Merge branch 'master' into issue_27485_fix

.github/CODEOWNERS

@@ -0,0 +1,2 @@
+/.github/   @efriis @baskaryan @ccurme
+/libs/packages.yml   @efriis

.github/workflows/_integration_test.yml

@@ -41,12 +41,6 @@ jobs:
         shell: bash
         run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Run integration tests
         shell: bash
         env:

.github/workflows/_release.yml

@@ -103,14 +103,19 @@ jobs:
           if [ -z "$PREV_TAG" ]; then
             REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
             echo $REGEX
-            PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
+            PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
           fi
 
-          # confirm prev-tag actually exists in git repo with git tag
-          GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
-          if [ -z "$GIT_TAG_RESULT" ]; then
-            echo "Previous tag $PREV_TAG not found in git repo"
-            exit 1
+          # if PREV_TAG is empty, let it be empty
+          if [ -z "$PREV_TAG" ]; then
+            echo "No previous tag found - first release"
+          else
+            # confirm prev-tag actually exists in git repo with git tag
+            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
+            if [ -z "$GIT_TAG_RESULT" ]; then
+              echo "Previous tag $PREV_TAG not found in git repo"
+              exit 1
+            fi
           fi
 
 
@@ -262,12 +267,6 @@ jobs:
           make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Import integration test dependencies
         run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}

docs/docs/how_to/graph_constructing.ipynb

@@ -44,6 +44,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.3.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
       "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
@@ -105,7 +108,7 @@
     "os.environ[\"NEO4J_USERNAME\"] = \"neo4j\"\n",
     "os.environ[\"NEO4J_PASSWORD\"] = \"password\"\n",
     "\n",
-    "graph = Neo4jGraph()"
+    "graph = Neo4jGraph(refresh_schema=False)"
    ]
   },
   {
@@ -149,8 +152,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Nodes:[Node(id='Marie Curie', type='Person'), Node(id='Pierre Curie', type='Person'), Node(id='University Of Paris', type='Organization')]\n",
-      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='Pierre Curie', type='Person'), type='MARRIED'), Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='University Of Paris', type='Organization'), type='PROFESSOR')]\n"
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='MARRIED', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='PROFESSOR', properties={})]\n"
      ]
     }
    ],
@@ -191,8 +194,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Nodes:[Node(id='Marie Curie', type='Person'), Node(id='Pierre Curie', type='Person'), Node(id='University Of Paris', type='Organization')]\n",
-      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='Pierre Curie', type='Person'), type='SPOUSE'), Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='University Of Paris', type='Organization'), type='WORKED_AT')]\n"
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]\n"
      ]
     }
    ],
@@ -209,6 +212,44 @@
     "print(f\"Relationships:{graph_documents_filtered[0].relationships}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To define the graph schema more precisely, consider using a three-tuple approach for relationships. In this approach, each tuple consists of three elements: the source node, the relationship type, and the target node."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]\n"
+     ]
+    }
+   ],
+   "source": [
+    "allowed_relationships = [\n",
+    "    (\"Person\", \"SPOUSE\", \"Person\"),\n",
+    "    (\"Person\", \"NATIONALITY\", \"Country\"),\n",
+    "    (\"Person\", \"WORKED_AT\", \"Organization\"),\n",
+    "]\n",
+    "\n",
+    "llm_transformer_tuple = LLMGraphTransformer(\n",
+    "    llm=llm,\n",
+    "    allowed_nodes=[\"Person\", \"Country\", \"Organization\"],\n",
+    "    allowed_relationships=allowed_relationships,\n",
+    ")\n",
+    "llm_transformer_tuple = llm_transformer_filtered.convert_to_graph_documents(documents)\n",
+    "print(f\"Nodes:{graph_documents_filtered[0].nodes}\")\n",
+    "print(f\"Relationships:{graph_documents_filtered[0].relationships}\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -229,15 +270,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Nodes:[Node(id='Marie Curie', type='Person', properties={'born_year': '1867'}), Node(id='Pierre Curie', type='Person'), Node(id='University Of Paris', type='Organization')]\n",
-      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='Pierre Curie', type='Person'), type='SPOUSE'), Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='University Of Paris', type='Organization'), type='WORKED_AT')]\n"
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={'born_year': '1867'}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={}), Node(id='Poland', type='Country', properties={}), Node(id='France', type='Country', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Poland', type='Country', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='France', type='Country', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]\n"
      ]
     }
    ],
@@ -264,12 +305,71 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
     "graph.add_graph_documents(graph_documents_props)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Most graph databases support indexes to optimize data import and retrieval. Since we might not know all the node labels in advance, we can handle this by adding a secondary base label to each node using the `baseEntityLabel` parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.add_graph_documents(graph_documents, baseEntityLabel=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Results will look like:\n",
+    "\n",
+    "![graph_construction3.png](../../static/img/graph_construction3.png)\n",
+    "\n",
+    "The final option is to also import the source documents for the extracted nodes and relationships. This approach lets us track which documents each entity appeared in."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.add_graph_documents(graph_documents, include_source=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Graph will have the following structure:\n",
+    "\n",
+    "![graph_construction4.png](../../static/img/graph_construction4.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this visualization, the source document is highlighted in blue, with all entities extracted from it connected by `MENTIONS` relationships."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -288,7 +388,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/openai.ipynb

@@ -509,6 +509,101 @@
     "output_message.content"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5c35d0a4-a6b8-4d35-a02b-a37a8bda5692",
+   "metadata": {},
+   "source": [
+    "## Predicted output\n",
+    "\n",
+    ":::info\n",
+    "Requires `langchain-openai>=0.2.6`\n",
+    ":::\n",
+    "\n",
+    "Some OpenAI models (such as their `gpt-4o` and `gpt-4o-mini` series) support [Predicted Outputs](https://platform.openai.com/docs/guides/latency-optimization#use-predicted-outputs), which allow you to pass in a known portion of the LLM's expected output ahead of time to reduce latency. This is useful for cases such as editing text or code, where only a small part of the model's output will change.\n",
+    "\n",
+    "Here's an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "88fee1e9-58c1-42ad-ae23-24b882e175e7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/// <summary>\n",
+      "/// Represents a user with a first name, last name, and email.\n",
+      "/// </summary>\n",
+      "public class User\n",
+      "{\n",
+      "    /// <summary>\n",
+      "    /// Gets or sets the user's first name.\n",
+      "    /// </summary>\n",
+      "    public string FirstName { get; set; }\n",
+      "\n",
+      "    /// <summary>\n",
+      "    /// Gets or sets the user's last name.\n",
+      "    /// </summary>\n",
+      "    public string LastName { get; set; }\n",
+      "\n",
+      "    /// <summary>\n",
+      "    /// Gets or sets the user's email.\n",
+      "    /// </summary>\n",
+      "    public string Email { get; set; }\n",
+      "}\n",
+      "{'token_usage': {'completion_tokens': 226, 'prompt_tokens': 166, 'total_tokens': 392, 'completion_tokens_details': {'accepted_prediction_tokens': 49, 'audio_tokens': None, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 107}, 'prompt_tokens_details': {'audio_tokens': None, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_45cf54deae', 'finish_reason': 'stop', 'logprobs': None}\n"
+     ]
+    }
+   ],
+   "source": [
+    "code = \"\"\"\n",
+    "/// <summary>\n",
+    "/// Represents a user with a first name, last name, and username.\n",
+    "/// </summary>\n",
+    "public class User\n",
+    "{\n",
+    "    /// <summary>\n",
+    "    /// Gets or sets the user's first name.\n",
+    "    /// </summary>\n",
+    "    public string FirstName { get; set; }\n",
+    "\n",
+    "    /// <summary>\n",
+    "    /// Gets or sets the user's last name.\n",
+    "    /// </summary>\n",
+    "    public string LastName { get; set; }\n",
+    "\n",
+    "    /// <summary>\n",
+    "    /// Gets or sets the user's username.\n",
+    "    /// </summary>\n",
+    "    public string Username { get; set; }\n",
+    "}\n",
+    "\"\"\"\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
+    "query = (\n",
+    "    \"Replace the Username property with an Email property. \"\n",
+    "    \"Respond only with code, and with no markdown formatting.\"\n",
+    ")\n",
+    "response = llm.invoke(\n",
+    "    [{\"role\": \"user\", \"content\": query}, {\"role\": \"user\", \"content\": code}],\n",
+    "    prediction={\"type\": \"content\", \"content\": code},\n",
+    ")\n",
+    "print(response.content)\n",
+    "print(response.response_metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2ee1b26d-a388-4e7c-9f40-bfd1388ecc03",
+   "metadata": {},
+   "source": [
+    "Note that currently predictions are billed as additional tokens and may increase your usage and costs in exchange for this reduced latency."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "feb4a499",
@@ -601,7 +696,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -615,7 +710,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,