Remove Key Features section from Slack RAG examples

- Simplified documentation by removing the bullet point list
- Keeps the focus on the actual examples and screenshots

.gitignore

@@ -105,6 +105,3 @@ apps/multimodal/vision-based-pdf-multi-vector/multi-vector-colpali-native-weavia
 # The following line used to force-add a large demo PDF; remove it to satisfy pre-commit:
 # !apps/multimodal/vision-based-pdf-multi-vector/pdfs/2004.12832v2.pdf
 !apps/multimodal/vision-based-pdf-multi-vector/fig/*
-
-# AUR build directory (Arch Linux)
-paru-bin/

README.md

@@ -1213,7 +1213,3 @@ This work is done at [**Berkeley Sky Computing Lab**](https://sky.cs.berkeley.ed
 <p align="center">
   Made with ❤️ by the Leann team
 </p>
-
-## 🤖 Explore LEANN with AI
-
-LEANN is indexed on [DeepWiki](https://deepwiki.com/yichuan-w/LEANN), so you can ask questions to LLMs using Deep Research to explore the codebase and get help to add new features.

apps/base_rag_example.py

@@ -180,14 +180,14 @@ class BaseRAGExample(ABC):
         ast_group.add_argument(
             "--ast-chunk-size",
             type=int,
-            default=300,
-            help="Maximum CHARACTERS per AST chunk (default: 300). Final chunks may be larger due to overlap. For 512 token models: recommended 300 chars",
+            default=512,
+            help="Maximum characters per AST chunk (default: 512)",
         )
         ast_group.add_argument(
             "--ast-chunk-overlap",
             type=int,
             default=64,
-            help="Overlap between AST chunks in CHARACTERS (default: 64). Added to chunk size, not included in it",
+            help="Overlap between AST chunks (default: 64)",
         )
         ast_group.add_argument(
             "--code-file-extensions",

packages/leann-backend-hnsw/CMakeLists.txt

@@ -29,25 +29,12 @@ if(APPLE)
     set(CMAKE_OSX_DEPLOYMENT_TARGET "11.0" CACHE STRING "Minimum macOS version")
 endif()
 
-# Find ZMQ using pkg-config with IMPORTED_TARGET for automatic target creation
+# Use system ZeroMQ instead of building from source
 find_package(PkgConfig REQUIRED)
-
-# On ARM64 macOS, ensure pkg-config finds ARM64 Homebrew packages first
-if(APPLE AND CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
-    set(ENV{PKG_CONFIG_PATH} "/opt/homebrew/lib/pkgconfig:/opt/homebrew/share/pkgconfig:$ENV{PKG_CONFIG_PATH}")
-endif()
-
-pkg_check_modules(ZMQ REQUIRED IMPORTED_TARGET libzmq)
-
-# This creates PkgConfig::ZMQ target automatically with correct properties
-if(TARGET PkgConfig::ZMQ)
-    message(STATUS "Found and configured ZMQ target: PkgConfig::ZMQ")
-else()
-    message(FATAL_ERROR "pkg_check_modules did not create IMPORTED target for ZMQ.")
-endif()
+pkg_check_modules(ZMQ REQUIRED libzmq)
 
 # Add cppzmq headers
-include_directories(SYSTEM third_party/cppzmq)
+include_directories(third_party/cppzmq)
 
 # Configure msgpack-c - disable boost dependency
 set(MSGPACK_USE_BOOST OFF CACHE BOOL "" FORCE)

packages/leann-core/src/leann/api.py

@@ -1236,17 +1236,6 @@ class LeannChat:
             "Please provide the best answer you can based on this context and your knowledge."
         )
 
-        print("The context provided to the LLM is:")
-        print(f"{'Relevance':<10} | {'Chunk id':<10} | {'Content':<60} | {'Source':<80}")
-        print("-" * 150)
-        for r in results:
-            chunk_relevance = f"{r.score:.3f}"
-            chunk_id = r.id
-            chunk_content = r.text[:60]
-            chunk_source = r.metadata.get("source", "")[:80]
-            print(
-                f"{chunk_relevance:<10} | {chunk_id:<10} | {chunk_content:<60} | {chunk_source:<80}"
-            )
         ask_time = time.time()
         ans = self.llm.ask(prompt, **llm_kwargs)
         ask_time = time.time() - ask_time

packages/leann-core/src/leann/chat.py

@@ -834,11 +834,6 @@ class OpenAIChat(LLMInterface):
 
         try:
             response = self.client.chat.completions.create(**params)
-            print(
-                f"Total tokens = {response.usage.total_tokens}, prompt tokens = {response.usage.prompt_tokens}, completion tokens = {response.usage.completion_tokens}"
-            )
-            if response.choices[0].finish_reason == "length":
-                print("The query is exceeding the maximum allowed number of tokens")
             return response.choices[0].message.content.strip()
         except Exception as e:
             logger.error(f"Error communicating with OpenAI: {e}")

packages/leann-core/src/leann/chunking_utils.py

@@ -11,119 +11,6 @@ from llama_index.core.node_parser import SentenceSplitter
 
 logger = logging.getLogger(__name__)
 
-
-def estimate_token_count(text: str) -> int:
-    """
-    Estimate token count for a text string.
-    Uses conservative estimation: ~4 characters per token for natural text,
-    ~1.2 tokens per character for code (worse tokenization).
-
-    Args:
-        text: Input text to estimate tokens for
-
-    Returns:
-        Estimated token count
-    """
-    try:
-        import tiktoken
-
-        encoder = tiktoken.get_encoding("cl100k_base")
-        return len(encoder.encode(text))
-    except ImportError:
-        # Fallback: Conservative character-based estimation
-        # Assume worst case for code: 1.2 tokens per character
-        return int(len(text) * 1.2)
-
-
-def calculate_safe_chunk_size(
-    model_token_limit: int,
-    overlap_tokens: int,
-    chunking_mode: str = "traditional",
-    safety_factor: float = 0.9,
-) -> int:
-    """
-    Calculate safe chunk size accounting for overlap and safety margin.
-
-    Args:
-        model_token_limit: Maximum tokens supported by embedding model
-        overlap_tokens: Overlap size (tokens for traditional, chars for AST)
-        chunking_mode: "traditional" (tokens) or "ast" (characters)
-        safety_factor: Safety margin (0.9 = 10% safety margin)
-
-    Returns:
-        Safe chunk size: tokens for traditional, characters for AST
-    """
-    safe_limit = int(model_token_limit * safety_factor)
-
-    if chunking_mode == "traditional":
-        # Traditional chunking uses tokens
-        # Max chunk = chunk_size + overlap, so chunk_size = limit - overlap
-        return max(1, safe_limit - overlap_tokens)
-    else:  # AST chunking
-        # AST uses characters, need to convert
-        # Conservative estimate: 1.2 tokens per char for code
-        overlap_chars = int(overlap_tokens * 3)  # ~3 chars per token for code
-        safe_chars = int(safe_limit / 1.2)
-        return max(1, safe_chars - overlap_chars)
-
-
-def validate_chunk_token_limits(chunks: list[str], max_tokens: int = 512) -> tuple[list[str], int]:
-    """
-    Validate that chunks don't exceed token limits and truncate if necessary.
-
-    Args:
-        chunks: List of text chunks to validate
-        max_tokens: Maximum tokens allowed per chunk
-
-    Returns:
-        Tuple of (validated_chunks, num_truncated)
-    """
-    validated_chunks = []
-    num_truncated = 0
-
-    for i, chunk in enumerate(chunks):
-        estimated_tokens = estimate_token_count(chunk)
-
-        if estimated_tokens > max_tokens:
-            # Truncate chunk to fit token limit
-            try:
-                import tiktoken
-
-                encoder = tiktoken.get_encoding("cl100k_base")
-                tokens = encoder.encode(chunk)
-                if len(tokens) > max_tokens:
-                    truncated_tokens = tokens[:max_tokens]
-                    truncated_chunk = encoder.decode(truncated_tokens)
-                    validated_chunks.append(truncated_chunk)
-                    num_truncated += 1
-                    logger.warning(
-                        f"Truncated chunk {i} from {len(tokens)} to {max_tokens} tokens "
-                        f"(from {len(chunk)} to {len(truncated_chunk)} characters)"
-                    )
-                else:
-                    validated_chunks.append(chunk)
-            except ImportError:
-                # Fallback: Conservative character truncation
-                char_limit = int(max_tokens / 1.2)  # Conservative for code
-                if len(chunk) > char_limit:
-                    truncated_chunk = chunk[:char_limit]
-                    validated_chunks.append(truncated_chunk)
-                    num_truncated += 1
-                    logger.warning(
-                        f"Truncated chunk {i} from {len(chunk)} to {char_limit} characters "
-                        f"(conservative estimate for {max_tokens} tokens)"
-                    )
-                else:
-                    validated_chunks.append(chunk)
-        else:
-            validated_chunks.append(chunk)
-
-    if num_truncated > 0:
-        logger.warning(f"Truncated {num_truncated}/{len(chunks)} chunks to fit token limits")
-
-    return validated_chunks, num_truncated
-
-
 # Code file extensions supported by astchunk
 CODE_EXTENSIONS = {
     ".py": "python",
@@ -195,17 +82,6 @@ def create_ast_chunks(
             continue
 
         try:
-            # Warn if AST chunk size + overlap might exceed common token limits
-            estimated_max_tokens = int(
-                (max_chunk_size + chunk_overlap) * 1.2
-            )  # Conservative estimate
-            if estimated_max_tokens > 512:
-                logger.warning(
-                    f"AST chunk size ({max_chunk_size}) + overlap ({chunk_overlap}) = {max_chunk_size + chunk_overlap} chars "
-                    f"may exceed 512 token limit (~{estimated_max_tokens} tokens estimated). "
-                    f"Consider reducing --ast-chunk-size to {int(400 / 1.2)} or --ast-chunk-overlap to {int(50 / 1.2)}"
-                )
-
             configs = {
                 "max_chunk_size": max_chunk_size,
                 "language": language,
@@ -341,14 +217,4 @@ def create_text_chunks(
         all_chunks = create_traditional_chunks(documents, chunk_size, chunk_overlap)
 
     logger.info(f"Total chunks created: {len(all_chunks)}")
-
-    # Validate chunk token limits (default to 512 for safety)
-    # This provides a safety net for embedding models with token limits
-    validated_chunks, num_truncated = validate_chunk_token_limits(all_chunks, max_tokens=512)
-
-    if num_truncated > 0:
-        logger.info(
-            f"Post-chunking validation: {num_truncated} chunks were truncated to fit 512 token limit"
-        )
-
-    return validated_chunks
+    return all_chunks

packages/leann-core/src/leann/cli.py

@@ -1,6 +1,5 @@
 import argparse
 import asyncio
-import time
 from pathlib import Path
 from typing import Any, Optional, Union
 
@@ -107,7 +106,7 @@ Examples:
             help="Documents directories and/or files (default: current directory)",
         )
         build_parser.add_argument(
-            "--backend-name",
+            "--backend",
             type=str,
             default="hnsw",
             choices=["hnsw", "diskann"],
@@ -181,25 +180,25 @@ Examples:
             "--doc-chunk-size",
             type=int,
             default=256,
-            help="Document chunk size in TOKENS (default: 256). Final chunks may be larger due to overlap. For 512 token models: recommended 350 tokens (350 + 128 overlap = 478 max)",
+            help="Document chunk size in tokens/characters (default: 256)",
         )
         build_parser.add_argument(
             "--doc-chunk-overlap",
             type=int,
             default=128,
-            help="Document chunk overlap in TOKENS (default: 128). Added to chunk size, not included in it",
+            help="Document chunk overlap (default: 128)",
         )
         build_parser.add_argument(
             "--code-chunk-size",
             type=int,
             default=512,
-            help="Code chunk size in TOKENS (default: 512). Final chunks may be larger due to overlap. For 512 token models: recommended 400 tokens (400 + 50 overlap = 450 max)",
+            help="Code chunk size in tokens/lines (default: 512)",
         )
         build_parser.add_argument(
             "--code-chunk-overlap",
             type=int,
             default=50,
-            help="Code chunk overlap in TOKENS (default: 50). Added to chunk size, not included in it",
+            help="Code chunk overlap (default: 50)",
         )
         build_parser.add_argument(
             "--use-ast-chunking",
@@ -209,14 +208,14 @@ Examples:
         build_parser.add_argument(
             "--ast-chunk-size",
             type=int,
-            default=300,
-            help="AST chunk size in CHARACTERS (non-whitespace) (default: 300). Final chunks may be larger due to overlap and expansion. For 512 token models: recommended 300 chars (300 + 64 overlap ~= 480 tokens)",
+            default=768,
+            help="AST chunk size in characters (default: 768)",
         )
         build_parser.add_argument(
             "--ast-chunk-overlap",
             type=int,
-            default=64,
-            help="AST chunk overlap in CHARACTERS (default: 64). Added to chunk size, not included in it. ~1.2 tokens per character for code",
+            default=96,
+            help="AST chunk overlap in characters (default: 96)",
         )
         build_parser.add_argument(
             "--ast-fallback-traditional",
@@ -255,11 +254,6 @@ Examples:
             action="store_true",
             help="Non-interactive mode: automatically select index without prompting",
         )
-        search_parser.add_argument(
-            "--show-metadata",
-            action="store_true",
-            help="Display file paths and metadata in search results",
-        )
 
         # Ask command
         ask_parser = subparsers.add_parser("ask", help="Ask questions")
@@ -1192,7 +1186,6 @@ Examples:
                 for doc in other_docs:
                     file_path = doc.metadata.get("file_path", "")
                     if file_filter(file_path):
-                        doc.metadata["source"] = file_path
                         filtered_docs.append(doc)
 
                 documents.extend(filtered_docs)
@@ -1268,7 +1261,7 @@ Examples:
                 from .chunking_utils import create_text_chunks
 
                 # Use enhanced chunking with AST support
-                chunk_texts = create_text_chunks(
+                all_texts = create_text_chunks(
                     documents,
                     chunk_size=self.node_parser.chunk_size,
                     chunk_overlap=self.node_parser.chunk_overlap,
@@ -1279,14 +1272,6 @@ Examples:
                     ast_fallback_traditional=getattr(args, "ast_fallback_traditional", True),
                 )
 
-                # Note: AST chunking currently returns plain text chunks without metadata
-                # We preserve basic file info by associating chunks with their source documents
-                # For better metadata preservation, documents list order should be maintained
-                for chunk_text in chunk_texts:
-                    # TODO: Enhance create_text_chunks to return metadata alongside text
-                    # For now, we store chunks with empty metadata
-                    all_texts.append({"text": chunk_text, "metadata": {}})
-
             except ImportError as e:
                 print(
                     f"⚠️  AST chunking utilities not available in package ({e}), falling back to traditional chunking"
@@ -1298,27 +1283,14 @@ Examples:
             for doc in tqdm(documents, desc="Chunking documents", unit="doc"):
                 # Check if this is a code file based on source path
                 source_path = doc.metadata.get("source", "")
-                file_path = doc.metadata.get("file_path", "")
                 is_code_file = any(source_path.endswith(ext) for ext in code_file_exts)
 
-                # Extract metadata to preserve with chunks
-                chunk_metadata = {
-                    "file_path": file_path or source_path,
-                    "file_name": doc.metadata.get("file_name", ""),
-                }
-
-                # Add optional metadata if available
-                if "creation_date" in doc.metadata:
-                    chunk_metadata["creation_date"] = doc.metadata["creation_date"]
-                if "last_modified_date" in doc.metadata:
-                    chunk_metadata["last_modified_date"] = doc.metadata["last_modified_date"]
-
                 # Use appropriate parser based on file type
                 parser = self.code_parser if is_code_file else self.node_parser
                 nodes = parser.get_nodes_from_documents([doc])
 
                 for node in nodes:
-                    all_texts.append({"text": node.get_content(), "metadata": chunk_metadata})
+                    all_texts.append(node.get_content())
 
         print(f"Loaded {len(documents)} documents, {len(all_texts)} chunks")
         return all_texts
@@ -1393,7 +1365,7 @@ Examples:
 
         index_dir.mkdir(parents=True, exist_ok=True)
 
-        print(f"Building index '{index_name}' with {args.backend_name} backend...")
+        print(f"Building index '{index_name}' with {args.backend} backend...")
 
         embedding_options: dict[str, Any] = {}
         if args.embedding_mode == "ollama":
@@ -1405,7 +1377,7 @@ Examples:
                 embedding_options["api_key"] = resolved_embedding_key
 
         builder = LeannBuilder(
-            backend_name=args.backend_name,
+            backend_name=args.backend,
             embedding_model=args.embedding_model,
             embedding_mode=args.embedding_mode,
             embedding_options=embedding_options or None,
@@ -1416,8 +1388,8 @@ Examples:
             num_threads=args.num_threads,
         )
 
-        for chunk in all_texts:
-            builder.add_text(chunk["text"], metadata=chunk["metadata"])
+        for chunk_text in all_texts:
+            builder.add_text(chunk_text)
 
         builder.build_index(index_path)
         print(f"Index built at {index_path}")
@@ -1538,25 +1510,7 @@ Examples:
         print(f"Search results for '{query}' (top {len(results)}):")
         for i, result in enumerate(results, 1):
             print(f"{i}. Score: {result.score:.3f}")
-
-            # Display metadata if flag is set
-            if args.show_metadata and result.metadata:
-                file_path = result.metadata.get("file_path", "")
-                if file_path:
-                    print(f"   📄 File: {file_path}")
-
-                file_name = result.metadata.get("file_name", "")
-                if file_name and file_name != file_path:
-                    print(f"   📝 Name: {file_name}")
-
-                # Show timestamps if available
-                if "creation_date" in result.metadata:
-                    print(f"   🕐 Created: {result.metadata['creation_date']}")
-                if "last_modified_date" in result.metadata:
-                    print(f"   🕑 Modified: {result.metadata['last_modified_date']}")
-
             print(f"   {result.text[:200]}...")
-            print(f"   Source: {result.metadata.get('source', '')}")
             print()
 
     async def ask_questions(self, args):
@@ -1588,7 +1542,6 @@ Examples:
             llm_kwargs["thinking_budget"] = args.thinking_budget
 
         def _ask_once(prompt: str) -> None:
-            query_start_time = time.time()
             response = chat.ask(
                 prompt,
                 top_k=args.top_k,
@@ -1599,9 +1552,7 @@ Examples:
                 pruning_strategy=args.pruning_strategy,
                 llm_kwargs=llm_kwargs,
             )
-            query_completion_time = time.time() - query_start_time
             print(f"LEANN: {response}")
-            print(f"The query took {query_completion_time:.3f} seconds to finish")
 
         initial_query = (args.query or "").strip()
 

packages/leann-core/src/leann/embedding_compute.py

@@ -14,88 +14,6 @@ import torch
 
 from .settings import resolve_ollama_host, resolve_openai_api_key, resolve_openai_base_url
 
-
-def truncate_to_token_limit(texts: list[str], max_tokens: int = 512) -> list[str]:
-    """
-    Truncate texts to token limit using tiktoken or conservative character truncation.
-
-    Args:
-        texts: List of texts to truncate
-        max_tokens: Maximum tokens allowed per text
-
-    Returns:
-        List of truncated texts that should fit within token limit
-    """
-    try:
-        import tiktoken
-
-        encoder = tiktoken.get_encoding("cl100k_base")
-        truncated = []
-
-        for text in texts:
-            tokens = encoder.encode(text)
-            if len(tokens) > max_tokens:
-                # Truncate to max_tokens and decode back to text
-                truncated_tokens = tokens[:max_tokens]
-                truncated_text = encoder.decode(truncated_tokens)
-                truncated.append(truncated_text)
-                logger.warning(
-                    f"Truncated text from {len(tokens)} to {max_tokens} tokens "
-                    f"(from {len(text)} to {len(truncated_text)} characters)"
-                )
-            else:
-                truncated.append(text)
-        return truncated
-
-    except ImportError:
-        # Fallback: Conservative character truncation
-        # Assume worst case: 1.5 tokens per character for code content
-        char_limit = int(max_tokens / 1.5)
-        truncated = []
-
-        for text in texts:
-            if len(text) > char_limit:
-                truncated_text = text[:char_limit]
-                truncated.append(truncated_text)
-                logger.warning(
-                    f"Truncated text from {len(text)} to {char_limit} characters "
-                    f"(conservative estimate for {max_tokens} tokens)"
-                )
-            else:
-                truncated.append(text)
-        return truncated
-
-
-def get_model_token_limit(model_name: str) -> int:
-    """
-    Get token limit for a given embedding model.
-
-    Args:
-        model_name: Name of the embedding model
-
-    Returns:
-        Token limit for the model, defaults to 512 if unknown
-    """
-    # Handle versioned model names (e.g., "nomic-embed-text:latest" -> "nomic-embed-text")
-    base_model_name = model_name.split(":")[0]
-
-    # Check exact match first
-    if model_name in EMBEDDING_MODEL_LIMITS:
-        return EMBEDDING_MODEL_LIMITS[model_name]
-
-    # Check base name match
-    if base_model_name in EMBEDDING_MODEL_LIMITS:
-        return EMBEDDING_MODEL_LIMITS[base_model_name]
-
-    # Check partial matches for common patterns
-    for known_model, limit in EMBEDDING_MODEL_LIMITS.items():
-        if known_model in base_model_name or base_model_name in known_model:
-            return limit
-
-    # Default to conservative 512 token limit
-    logger.warning(f"Unknown model '{model_name}', using default 512 token limit")
-    return 512
-
 # Set up logger with proper level
 logger = logging.getLogger(__name__)
 LOG_LEVEL = os.getenv("LEANN_LOG_LEVEL", "WARNING").upper()
@@ -105,17 +23,6 @@ logger.setLevel(log_level)
 # Global model cache to avoid repeated loading
 _model_cache: dict[str, Any] = {}
 
-# Known embedding model token limits
-EMBEDDING_MODEL_LIMITS = {
-    "nomic-embed-text": 512,
-    "nomic-embed-text-v2": 512,
-    "mxbai-embed-large": 512,
-    "all-minilm": 512,
-    "bge-m3": 8192,
-    "snowflake-arctic-embed": 512,
-    # Add more models as needed
-}
-
 
 def compute_embeddings(
     texts: list[str],
@@ -667,10 +574,9 @@ def compute_embeddings_ollama(
     host: Optional[str] = None,
 ) -> np.ndarray:
     """
-    Compute embeddings using Ollama API with true batch processing.
+    Compute embeddings using Ollama API with simplified batch processing.
 
-    Uses the /api/embed endpoint which supports batch inputs.
-    Batch size: 32 for MPS/CPU, 128 for CUDA to optimize performance.
+    Uses batch size of 32 for MPS/CPU and 128 for CUDA to optimize performance.
 
     Args:
         texts: List of texts to compute embeddings for
@@ -775,11 +681,11 @@ def compute_embeddings_ollama(
             logger.info(f"Resolved model name '{model_name}' to '{resolved_model_name}'")
         model_name = resolved_model_name
 
-        # Verify the model supports embeddings by testing it with /api/embed
+        # Verify the model supports embeddings by testing it
         try:
             test_response = requests.post(
-                f"{resolved_host}/api/embed",
-                json={"model": model_name, "input": "test"},
+                f"{resolved_host}/api/embeddings",
+                json={"model": model_name, "prompt": "test"},
                 timeout=10,
             )
             if test_response.status_code != 200:
@@ -811,78 +717,63 @@ def compute_embeddings_ollama(
         # If torch is not available, use conservative batch size
         batch_size = 32
 
-    logger.info(f"Using batch size: {batch_size} for true batch processing")
-
-    # Get model token limit and apply truncation
-    token_limit = get_model_token_limit(model_name)
-    logger.info(f"Model '{model_name}' token limit: {token_limit}")
-
-    # Apply token-aware truncation to all texts
-    truncated_texts = truncate_to_token_limit(texts, token_limit)
-    if len(truncated_texts) != len(texts):
-        logger.error("Truncation failed - text count mismatch")
-        truncated_texts = texts  # Fallback to original texts
+    logger.info(f"Using batch size: {batch_size}")
 
     def get_batch_embeddings(batch_texts):
-        """Get embeddings for a batch of texts using /api/embed endpoint."""
-        max_retries = 3
-        retry_count = 0
+        """Get embeddings for a batch of texts."""
+        all_embeddings = []
+        failed_indices = []
 
-        # Texts are already truncated to token limit by the outer function
-        while retry_count < max_retries:
-            try:
-                # Use /api/embed endpoint with "input" parameter for batch processing
-                response = requests.post(
-                    f"{resolved_host}/api/embed",
-                    json={"model": model_name, "input": batch_texts},
-                    timeout=60,  # Increased timeout for batch processing
-                )
-                response.raise_for_status()
+        for i, text in enumerate(batch_texts):
+            max_retries = 3
+            retry_count = 0
 
-                result = response.json()
-                batch_embeddings = result.get("embeddings")
-
-                if batch_embeddings is None:
-                    raise ValueError("No embeddings returned from API")
-
-                if not isinstance(batch_embeddings, list):
-                    raise ValueError(f"Invalid embeddings format: {type(batch_embeddings)}")
-
-                if len(batch_embeddings) != len(batch_texts):
-                    raise ValueError(
-                        f"Mismatch: requested {len(batch_texts)} embeddings, got {len(batch_embeddings)}"
+            # Truncate very long texts to avoid API issues
+            truncated_text = text[:8000] if len(text) > 8000 else text
+            while retry_count < max_retries:
+                try:
+                    response = requests.post(
+                        f"{resolved_host}/api/embeddings",
+                        json={"model": model_name, "prompt": truncated_text},
+                        timeout=30,
                     )
+                    response.raise_for_status()
 
-                return batch_embeddings, []
+                    result = response.json()
+                    embedding = result.get("embedding")
 
-            except requests.exceptions.Timeout:
-                retry_count += 1
-                if retry_count >= max_retries:
-                    logger.warning(f"Timeout for batch after {max_retries} retries")
-                    return None, list(range(len(batch_texts)))
+                    if embedding is None:
+                        raise ValueError(f"No embedding returned for text {i}")
 
-            except Exception as e:
-                retry_count += 1
-                if retry_count >= max_retries:
-                    # Enhanced error detection for token limit violations
-                    error_msg = str(e).lower()
-                    if "token" in error_msg and ("limit" in error_msg or "exceed" in error_msg or "length" in error_msg):
-                        logger.error(
-                            f"Token limit exceeded for batch. Error: {e}. "
-                            f"Consider reducing chunk sizes or check token truncation."
-                        )
-                    else:
-                        logger.error(f"Failed to get embeddings for batch: {e}")
-                    return None, list(range(len(batch_texts)))
+                    if not isinstance(embedding, list) or len(embedding) == 0:
+                        raise ValueError(f"Invalid embedding format for text {i}")
 
-        return None, list(range(len(batch_texts)))
+                    all_embeddings.append(embedding)
+                    break
 
-    # Process truncated texts in batches
+                except requests.exceptions.Timeout:
+                    retry_count += 1
+                    if retry_count >= max_retries:
+                        logger.warning(f"Timeout for text {i} after {max_retries} retries")
+                        failed_indices.append(i)
+                        all_embeddings.append(None)
+                        break
+
+                except Exception as e:
+                    retry_count += 1
+                    if retry_count >= max_retries:
+                        logger.error(f"Failed to get embedding for text {i}: {e}")
+                        failed_indices.append(i)
+                        all_embeddings.append(None)
+                        break
+        return all_embeddings, failed_indices
+
+    # Process texts in batches
     all_embeddings = []
     all_failed_indices = []
 
     # Setup progress bar if needed
-    show_progress = is_build or len(truncated_texts) > 10
+    show_progress = is_build or len(texts) > 10
     try:
         if show_progress:
             from tqdm import tqdm
@@ -890,36 +781,32 @@ def compute_embeddings_ollama(
         show_progress = False
 
     # Process batches
-    num_batches = (len(truncated_texts) + batch_size - 1) // batch_size
+    num_batches = (len(texts) + batch_size - 1) // batch_size
 
     if show_progress:
-        batch_iterator = tqdm(range(num_batches), desc="Computing Ollama embeddings (batched)")
+        batch_iterator = tqdm(range(num_batches), desc="Computing Ollama embeddings")
     else:
         batch_iterator = range(num_batches)
 
     for batch_idx in batch_iterator:
         start_idx = batch_idx * batch_size
-        end_idx = min(start_idx + batch_size, len(truncated_texts))
-        batch_texts = truncated_texts[start_idx:end_idx]
+        end_idx = min(start_idx + batch_size, len(texts))
+        batch_texts = texts[start_idx:end_idx]
 
         batch_embeddings, batch_failed = get_batch_embeddings(batch_texts)
 
-        if batch_embeddings is not None:
-            all_embeddings.extend(batch_embeddings)
-        else:
-            # Entire batch failed, add None placeholders
-            all_embeddings.extend([None] * len(batch_texts))
-            # Adjust failed indices to global indices
-            global_failed = [start_idx + idx for idx in batch_failed]
-            all_failed_indices.extend(global_failed)
+        # Adjust failed indices to global indices
+        global_failed = [start_idx + idx for idx in batch_failed]
+        all_failed_indices.extend(global_failed)
+        all_embeddings.extend(batch_embeddings)
 
     # Handle failed embeddings
     if all_failed_indices:
-        if len(all_failed_indices) == len(truncated_texts):
+        if len(all_failed_indices) == len(texts):
             raise RuntimeError("Failed to compute any embeddings")
 
         logger.warning(
-            f"Failed to compute embeddings for {len(all_failed_indices)}/{len(truncated_texts)} texts"
+            f"Failed to compute embeddings for {len(all_failed_indices)}/{len(texts)} texts"
         )
 
         # Use zero embeddings as fallback for failed ones

packages/leann-core/src/leann/mcp.py

@@ -60,11 +60,6 @@ def handle_request(request):
                                     "maximum": 128,
                                     "description": "Search complexity level. Use 16-32 for fast searches (recommended), 64+ for higher precision when needed.",
                                 },
-                                "show_metadata": {
-                                    "type": "boolean",
-                                    "default": False,
-                                    "description": "Include file paths and metadata in search results. Useful for understanding which files contain the results.",
-                                },
                             },
                             "required": ["index_name", "query"],
                         },
@@ -109,8 +104,6 @@ def handle_request(request):
                     f"--complexity={args.get('complexity', 32)}",
                     "--non-interactive",
                 ]
-                if args.get("show_metadata", False):
-                    cmd.append("--show-metadata")
                 result = subprocess.run(cmd, capture_output=True, text=True)
 
             elif tool_name == "leann_list":