Harrison/llama (#2314)

Co-authored-by: RJ Adriaansen <adriaansen@eshcc.eur.nl>

docs/ecosystem/llamacpp.md

@@ -0,0 +1,26 @@
+# Llama.cpp
+
+This page covers how to use [llama.cpp](https://github.com/ggerganov/llama.cpp) within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Jina wrappers.
+
+## Installation and Setup
+- Install the Python package with `pip install llama-cpp-python`
+- Download one of the [supported models](https://github.com/ggerganov/llama.cpp#description) and convert them to the llama.cpp format per the [instructions](https://github.com/ggerganov/llama.cpp)
+
+## Wrappers
+
+### LLM
+
+There exists a LlamaCpp LLM wrapper, which you can access with 
+```python
+from langchain.llms import LlamaCpp
+```
+For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/llamacpp.ipynb)
+
+### Embeddings
+
+There exists a LlamaCpp Embeddings wrapper, which you can access with 
+```python
+from langchain.embeddings import LlamaCppEmbeddings
+```
+For a more detailed walkthrough of this, see [this notebook](../modules/models/llms/integrations/examples/llamacpp.ipynb)

docs/modules/models/llms/integrations/llamacpp.ipynb

@@ -0,0 +1,98 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-cpp-python"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import LlamaCpp\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = LlamaCpp(model_path=\"./ggml-model-q4_0.bin\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWe know that Justin Bieber is currently 25 years old and that he was born on March 1st, 1994 and that he is a singer and he has an album called Purpose, so we know that he was born when Super Bowl XXXVIII was played between Dallas and Seattle and that it took place February 1st, 2004 and that the Seattle Seahawks won 24-21, so Seattle is our answer!'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "workspace",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/models/text_embedding/examples/llamacpp.ipynb

@@ -0,0 +1,66 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-cpp-python"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import LlamaCppEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llama = LlamaCppEmbeddings(model_path=\"/path/to/model/ggml-model-q4_0.bin\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_result = embeddings.embed_documents([text])"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/reference/integrations.md

@@ -52,6 +52,9 @@ The following use cases require specific installs and api keys:
   - If you want to set up OpenSearch on your local, [here](https://opensearch.org/docs/latest/)
 - _DeepLake_:
   - Install requirements with `pip install deeplake`
+- _LlamaCpp_:
+  - Install requirements with `pip install llama-cpp-python`
+  - Download model and convert following [llama.cpp instructions](https://github.com/ggerganov/llama.cpp)
 
 
 If you are using the `NLTKTextSplitter` or the `SpacyTextSplitter`, you will also need to install the appropriate models. For example, if you want to use the `SpacyTextSplitter`, you will need to install the `en_core_web_sm` model with `python -m spacy download en_core_web_sm`. Similarly, if you want to use the `NLTKTextSplitter`, you will need to install the `punkt` model with `python -m nltk.downloader punkt`.