Vector-store content retrieval

Use vector-store content retrieval when metadata search and content_snippet fields are not enough to answer a file-content question.

This pattern is for government files and user files staged through Add_To_Vector_Store. It is not a GovTribe documentation search or a general GovTribe knowledge base.

When to use vector-store retrieval

Use this pattern when the user needs semantic retrieval from file text, such as:

• requirements, clauses, instructions, or risks buried inside a solicitation attachment
• exact supporting evidence from a user-uploaded file
• concept-level matching across long file text where keyword metadata search is too thin
• a focused answer that depends on retrieved chunks from one or more staged files

Use normal search tools first when file metadata, record fields, or content_snippet values answer the question.

Decide whether to stage files

Prefer the least expensive path that can answer the question.

Before staging files

Resolve the file or file-bearing entity before calling Add_To_Vector_Store.

Supported staged item types currently include file records and selected file-bearing entities such as government_file, user_file, pursuit, federal_contract_opportunity, federal_contract_idv, and federal_grant_opportunity.

Add files to a vector store

Call Add_To_Vector_Store with the resolved items. Omit govtribe_vector_store_id to create a new vector store, or include an existing ID to append files to a reusable store.

Tool: Add_To_Vector_Store

{
  "items": [
    {
      "govtribe_type": "government_file",
      "govtribe_id": "<GOVERNMENT_FILE_ID>"
    }
  ]
}

Capture the returned govtribe_vector_store_id. Later steps use that ID for readiness checks and retrieval.

Poll readiness

Inspect the status returned by Add_To_Vector_Store.

Do not search the vector store until the add response reports that the hosted tool is ready.

Search staged file content

Call Search_Vector_Store after the vector store is ready. Keep max_num_results as small as the question allows.

Focused retrieval:

Tool: Search_Vector_Store

{
  "query": "List mandatory deliverables and submission format instructions.",
  "govtribe_vector_store_id": "<VECTOR_STORE_ID>",
  "max_num_results": 5,
  "rewrite_query": false
}

Conceptual retrieval:

Tool: Search_Vector_Store

{
  "query": "Summarize cybersecurity incident response expectations and reporting deadlines.",
  "govtribe_vector_store_id": "<VECTOR_STORE_ID>",
  "max_num_results": 10,
  "rewrite_query": true
}

Treat returned chunks as semantic evidence. They can support an answer, but they are not a full-document export.

Query construction

Examples

Find candidate government files before staging:

Tool: Search_Government_Files

{
  "query": "\"proposal instructions\"",
  "federal_contract_opportunity_ids": ["<FEDERAL_CONTRACT_OPPORTUNITY_ID>"],
  "fields_to_return": [
    "govtribe_id",
    "name",
    "content_snippet",
    "parent_record"
  ],
  "per_page": 5
}

Stage one file and retrieve compliance instructions:

Step 1 Tool: Add_To_Vector_Store

{
  "items": [
    {
      "govtribe_type": "government_file",
      "govtribe_id": "<GOVERNMENT_FILE_ID>"
    }
  ]
}

Step 2 Tool: Search_Vector_Store

{
  "query": "Extract proposal volume requirements, page limits, due date instructions, and required forms.",
  "govtribe_vector_store_id": "<VECTOR_STORE_ID>",
  "max_num_results": 8,
  "rewrite_query": false
}

Stage all files attached to an opportunity when the user asks about the full package:

Tool: Add_To_Vector_Store

{
  "items": [
    {
      "govtribe_type": "federal_contract_opportunity",
      "govtribe_id": "<FEDERAL_CONTRACT_OPPORTUNITY_ID>"
    }
  ]
}

Retrieve evidence for a source-grounded answer:

Tool: Search_Vector_Store

{
  "query": "What past performance requirements, key personnel requirements, and technical evaluation factors appear in the solicitation package?",
  "govtribe_vector_store_id": "<VECTOR_STORE_ID>",
  "max_num_results": 10,
  "rewrite_query": true
}

When not to use it

Do not stage files just because vector retrieval is available. Prefer the normal MCP search path when:

• the question is about record metadata, not file text
• content_snippet already answers the question
• the user needs a list of files, not semantic chunks from file contents
• the selected govtribe_type is not supported by Add_To_Vector_Store

Related articles

• Add to vector store MCP tool: Review supported item types and staging arguments.
• Search vector store MCP tool: Review semantic retrieval arguments.
• Search vector store MCP response: Interpret returned text reports, snippets, and readiness messages.
• Search government files: Search government-file metadata and snippets before staging full text.
• Search user files: Search team-uploaded file metadata and snippets before staging full text.