From 603a0bea29f53d51870873b4714aa79067285744 Mon Sep 17 00:00:00 2001
From: Rohit Kumar Singh <9626333+SKRohit@users.noreply.github.com>
Date: Wed, 12 Jul 2023 13:05:49 +0530
Subject: [PATCH] Fixes incorrect docstore creation in faiss.py (#7026)

- **Description**: Current implementation assumes that the length of
`texts` and `ids` should be same but if the passed `ids` length is not
equal to the passed length of `texts`, current code
`dict(zip(index_to_id.values(), documents))` is not failing or giving
any warning and silently creating docstores only for the passed `ids`
i.e. if `ids = ['A']` and `texts=["I love Open Source","I love
langchain"]` then only one `docstore` will be created. But either two
docstores should be created assuming same id value for all the elements
of `texts` or an error should be raised.

- **Issue**: My change fixes this by using dictionary comprehension
instead of `zip`. This was if lengths of `ids` and `texts` mismatches an
explicit `IndexError` will be raised.

@rlancemartin, @eyurtsev
---
 langchain/vectorstores/faiss.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/langchain/vectorstores/faiss.py b/langchain/vectorstores/faiss.py
index 74b5d747414..eb3df5685c7 100644
--- a/langchain/vectorstores/faiss.py
+++ b/langchain/vectorstores/faiss.py
@@ -521,6 +521,13 @@ class FAISS(VectorStore):
             metadata = metadatas[i] if metadatas else {}
             documents.append(Document(page_content=text, metadata=metadata))
         index_to_id = dict(enumerate(ids))
+
+        if len(index_to_id) != len(documents):
+            raise Exception(
+                f"{len(index_to_id)} ids provided for {len(documents)} documents."
+                " Each document should have an id."
+            )
+
         docstore = InMemoryDocstore(dict(zip(index_to_id.values(), documents)))
         return cls(
             embedding.embed_query,