From 973866c89405dc19c520b7608408c1bdfaa76b16 Mon Sep 17 00:00:00 2001
From: Raynor Chavez <raynorkirksonchavez@gmail.com>
Date: Tue, 22 Aug 2023 01:43:15 +0800
Subject: [PATCH] fix: Updated marqo integration for marqo version 1.0.0+
 (#9521)

- Description: Updated marqo integration to use tensor_fields instead of
non_tensor_fields. Upgraded marqo version to 1.2.4
  - Dependencies: marqo 1.2.4

---------

Co-authored-by: Raynor Kirkson E. Chavez <raynor.chavez@192.168.254.171>
Co-authored-by: Bagatur <baskaryan@gmail.com>
---
 .../langchain/langchain/vectorstores/marqo.py | 20 +++++++++----------
 libs/langchain/poetry.lock                    | 12 ++++++-----
 libs/langchain/pyproject.toml                 |  2 +-
 .../vectorstores/test_marqo.py                |  1 +
 4 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/libs/langchain/langchain/vectorstores/marqo.py b/libs/langchain/langchain/vectorstores/marqo.py
index e3873e4e15b..0d1dfe0489e 100644
--- a/libs/langchain/langchain/vectorstores/marqo.py
+++ b/libs/langchain/langchain/vectorstores/marqo.py
@@ -78,7 +78,7 @@ class Marqo(VectorStore):
         self._searchable_attributes = searchable_attributes
         self.page_content_builder = page_content_builder
 
-        self._non_tensor_fields = ["metadata"]
+        self.tensor_fields = ["text"]
 
         self._document_batch_size = 1024
 
@@ -132,7 +132,7 @@ class Marqo(VectorStore):
         for i in range(0, num_docs, self._document_batch_size):
             response = self._client.index(self._index_name).add_documents(
                 documents[i : i + self._document_batch_size],
-                non_tensor_fields=self._non_tensor_fields,
+                tensor_fields=self.tensor_fields,
                 **self._add_documents_settings,
             )
             if response["errors"]:
@@ -330,17 +330,15 @@ class Marqo(VectorStore):
             Dict[str, Dict[List[Dict[str, Dict[str, Any]]]]]: A bulk search results
             object
         """
-        bulk_results = self._client.bulk_search(
-            [
-                {
-                    "index": self._index_name,
-                    "q": query,
-                    "searchableAttributes": self._searchable_attributes,
-                    "limit": k,
-                }
+        bulk_results = {
+            "result": [
+                self._client.index(self._index_name).search(
+                    q=query, searchable_attributes=self._searchable_attributes, limit=k
+                )
                 for query in queries
             ]
-        )
+        }
+
         return bulk_results
 
     @classmethod
diff --git a/libs/langchain/poetry.lock b/libs/langchain/poetry.lock
index 9305a0838f8..a0a76d09799 100644
--- a/libs/langchain/poetry.lock
+++ b/libs/langchain/poetry.lock
@@ -4407,19 +4407,21 @@ files = [
 
 [[package]]
 name = "marqo"
-version = "0.11.0"
+version = "1.2.4"
 description = "Tensor search for humans"
 category = "main"
 optional = true
 python-versions = ">=3"
 files = [
-    {file = "marqo-0.11.0-py3-none-any.whl", hash = "sha256:e1a5409beeb02dcec725566cfbc5fd88a84ce65ca7bce08a1120f8082badeab4"},
-    {file = "marqo-0.11.0.tar.gz", hash = "sha256:808e691cf06f5f7d67d422dc7f5f6fcc53b9acc6a4bc000abbcae8a817fd765d"},
+    {file = "marqo-1.2.4-py3-none-any.whl", hash = "sha256:aaf59ca35214febaa893e102828a50ab9e53fe57201cd43714ab7c0515166068"},
+    {file = "marqo-1.2.4.tar.gz", hash = "sha256:3fe0eb8e1ed73883fd8e6001582d18dab6e149d79e41b92a1403b2ff52d18c43"},
 ]
 
 [package.dependencies]
-pydantic = "*"
+packaging = "*"
+pydantic = "<2.0.0"
 requests = "*"
+typing-extensions = ">=4.5.0"
 urllib3 = "*"
 
 [[package]]
@@ -10487,4 +10489,4 @@ text-helpers = ["chardet"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "a5e3458dd0cabcefd83caec6eb33b6fb593c2c347ca1d33c1f182341e852a9c8"
+content-hash = "0247674f3f274fd2249ceb02c23a468f911a7c482796ea67252b203d1ab938ae"
diff --git a/libs/langchain/pyproject.toml b/libs/langchain/pyproject.toml
index d74fda8f2f0..8c3c8c18df2 100644
--- a/libs/langchain/pyproject.toml
+++ b/libs/langchain/pyproject.toml
@@ -37,7 +37,7 @@ pinecone-text = {version = "^0.4.2", optional = true}
 pymongo = {version = "^4.3.3", optional = true}
 clickhouse-connect = {version="^0.5.14", optional=true}
 weaviate-client = {version = "^3", optional = true}
-marqo = {version = "^0.11.0", optional=true}
+marqo = {version = "^1.2.4", optional=true}
 google-api-python-client = {version = "2.70.0", optional = true}
 google-auth = {version = "^2.18.1", optional = true}
 wolframalpha = {version = "5.0.0", optional = true}
diff --git a/libs/langchain/tests/integration_tests/vectorstores/test_marqo.py b/libs/langchain/tests/integration_tests/vectorstores/test_marqo.py
index 4821ee2dc2a..94549735a67 100644
--- a/libs/langchain/tests/integration_tests/vectorstores/test_marqo.py
+++ b/libs/langchain/tests/integration_tests/vectorstores/test_marqo.py
@@ -158,6 +158,7 @@ def test_marqo_multimodal() -> None:
                 "mainline/examples/ImageSearchGuide/data/image2.jpg",
             },
         ],
+        tensor_fields=["caption", "image"],
     )
 
     def get_content(res: Dict[str, str]) -> str: