cocoindex-code 0.2.29__tar.gz → 0.2.30__tar.gz

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cocoindex-code
-Version: 0.2.29
+Version: 0.2.30
 Summary: MCP server for indexing and querying codebases using CocoIndex
 Project-URL: Homepage, https://github.com/cocoindex-io/cocoindex-code
 Project-URL: Repository, https://github.com/cocoindex-io/cocoindex-code
@@ -441,7 +441,7 @@ embedding:
   # `ccc init` auto-populates these for known models (e.g. Cohere, Voyage, Nvidia NIM,
   # nomic-ai code-retrieval models, Snowflake arctic-embed).
   # indexing_params:
-  #   input_type: search_document        # litellm: input_type, dimensions
+  #   input_type: search_document        # litellm: input_type
   # query_params:
   #   input_type: search_query           # sentence-transformers: prompt_name
 
@@ -471,7 +471,7 @@ embedding:
 
 OpenAI embeddings (`text-embedding-3-*`, `text-embedding-ada-002`) are intentionally not in the list: they're symmetric and have no equivalent knob.
 
-**Accepted keys:** `prompt_name` (sentence-transformers), `input_type` and `dimensions` (litellm). Other keys are rejected at daemon startup with a clear error.
+**Accepted keys:** `prompt_name` (sentence-transformers) and `input_type` (litellm). Other keys are rejected at daemon startup with a clear error. Note: `dimensions` is intentionally not exposed here — output dimension must be identical for indexing and query, so it's a model-wide setting rather than a per-side knob.
 
 **Doctor checks both sides.** `ccc doctor` exercises the model once with `indexing_params` and once with `query_params`, reporting each as a separate `Model Check (indexing)` / `Model Check (query)` entry — so a misconfiguration on one side is diagnosable without hiding behind the other.
 

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/README.md

@@ -397,7 +397,7 @@ embedding:
   # `ccc init` auto-populates these for known models (e.g. Cohere, Voyage, Nvidia NIM,
   # nomic-ai code-retrieval models, Snowflake arctic-embed).
   # indexing_params:
-  #   input_type: search_document        # litellm: input_type, dimensions
+  #   input_type: search_document        # litellm: input_type
   # query_params:
   #   input_type: search_query           # sentence-transformers: prompt_name
 
@@ -427,7 +427,7 @@ embedding:
 
 OpenAI embeddings (`text-embedding-3-*`, `text-embedding-ada-002`) are intentionally not in the list: they're symmetric and have no equivalent knob.
 
-**Accepted keys:** `prompt_name` (sentence-transformers), `input_type` and `dimensions` (litellm). Other keys are rejected at daemon startup with a clear error.
+**Accepted keys:** `prompt_name` (sentence-transformers) and `input_type` (litellm). Other keys are rejected at daemon startup with a clear error. Note: `dimensions` is intentionally not exposed here — output dimension must be identical for indexing and query, so it's a model-wide setting rather than a per-side knob.
 
 **Doctor checks both sides.** `ccc doctor` exercises the model once with `indexing_params` and once with `query_params`, reporting each as a separate `Model Check (indexing)` / `Model Check (query)` entry — so a misconfiguration on one side is diagnosable without hiding behind the other.
 

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/src/cocoindex_code/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.2.29'
-__version_tuple__ = version_tuple = (0, 2, 29)
+__version__ = version = '0.2.30'
+__version_tuple__ = version_tuple = (0, 2, 30)
 
 __commit_id__ = commit_id = None

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/src/cocoindex_code/daemon.py

@@ -586,7 +586,7 @@ def run_daemon() -> None:
             handshake_warnings.append(
                 _build_backward_compat_warning(user_settings, user_settings_path())
             )
-        embedder = create_embedder(user_settings.embedding)
+        embedder = create_embedder(user_settings.embedding, indexing_params=indexing_params)
     else:
         settings_env_keys = []
         embedder = None

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/src/cocoindex_code/embedder_params.py

@@ -21,13 +21,14 @@ __all__ = [
 
 
 # Accepted kwargs per provider.  Intentionally minimal — we only expose knobs
-# that users have reason to tune.  ``normalize_embeddings`` (sentence-
-# transformers) and ``encoding_format`` (litellm) are deliberately excluded
-# because other code assumes unit vectors (query._l2_to_score) and float
-# payloads (litellm_embedder hardcodes encoding_format="float").
+# that users have reason to tune AND that make sense per-side (indexing vs
+# query).  Excluded keys:
+#   - ``normalize_embeddings`` (sentence-transformers): query._l2_to_score
+#     assumes unit vectors.
+#   - ``encoding_format`` (litellm): litellm_embedder hardcodes "float".
 _ACCEPTED_KWARGS: dict[str, frozenset[str]] = {
     "sentence-transformers": frozenset({"prompt_name"}),
-    "litellm": frozenset({"input_type", "dimensions"}),
+    "litellm": frozenset({"input_type"}),
 }
 
 

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/src/cocoindex_code/settings.py

@@ -544,7 +544,7 @@ _PARAMS_COMMENT_BY_PROVIDER: dict[str, str] = {
     "litellm": (
         "  #\n"
         "  # Extra kwargs passed to the embedder. Supported keys:\n"
-        "  #   input_type, dimensions\n"
+        "  #   input_type\n"
         "  # indexing_params: {}\n"
         "  # query_params: {}\n"
     ),

{cocoindex_code-0.2.29 → cocoindex_code-0.2.30}/src/cocoindex_code/shared.py

@@ -76,8 +76,26 @@ async def check_embedding(
         return EmbeddingCheckResult(dim=None, error=msg)
 
 
-def create_embedder(settings: EmbeddingSettings) -> Embedder:
-    """Create and return an embedder instance based on settings."""
+def create_embedder(
+    settings: EmbeddingSettings,
+    indexing_params: dict[str, Any] | None = None,
+) -> Embedder:
+    """Create and return an embedder instance based on settings.
+
+    For LiteLLM embedders, *indexing_params* (e.g. ``{"input_type": "passage"}``)
+    are passed to the constructor as default kwargs forwarded into every
+    ``litellm.aembedding`` call — including paths that don't go through
+    :data:`INDEXING_EMBED_PARAMS` (e.g. the dimension probe in ``_get_dim``,
+    or any helper that calls ``embed()`` with no per-side kwargs). Per-call
+    overrides (the ``query_params`` spread at query time) still take effect
+    because :meth:`LiteLLMEmbedder._embed` overlays kwargs on top of the
+    constructor's ``self._kwargs``.
+
+    *indexing_params* is ignored for sentence-transformers — its constructor
+    doesn't accept arbitrary kwargs; ``prompt_name`` is a per-call argument
+    only and the indexing default is supplied at the call site via
+    :data:`INDEXING_EMBED_PARAMS`.
+    """
     if settings.provider == "sentence-transformers":
         from cocoindex.ops.sentence_transformers import SentenceTransformerEmbedder
 
@@ -103,6 +121,7 @@ def create_embedder(settings: EmbeddingSettings) -> Embedder:
         instance = PacedLiteLLMEmbedder(
             settings.model,
             min_interval_ms=min_interval_ms,
+            **(dict(indexing_params) if indexing_params else {}),
         )
         logger.info(
             "Embedding model (LiteLLM): %s | min_interval_ms: %s",