Merge branch 'main' into dglog/docs-updates-2

libs/ai-endpoints/docs/chat/nvidia_ai_endpoints.ipynb

@@ -533,43 +533,6 @@
     "For more advanced or custom use-cases (i.e. supporting the diffusion models), you may be interested in leveraging the `NVEModel` client as a requests backbone. The `NVIDIAEmbeddings` class is a good source of inspiration for this. "
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "1cd6249a-7ffa-4886-b7e8-5778dc93499e",
-   "metadata": {},
-   "source": [
-    "## RAG: Context models\n",
-    "\n",
-    "NVIDIA also has Q&A models that support a special \"context\" chat message containing retrieved context (such as documents within a RAG chain). This is useful to avoid prompt-injecting the model. The `_qa_` models like `nemotron_qa_8b` support this.\n",
-    "\n",
-    "**Note:** Only \"user\" (human) and \"context\" chat messages are supported for these models; System or AI messages that would useful in conversational flows are not supported."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f994b4d3-c1b0-4e87-aad0-a7b487e2aa43",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#from langchain_core.messages import ChatMessage\n",
-    "#rom langchain_core.output_parsers import StrOutputParser\n",
-    "#from langchain_core.prompts import ChatPromptTemplate\n",
-    "#from langchain_nvidia_ai_endpoints import ChatNVIDIA\n",
-    "\n",
-    "#prompt = ChatPromptTemplate.from_messages(\n",
-    "#    [\n",
-    "#        ChatMessage(\n",
-    "#            role=\"context\", content=\"Parrots and Cats have signed the peace accord.\"\n",
-    "#        ),\n",
-    "#        (\"user\", \"{input}\"),\n",
-    "#    ]\n",
-    "#)\n",
-    "#llm = ChatNVIDIA(model=\"meta/llama3-8b-instruct\")\n",
-    "#chain = prompt | llm | StrOutputParser()\n",
-    "#chain.invoke({\"input\": \"What was signed?\"})"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "137662a6",

libs/ai-endpoints/langchain_nvidia_ai_endpoints/_statics.py

@@ -189,6 +189,14 @@ class Model(BaseModel):
             "model_type": "image_in",
             "model_name": "microsoft/phi-3-vision-128k-instruct",
         },
+        "ai-granite-8b-code-instruct": {
+            "model_type": "chat",
+            "model_name": "ibm/granite-8b-code-instruct",
+        },
+        "ai-granite-34b-code-instruct": {
+            "model_type": "chat",
+            "model_name": "ibm/granite-34b-code-instruct",
+        },
     }
 )
 

libs/ai-endpoints/pyproject.toml

@@ -1,14 +1,14 @@
 [tool.poetry]
 name = "langchain-nvidia-ai-endpoints"
-version = "0.0.18"
+version = "0.0.19"
 description = "An integration package connecting NVIDIA AI Endpoints and LangChain"
 authors = []
 readme = "README.md"
-repository = "https://github.com/langchain-ai/langchain"
+repository = "https://github.com/langchain-ai/langchain-nvidia"
 license = "MIT"
 
 [tool.poetry.urls]
-"Source Code" = "https://github.com/langchain-ai/langchain/tree/master/libs/partners/nvidia-ai-endpoints"
+"Source Code" = "https://github.com/langchain-ai/langchain-nvidia/tree/main/libs/ai-endpoints"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
@@ -26,7 +26,7 @@ pytest-mock = "^3.10.0"
 syrupy = "^4.0.2"
 pytest-watcher = "^0.3.4"
 pytest-asyncio = "^0.21.1"
-langchain-core = {git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core"}
+langchain-core = { git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core" }
 requests-mock = "^1.11.0"
 faker = "^24.4.0"
 
@@ -52,13 +52,13 @@ ruff = "^0.1.5"
 mypy = "^0.991"
 types-requests = "^2.31.0.10"
 types-pillow = "^10.2.0.20240125"
-langchain-core = {git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core"}
+langchain-core = { git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core" }
 
 [tool.poetry.group.dev]
 optional = true
 
 [tool.poetry.group.dev.dependencies]
-langchain-core = {git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core"}
+langchain-core = { git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core" }
 
 [tool.ruff.lint]
 select = [

libs/trt/pyproject.toml

@@ -4,11 +4,11 @@ version = "0.0.1"
 description = "An integration package connecting TritonTensorRT and LangChain"
 authors = []
 readme = "README.md"
-repository = "https://github.com/langchain-ai/langchain"
+repository = "https://github.com/langchain-ai/langchain-nvidia"
 license = "MIT"
 
 [tool.poetry.urls]
-"Source Code" = "https://github.com/langchain-ai/langchain/tree/master/libs/partners/nvidia-trt"
+"Source Code" = "https://github.com/langchain-ai/langchain-nvidia/tree/main/libs/trt"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
@@ -28,7 +28,7 @@ pytest-mock = "^3.10.0"
 syrupy = "^4.0.2"
 pytest-watcher = "^0.3.4"
 pytest-asyncio = "^0.21.1"
-langchain-core = {git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core"}
+langchain-core = { git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core" }
 
 [tool.poetry.group.codespell]
 optional = true
@@ -49,13 +49,13 @@ ruff = "^0.1.5"
 
 [tool.poetry.group.typing.dependencies]
 mypy = "^0.991"
-langchain-core = {git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core"}
+langchain-core = { git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core" }
 
 [tool.poetry.group.dev]
 optional = true
 
 [tool.poetry.group.dev.dependencies]
-langchain-core = {git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core"}
+langchain-core = { git = "https://github.com/langchain-ai/langchain.git", subdirectory = "libs/core" }
 
 [tool.ruff.lint]
 select = [