Pod

Yes, this is on purpose. Pod is built for agents, so the default page is plain HTML.
Human? View the normal website.
Agent? You probably prefer /mcp/local-faiss-mcp-server/issues.md or /mcp/local-faiss-mcp-server/issues.json, or Pod over MCP.

Reported issues for Local FAISS MCP Server

Pod holds 11 of 11 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to Local FAISS MCP Server.

Most discussed

Extract and store document metadata (author, date, tags)

Extract rich metadata from documents for better search and organization.

Why: Metadata enables filtering by date, author, document type, etc.

Expected behavior:

$ local-faiss list --metadata

Documents:
1. research_paper.pdf
   Author: John Doe
   Created: 2024-01-15
   Pages: 42
   Tags: machine-learning, RAG
   Chunks: 15

$ local-faiss search "neural networks" --filter "created:2024"

Implementation approach:

  1. Extract PDF metadata using pypdf (author, title, creati

Read the thread · 2025-12-09 · closed · 4 comments

What’s the right memory abstraction for MCP-based agents?

I built this MCP server to explore local-first memory using FAISS.

What I’m running into is that the interaction model feels fundamentally wrong.

Having to tell an agent “use the vector DB” or “store this in FAISS” is not how memory should work. Memory should be implicit, contextual, and constrained — not a tool the user has to invoke.

This makes me question:

when an agent should decide to persist something at all? whether memory should be event-driven vs query-driven? how to avoid polluting

Read the thread · 2025-12-20 · closed · 2 comments

[Feature] Bring your own embedding model

User wants to specify any local embedding model. This feature can be triggered ad deployment time:


local-faiss-mcp --embed [model]

The --embed flag will take in Huggingface model names and defaults to the current embedding model: 'all-MiniLM-L6-v2'

Read the thread · 2025-12-02 · closed · 2 comments

[Feature] Query highlight

User wants to retrieve the most relevant section within the document to answer the query. This can be done through a pipeline or providing a MCP prompt to the model. See https://modelcontextprotocol.io/specification/2025-06-18/server/prompts for more information about MCP prompts.

An MCP prompt for answer extraction and quotation can have as inputs the original query and each of the retrieved / top k documents.

Read the thread · 2025-12-02 · closed · 2 comments

[Feature] Support re-ranking models

User can trigger re-ranking models in the search pipeline with flag at deployment time:

local-faiss-mcp -rerank [model]

The rerank flag takes in a Huggingface model name or defaults to a known reranking model, such as Qwen/Qwen3-Reranker-0.6B.

Read the thread · 2025-12-02 · closed · 2 comments

[Feature] CLI to index documents outside model context

The user will be able to index a file, usually of document type (pdf, docx, txt, md), by issuing a bash command of the form:

local-faiss index [-i index_path] [-f/--folder folder_path] document1 document2 document3

The user can also search using local-faiss:

local-faiss search [-i index_path] "natural language text query from user"

Read the thread · 2025-12-02 · closed · 1 comment

Add delete and update commands for index management

Users need to remove or update documents in the index without rebuilding everything.

Why: Currently, there's no way to remove indexed documents except deleting the entire index.

Expected behavior:

# Delete a document
$ local-faiss delete document.pdf
Removed 15 chunks from index

# Update a document (delete + re-index)
$ local-faiss update document.pdf
Updated 12 chunks (was 15)

# List what would be deleted
$ local-faiss delete --dry-run "docs/*.pdf"
Would delete:
- docs/file1

[Read the thread](https://github.com/nonatofabio/local_faiss_mcp/issues/10) · 2025-12-09 · open · 0 comments

### Add hybrid search combining BM25 and vector similarity

Implement hybrid search that combines lexical (BM25) and semantic (vector) search for better results.

**Why**: Hybrid search outperforms pure vector search by combining keyword matching with semantic similarity.

**Expected behavior**:
```bash
$ local-faiss search --hybrid "FAISS algorithm"

Or via MCP config:

{
  "args": ["--index-dir", "./.vector_store", "--search-mode", "hybrid"]
}

Implementation approach:

  1. Add BM25 indexing during document ingestion (using rank-bm25

Read the thread · 2025-12-09 · open · 0 comments

Most recent

Show progress bar when indexing multiple files

Add a progress bar using tqdm when indexing multiple documents.

Why: Users need feedback during long batch operations.

Expected behavior:

$ local-faiss index documents/*.pdf

Indexing 50 files...
██████████████░░░░░░ 15/50 (30%) - document_15.pdf

Implementation hints:

Acceptance criteria

Read the thread · 2025-12-09 · closed · 0 comments

Add colored output to CLI for better readability

Enhance CLI with colors using colorama or rich for better user experience.

Why: Colored output makes success/error states instantly recognizable.

Expected behavior:

Implementation hints:

Read the thread · 2025-12-09 · closed · 0 comments

Add local-faiss list command to show indexed documents

Add a new CLI command to list all documents in the index with their metadata.

Why: Users need visibility into what's indexed without querying.

Expected behavior:

$ local-faiss list

Indexed Documents (3 total):
1. research_paper.pdf
   - Chunks: 15
   - Indexed: 2024-12-08 14:23

2. readme.md
   - Chunks: 3
   - Indexed: 2024-12-08 14:25

3. notes.txt
   - Chunks: 8
   - Indexed: 2024-12-08 15:10

Implementation hints:

Read the thread · 2025-12-09 · closed · 0 comments

The remaining reports are on the project's issue tracker.