From 4b505060bd29e532641dbdc17691e83ea717fafc Mon Sep 17 00:00:00 2001
From: Hech <53417823+HeChangHaoGary@users.noreply.github.com>
Date: Tue, 15 Aug 2023 16:06:06 +0800
Subject: [PATCH] fix: max_marginal_relevance_search and docs in Dingo (#9244)

---
 .../integrations/vectorstores/dingo.ipynb     | 12 +++++----
 .../langchain/langchain/vectorstores/dingo.py | 26 +++++++++++++------
 2 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/docs/extras/integrations/vectorstores/dingo.ipynb b/docs/extras/integrations/vectorstores/dingo.ipynb
index fab91b3273..0369f1ecb0 100644
--- a/docs/extras/integrations/vectorstores/dingo.ipynb
+++ b/docs/extras/integrations/vectorstores/dingo.ipynb
@@ -23,7 +23,9 @@
    },
    "outputs": [],
    "source": [
-    "!pip install dingodb"
+    "!pip install dingodb\n",
+    "or install latest:\n",
+    "!pip install git+https://git@github.com/dingodb/pydingo.git"
    ]
   },
   {
@@ -107,7 +109,7 @@
     "dingo_client = DingoDB(user=\"\", password=\"\", host=[\"127.0.0.1:13000\"])\n",
     "# First, check if our index already exists. If it doesn't, we create it\n",
     "if index_name not in dingo_client.get_index():\n",
-    "    # we create a new index\n",
+    "    # we create a new index, modify to your own\n",
     "    dingo_client.create_index(\n",
     "      index_name=index_name,\n",
     "      dimension=1536,\n",
@@ -150,7 +152,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(docs[0][1])"
+    "print(docs[0].page_content)"
    ]
   },
   {
@@ -170,9 +172,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vectorstore = Dingo(client, embeddings.embed_query, \"text\")\n",
+    "vectorstore = Dingo(embeddings, \"text\", client=dingo_client, index_name=index_name)\n",
     "\n",
-    "vectorstore.add_texts(\"More text!\")"
+    "vectorstore.add_texts([\"More text!\"])"
    ]
   },
   {
diff --git a/libs/langchain/langchain/vectorstores/dingo.py b/libs/langchain/langchain/vectorstores/dingo.py
index a1f31eeb40..44765cdd31 100644
--- a/libs/langchain/langchain/vectorstores/dingo.py
+++ b/libs/langchain/langchain/vectorstores/dingo.py
@@ -112,9 +112,11 @@ class Dingo(VectorStore):
         # upsert to Dingo
         for i in range(0, len(list(texts)), batch_size):
             j = i + batch_size
-            self._client.vector_add(
+            add_res = self._client.vector_add(
                 self._index_name, metadatas_list[i:j], embeds[i:j], ids[i:j]
             )
+            if not add_res:
+                raise Exception("vector add fail")
 
         return ids
 
@@ -205,20 +207,26 @@ class Dingo(VectorStore):
             List of Documents selected by maximal marginal relevance.
         """
         results = self._client.vector_search(
-            self._index_name, [embedding], search_params, k
+            self._index_name, [embedding], search_params=search_params, top_k=k
         )
 
         mmr_selected = maximal_marginal_relevance(
             np.array([embedding], dtype=np.float32),
-            [item["floatValues"] for item in results[0]["vectorWithDistances"]],
+            [
+                item["vector"]["floatValues"]
+                for item in results[0]["vectorWithDistances"]
+            ],
             k=k,
             lambda_mult=lambda_mult,
         )
-        selected = [
-            results[0]["vectorWithDistances"][i]["metaData"] for i in mmr_selected
-        ]
+        selected = []
+        for i in mmr_selected:
+            meta_data = {}
+            for k, v in results[0]["vectorWithDistances"][i]["scalarData"].items():
+                meta_data.update({str(k): v["fields"][0]["data"]})
+            selected.append(meta_data)
         return [
-            Document(page_content=metadata.pop((self._text_key)), metadata=metadata)
+            Document(page_content=metadata.pop(self._text_key), metadata=metadata)
             for metadata in selected
         ]
 
@@ -328,9 +336,11 @@ class Dingo(VectorStore):
         # upsert to Dingo
         for i in range(0, len(list(texts)), batch_size):
             j = i + batch_size
-            dingo_client.vector_add(
+            add_res = dingo_client.vector_add(
                 index_name, metadatas_list[i:j], embeds[i:j], ids[i:j]
             )
+            if not add_res:
+                raise Exception("vector add fail")
         return cls(embedding, text_key, client=dingo_client, index_name=index_name)
 
     def delete(