From c633ded3d8a0c1a1085bbfbbca6536b5005e73d9 Mon Sep 17 00:00:00 2001
From: Anushree Bannadabhavi <anushree.bannadabhavi@gmail.com>
Date: Wed, 10 Apr 2024 05:55:26 -0400
Subject: [PATCH] Add cohere ranker integration information (#217)

---
 integrations/cohere.md | 36 +++++++++++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/integrations/cohere.md b/integrations/cohere.md
index b1659448..cb962dfa 100644
--- a/integrations/cohere.md
+++ b/integrations/cohere.md
@@ -24,12 +24,13 @@ toc: true
   - [Usage](#usage)
     - [Embedding Models](#embedding-models)
     - [Generative Models (LLMs)](#generative-models-llms)
+    - [Ranker Models](#ranker-models)
 - [Haystack 1.x](#haystack-1x)
   - [Installation (1.x)](#installation-1x)
   - [Usage (1.x)](#usage-1x)
     - [Embedding Models](#embedding-models-1)
     - [Generative Models (LLMs)](#generative-models-llms-1)
-    - [Ranker Models](#ranker-models)
+    - [Ranker Models](#ranker-models-1)
 
 ## Haystack 2.0
 
@@ -134,6 +135,39 @@ res = pipe.run(data={"prompt_builder": {"template_variables": {"country": "Germa
 print(res)
 ```
 
+#### Ranker Models
+
+To use `/ranker` models from Cohere, initialize a [CohereRanker](https://docs.haystack.deepset.ai/docs/cohereranker) with the model name. By default, the Cohere API key with be automatically read from either the `COHERE_API_KEY` environment variable or the `CO_API_KEY` environment variable. You can then use this `CohereRanker` to rank documents based on semantic relevance to a specified query.
+
+Below is the example indexing pipeline with `InMemoryDocumentStore`, `InMemoryBM25Retriever` and `CohereRanker`:
+
+```python
+from haystack import Document, Pipeline
+from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
+from haystack.document_stores.in_memory import InMemoryDocumentStore
+from haystack_integrations.components.rankers.cohere import CohereRanker
+
+docs = [
+    Document(content="Paris is in France"),
+    Document(content="Berlin is in Germany"),
+    Document(content="Lyon is in France"),
+]
+document_store = InMemoryDocumentStore()
+document_store.write_documents(docs)
+
+retriever = InMemoryBM25Retriever(document_store=document_store)
+ranker = CohereRanker()
+
+document_ranker_pipeline = Pipeline()
+document_ranker_pipeline.add_component(instance=retriever, name="retriever")
+document_ranker_pipeline.add_component(instance=ranker, name="ranker")
+
+document_ranker_pipeline.connect("retriever.documents", "ranker.documents")
+
+query = "Cities in France"
+res = document_ranker_pipeline.run(data = {"retriever": {"query": query, "top_k": 3}, "ranker": {"query": query, "top_k": 2}})
+```
+
 ## Haystack 1.x
 
 You can use [Cohere Models](https://cohere.com/) in your Haystack pipelines with the [EmbeddingRetriever](https://docs.haystack.deepset.ai/v1.25/docs/retriever#embedding-retrieval-recommended), [PromptNode](https://docs.haystack.deepset.ai/v1.25/docs/prompt_node), and [CohereRanker](https://docs.haystack.deepset.ai/v1.25/docs/ranker#cohereranker).