponse
+
+
+class TogetherAIRerank(BaseLLM):
+    def rerank(
+        self,
+        model: str,
+        api_key: str,
+        query: str,
+        documents: List[Union[str, Dict[str, Any]]],
+        top_n: Optional[int] = None,
+        rank_fields: Optional[List[str]] = None,
+        return_documents: Optional[bool] = True,
+        max_chunks_per_doc: Optional[int] = None,
+        _is_async: Optional[bool] = False,
+    ) -> RerankResponse:
+        client = _get_httpx_client()
+
+        request_data = RerankRequest(
+            model=model,
+            query=query,
+            top_n=top_n,
+            documents=documents,
+            rank_fields=rank_fields,
+            return_documents=return_documents,
+        )
+
+        # exclude None values from request_data
+        request_data_dict = request_data.dict(exclude_none=True)
+        if max_chunks_per_doc is not None:
+            raise ValueError("TogetherAI does not support max_chunks_per_doc")
+
+        if _is_async:
+            return self.async_rerank(request_data_dict, api_key)  # type: ignore # Call async method
+
+        response = client.post(
+            "https://api.together.xyz/v1/rerank",
+            headers={
+                "accept": "application/json",
+                "content-type": "application/json",
+                "authorization": f"Bearer {api_key}",
+            },
+            json=request_data_dict,
+        )
+
+        if response.status_code != 200:
+            raise Exception(response.text)
+
+        _json_response = response.json()
+
+        return TogetherAIRerankConfig()._transform_response(_json_response)
+
+    async def async_rerank(  # New async method
+        self,
+        request_data_dict: Dict[str, Any],
+        api_key: str,
+    ) -> RerankResponse:
+        client = get_async_httpx_client(
+            llm_provider=litellm.LlmProviders.TOGETHER_AI
+        )  # Use async client
+
+        response = await client.post(
+            "https://api.together.xyz/v1/rerank",
+            headers={
+                "accept": "application/json",
+                "content-type": "application/json",
+                "authorization": f"Bearer {api_key}",
+            },
+            json=request_data_dict,
+        )
+
+        if response.status_code != 200:
+            raise Exception(response.text)
+
+        _json_response = response.json()
+
+        return TogetherAIRerankConfig()._transform_response(_json_response)
diff --git a/.venv/lib/python3.12/site-packages/litellm/llms/together_ai/rerank/transformation.py b/.venv/lib/python3.12/site-packages/litellm/llms/together_ai/rerank/transformation.py
new file mode 100644
index 00000000..47143769
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/litellm/llms/together_ai/rerank/transformation.py
@@ -0,0 +1,63 @@
+"""
+Transformation logic from Cohere's /v1/rerank format to Together AI's  `/v1/rerank` format. 
+
+Why separate file? Make it easy to see how transformation works
+"""
+
+import uuid
+from typing import List, Optional
+
+from litellm.types.rerank import (
+    RerankBilledUnits,
+    RerankResponse,
+    RerankResponseDocument,
+    RerankResponseMeta,
+    RerankResponseResult,
+    RerankTokens,
+)
+
+
+class TogetherAIRerankConfig:
+    def _transform_response(self, response: dict) -> RerankResponse:
+
+        _billed_units = RerankBilledUnits(**response.get("usage", {}))
+        _tokens = RerankTokens(**response.get("usage", {}))
+        rerank_meta = RerankResponseMeta(billed_units=_billed_units, tokens=_tokens)
+
+        _results: Optional[List[dict]] = response.get("results")
+
+        if _results is None:
+            raise ValueError(f"No results found in the response={response}")
+
+        rerank_results: List[RerankResponseResult] = []
+
+        for result in _results:
+            # Validate required fields exist
+            if not all(key in result for key in ["index", "relevance_score"]):
+                raise ValueError(f"Missing required fields in the result={result}")
+
+            # Get document data if it exists
+            document_data = result.get("document", {})
+            document = (
+                RerankResponseDocument(text=str(document_data.get("text", "")))
+                if document_data
+                else None
+            )
+
+            # Create typed result
+            rerank_result = RerankResponseResult(
+                index=int(result["index"]),
+                relevance_score=float(result["relevance_score"]),
+            )
+
+            # Only add document if it exists
+            if document:
+                rerank_result["document"] = document
+
+            rerank_results.append(rerank_result)
+
+        return RerankResponse(
+            id=response.get("id") or str(uuid.uuid4()),
+            results=rerank_results,
+            meta=rerank_meta,
+        )  # Return response