fix: add trust_code env config

hindsight-api/hindsight_api/config.py

@@ -66,6 +66,7 @@
 ENV_EMBEDDINGS_PROVIDER = "HINDSIGHT_API_EMBEDDINGS_PROVIDER"
 ENV_EMBEDDINGS_LOCAL_MODEL = "HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL"
 ENV_EMBEDDINGS_LOCAL_FORCE_CPU = "HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU"
+ENV_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE = "HINDSIGHT_API_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE"
 ENV_EMBEDDINGS_TEI_URL = "HINDSIGHT_API_EMBEDDINGS_TEI_URL"
 ENV_EMBEDDINGS_OPENAI_API_KEY = "HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY"
 ENV_EMBEDDINGS_OPENAI_MODEL = "HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL"
@@ -98,6 +99,7 @@
 ENV_RERANKER_LOCAL_MODEL = "HINDSIGHT_API_RERANKER_LOCAL_MODEL"
 ENV_RERANKER_LOCAL_FORCE_CPU = "HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU"
 ENV_RERANKER_LOCAL_MAX_CONCURRENT = "HINDSIGHT_API_RERANKER_LOCAL_MAX_CONCURRENT"
+ENV_RERANKER_LOCAL_TRUST_REMOTE_CODE = "HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE"
 ENV_RERANKER_TEI_URL = "HINDSIGHT_API_RERANKER_TEI_URL"
 ENV_RERANKER_TEI_BATCH_SIZE = "HINDSIGHT_API_RERANKER_TEI_BATCH_SIZE"
 ENV_RERANKER_TEI_MAX_CONCURRENT = "HINDSIGHT_API_RERANKER_TEI_MAX_CONCURRENT"
@@ -201,13 +203,17 @@
 DEFAULT_EMBEDDINGS_PROVIDER = "local"
 DEFAULT_EMBEDDINGS_LOCAL_MODEL = "BAAI/bge-small-en-v1.5"
 DEFAULT_EMBEDDINGS_LOCAL_FORCE_CPU = False  # Force CPU mode for local embeddings (avoids MPS/XPC issues on macOS)
+DEFAULT_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE = False  # Security: disabled by default, required for some models
 DEFAULT_EMBEDDINGS_OPENAI_MODEL = "text-embedding-3-small"
 DEFAULT_EMBEDDING_DIMENSION = 384
 
 DEFAULT_RERANKER_PROVIDER = "local"
 DEFAULT_RERANKER_LOCAL_MODEL = "cross-encoder/ms-marco-MiniLM-L-6-v2"
 DEFAULT_RERANKER_LOCAL_FORCE_CPU = False  # Force CPU mode for local reranker (avoids MPS/XPC issues on macOS)
 DEFAULT_RERANKER_LOCAL_MAX_CONCURRENT = 4  # Limit concurrent CPU-bound reranking to prevent thrashing
+DEFAULT_RERANKER_LOCAL_TRUST_REMOTE_CODE = (
+    False  # Security: disabled by default, required for some models like jina-reranker-v2
+)
 DEFAULT_RERANKER_TEI_BATCH_SIZE = 128
 DEFAULT_RERANKER_TEI_MAX_CONCURRENT = 8
 DEFAULT_RERANKER_MAX_CANDIDATES = 300
@@ -404,6 +410,7 @@ class HindsightConfig:
     embeddings_provider: str
     embeddings_local_model: str
     embeddings_local_force_cpu: bool
+    embeddings_local_trust_remote_code: bool
     embeddings_tei_url: str | None
     embeddings_openai_base_url: str | None
     embeddings_cohere_api_key: str | None
@@ -418,6 +425,7 @@ class HindsightConfig:
     reranker_local_model: str
     reranker_local_force_cpu: bool
     reranker_local_max_concurrent: int
+    reranker_local_trust_remote_code: bool
     reranker_tei_url: str | None
     reranker_tei_batch_size: int
     reranker_tei_max_concurrent: int
@@ -607,6 +615,10 @@ def from_env(cls) -> "HindsightConfig":
                 ENV_EMBEDDINGS_LOCAL_FORCE_CPU, str(DEFAULT_EMBEDDINGS_LOCAL_FORCE_CPU)
             ).lower()
             in ("true", "1"),
+            embeddings_local_trust_remote_code=os.getenv(
+                ENV_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE, str(DEFAULT_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE)
+            ).lower()
+            in ("true", "1"),
             embeddings_tei_url=os.getenv(ENV_EMBEDDINGS_TEI_URL),
             embeddings_openai_base_url=os.getenv(ENV_EMBEDDINGS_OPENAI_BASE_URL) or None,
             # Cohere embeddings (with backward-compatible fallback to shared API key)
@@ -628,6 +640,10 @@ def from_env(cls) -> "HindsightConfig":
             reranker_local_max_concurrent=int(
                 os.getenv(ENV_RERANKER_LOCAL_MAX_CONCURRENT, str(DEFAULT_RERANKER_LOCAL_MAX_CONCURRENT))
             ),
+            reranker_local_trust_remote_code=os.getenv(
+                ENV_RERANKER_LOCAL_TRUST_REMOTE_CODE, str(DEFAULT_RERANKER_LOCAL_TRUST_REMOTE_CODE)
+            ).lower()
+            in ("true", "1"),
             reranker_tei_url=os.getenv(ENV_RERANKER_TEI_URL),
             reranker_tei_batch_size=int(os.getenv(ENV_RERANKER_TEI_BATCH_SIZE, str(DEFAULT_RERANKER_TEI_BATCH_SIZE))),
             reranker_tei_max_concurrent=int(

hindsight-api/hindsight_api/engine/cross_encoder.py

@@ -24,6 +24,7 @@
     DEFAULT_RERANKER_LOCAL_FORCE_CPU,
     DEFAULT_RERANKER_LOCAL_MAX_CONCURRENT,
     DEFAULT_RERANKER_LOCAL_MODEL,
+    DEFAULT_RERANKER_LOCAL_TRUST_REMOTE_CODE,
     DEFAULT_RERANKER_PROVIDER,
     DEFAULT_RERANKER_TEI_BATCH_SIZE,
     DEFAULT_RERANKER_TEI_MAX_CONCURRENT,
@@ -34,6 +35,7 @@
     ENV_RERANKER_LOCAL_FORCE_CPU,
     ENV_RERANKER_LOCAL_MAX_CONCURRENT,
     ENV_RERANKER_LOCAL_MODEL,
+    ENV_RERANKER_LOCAL_TRUST_REMOTE_CODE,
     ENV_RERANKER_PROVIDER,
     ENV_RERANKER_TEI_BATCH_SIZE,
     ENV_RERANKER_TEI_MAX_CONCURRENT,
@@ -98,7 +100,13 @@ class LocalSTCrossEncoder(CrossEncoderModel):
     _executor: ThreadPoolExecutor | None = None
     _max_concurrent: int = 4  # Limit concurrent CPU-bound reranking calls
 
-    def __init__(self, model_name: str | None = None, max_concurrent: int = 4, force_cpu: bool = False):
+    def __init__(
+        self,
+        model_name: str | None = None,
+        max_concurrent: int = 4,
+        force_cpu: bool = False,
+        trust_remote_code: bool = False,
+    ):
         """
         Initialize local SentenceTransformers cross-encoder.
 
@@ -109,9 +117,13 @@ def __init__(self, model_name: str | None = None, max_concurrent: int = 4, force
                            Higher values may cause CPU thrashing under load.
             force_cpu: Force CPU mode (avoids MPS/XPC issues on macOS in daemon mode).
                       Default: False
+            trust_remote_code: Allow loading models with custom code (security risk).
+                              Required for some models like jina-reranker-v2-base-multilingual.
+                              Default: False (disabled for security)
         """
         self.model_name = model_name or DEFAULT_RERANKER_LOCAL_MODEL
         self.force_cpu = force_cpu
+        self.trust_remote_code = trust_remote_code
         self._model = None
         LocalSTCrossEncoder._max_concurrent = max_concurrent
 
@@ -177,6 +189,7 @@ async def initialize(self) -> None:
                     self.model_name,
                     device=device,
                     model_kwargs={"low_cpu_mem_usage": False},
+                    trust_remote_code=self.trust_remote_code,
                 )
             finally:
                 # Restore original logging level
@@ -843,6 +856,7 @@ def create_cross_encoder_from_env() -> CrossEncoderModel:
             model_name=config.reranker_local_model,
             max_concurrent=config.reranker_local_max_concurrent,
             force_cpu=config.reranker_local_force_cpu,
+            trust_remote_code=config.reranker_local_trust_remote_code,
         )
     elif provider == "cohere":
         api_key = config.reranker_cohere_api_key

hindsight-api/hindsight_api/engine/embeddings.py

@@ -21,12 +21,14 @@
     DEFAULT_EMBEDDINGS_LITELLM_MODEL,
     DEFAULT_EMBEDDINGS_LOCAL_FORCE_CPU,
     DEFAULT_EMBEDDINGS_LOCAL_MODEL,
+    DEFAULT_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE,
     DEFAULT_EMBEDDINGS_OPENAI_MODEL,
     DEFAULT_EMBEDDINGS_PROVIDER,
     DEFAULT_LITELLM_API_BASE,
     ENV_EMBEDDINGS_COHERE_API_KEY,
     ENV_EMBEDDINGS_LOCAL_FORCE_CPU,
     ENV_EMBEDDINGS_LOCAL_MODEL,
+    ENV_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE,
     ENV_EMBEDDINGS_OPENAI_API_KEY,
     ENV_EMBEDDINGS_OPENAI_BASE_URL,
     ENV_EMBEDDINGS_OPENAI_MODEL,
@@ -90,7 +92,7 @@ class LocalSTEmbeddings(Embeddings):
     The embedding dimension is auto-detected from the model.
     """
 
-    def __init__(self, model_name: str | None = None, force_cpu: bool = False):
+    def __init__(self, model_name: str | None = None, force_cpu: bool = False, trust_remote_code: bool = False):
         """
         Initialize local SentenceTransformers embeddings.
 
@@ -99,9 +101,13 @@ def __init__(self, model_name: str | None = None, force_cpu: bool = False):
                        Default: BAAI/bge-small-en-v1.5
             force_cpu: Force CPU mode (avoids MPS/XPC issues on macOS in daemon mode).
                       Default: False
+            trust_remote_code: Allow loading models with custom code (security risk).
+                              Required for some models with custom architectures.
+                              Default: False (disabled for security)
         """
         self.model_name = model_name or DEFAULT_EMBEDDINGS_LOCAL_MODEL
         self.force_cpu = force_cpu
+        self.trust_remote_code = trust_remote_code
         self._model = None
         self._dimension: int | None = None
 
@@ -171,6 +177,7 @@ async def initialize(self) -> None:
                     self.model_name,
                     device=device,
                     model_kwargs={"low_cpu_mem_usage": False},
+                    trust_remote_code=self.trust_remote_code,
                 )
             finally:
                 # Restore original logging level
@@ -736,6 +743,7 @@ def create_embeddings_from_env() -> Embeddings:
         return LocalSTEmbeddings(
             model_name=config.embeddings_local_model,
             force_cpu=config.embeddings_local_force_cpu,
+            trust_remote_code=config.embeddings_local_trust_remote_code,
         )
     elif provider == "openai":
         # Use dedicated embeddings API key, or fall back to LLM API key

hindsight-api/hindsight_api/main.py

@@ -197,6 +197,7 @@ def main():
             embeddings_provider=config.embeddings_provider,
             embeddings_local_model=config.embeddings_local_model,
             embeddings_local_force_cpu=config.embeddings_local_force_cpu,
+            embeddings_local_trust_remote_code=config.embeddings_local_trust_remote_code,
             embeddings_tei_url=config.embeddings_tei_url,
             embeddings_openai_base_url=config.embeddings_openai_base_url,
             embeddings_cohere_api_key=config.embeddings_cohere_api_key,
@@ -209,6 +210,7 @@ def main():
             reranker_local_model=config.reranker_local_model,
             reranker_local_force_cpu=config.reranker_local_force_cpu,
             reranker_local_max_concurrent=config.reranker_local_max_concurrent,
+            reranker_local_trust_remote_code=config.reranker_local_trust_remote_code,
             reranker_tei_url=config.reranker_tei_url,
             reranker_tei_batch_size=config.reranker_tei_batch_size,
             reranker_tei_max_concurrent=config.reranker_tei_max_concurrent,

hindsight-docs/docs/developer/configuration.md

@@ -269,6 +269,7 @@ export HINDSIGHT_API_RETAIN_LLM_MAX_BACKOFF=120.0    # Cap at 2min instead of 1m
 |----------|-------------|---------|
 | `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, `openai`, `cohere`, or `litellm` | `local` |
 | `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL` | Model for local provider | `BAAI/bge-small-en-v1.5` |
+| `HINDSIGHT_API_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE` | Allow loading models with custom code (security risk, disabled by default) | `false` |
 | `HINDSIGHT_API_EMBEDDINGS_TEI_URL` | TEI server URL | - |
 | `HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY` | OpenAI API key (falls back to `HINDSIGHT_API_LLM_API_KEY`) | - |
 | `HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL` | OpenAI embedding model | `text-embedding-3-small` |
@@ -285,6 +286,11 @@ export HINDSIGHT_API_RETAIN_LLM_MAX_BACKOFF=120.0    # Cap at 2min instead of 1m
 export HINDSIGHT_API_EMBEDDINGS_PROVIDER=local
 export HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=BAAI/bge-small-en-v1.5
 
+# Local with custom model requiring trust_remote_code
+# WARNING: Only enable trust_remote_code for models you trust (security risk)
+# export HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=your-custom-model
+# export HINDSIGHT_API_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE=true
+
 # OpenAI - cloud-based embeddings
 export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
 export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxxxxxxxxxxx  # or reuses HINDSIGHT_API_LLM_API_KEY
@@ -341,6 +347,7 @@ Supported OpenAI embedding dimensions:
 | `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local`, `tei`, `cohere`, `flashrank`, `litellm`, or `rrf` | `local` |
 | `HINDSIGHT_API_RERANKER_LOCAL_MODEL` | Model for local provider | `cross-encoder/ms-marco-MiniLM-L-6-v2` |
 | `HINDSIGHT_API_RERANKER_LOCAL_MAX_CONCURRENT` | Max concurrent local reranking (prevents CPU thrashing under load) | `4` |
+| `HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE` | Allow loading models with custom code (security risk, disabled by default) | `false` |
 | `HINDSIGHT_API_RERANKER_TEI_URL` | TEI server URL | - |
 | `HINDSIGHT_API_RERANKER_TEI_BATCH_SIZE` | Batch size for TEI reranking | `128` |
 | `HINDSIGHT_API_RERANKER_TEI_MAX_CONCURRENT` | Max concurrent TEI reranking requests | `8` |
@@ -358,6 +365,12 @@ Supported OpenAI embedding dimensions:
 export HINDSIGHT_API_RERANKER_PROVIDER=local
 export HINDSIGHT_API_RERANKER_LOCAL_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
 
+# Local with custom model requiring trust_remote_code (e.g., jina-reranker-v2)
+# WARNING: Only enable trust_remote_code for models you trust (security risk)
+export HINDSIGHT_API_RERANKER_PROVIDER=local
+export HINDSIGHT_API_RERANKER_LOCAL_MODEL=jinaai/jina-reranker-v2-base-multilingual
+export HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE=true
+
 # TEI - for high-performance inference
 export HINDSIGHT_API_RERANKER_PROVIDER=tei
 export HINDSIGHT_API_RERANKER_TEI_URL=http://localhost:8081