Merge branch 'main' of https://github.com/cohere-ai/quick-start-conne…

…ctors into sharepoint-oauth # Conflicts: # README.md # cockroach/dev/load_data.py # confluence/dev/load_data.py # elastic/docker-compose.yml # gdrive/README.md # jira/dev/load_data.py # mongodb/dev/load_data.py # mongodb/docker-compose.yml # opensearch/docker-compose.yml # pinecone/dev/generate_embeddings.py # postgres/docker-compose.yml # redis/dev/load_data.py # redis/docker-compose.yml # sharepoint/.env-template # sharepoint/README.md # sharepoint/provider/client.py # sharepoint/provider/provider.py # sharepoint/provider/unstructured.py # snowflake/README.md # solr/docker-compose.yml # vespa/docker-compose.yml # weaviate/docker-compose.yml # wordpress/dev/load_data.py
cohere-ai · Dec 13, 2023 · 213881a · 213881a
2 parents cff39ac + ee28963
commit 213881a
Show file tree

Hide file tree

Showing 34 changed files with 32,767 additions and 27 deletions.
diff --git a/README.md b/README.md
@@ -15,7 +15,7 @@
 
 # Overview
 
-Cohere's Build-Your-Own-Connector framework allows you to integrate Cohere's Command LLM via the [co.chat api endpoint](https://docs.cohere.com/reference/chat) to any datastore/software that holds text information and has a corresponding search endpoint exposed in its API. This allows the Command model to generated responses to user queries that are grounded in proprietary information.
+Cohere's Build-Your-Own-Connector framework allows you to integrate Cohere's Command LLM via the [Chat api endpoint](https://docs.cohere.com/reference/chat) to any datastore/software that holds text information and has a corresponding search endpoint exposed in its API. This allows the Command model to generated responses to user queries that are grounded in proprietary information.
 
 Some examples of the use-cases you can enable with this framework:
 
@@ -46,7 +46,7 @@ After configuring the `.env`, you will be able to use `poetry`'s CLI to start a
 
 # Integrating With Cohere
 
-All of the connectors in this repository have been tailored to integrate with Cohere's [co.chat](https://docs.cohere.com/reference/chat) API to make creating a grounded chatbot quick and easy.
+All of the connectors in this repository have been tailored to integrate with Cohere's [Chat](https://docs.cohere.com/reference/chat) API to make creating a grounded chatbot quick and easy.
 
 Cohere's API requires that connectors return documents as an array of JSON objects. Each document should be an object with string keys and string values containing all the relevant information about the document (e.g. `title`, `url`, etc.). For best results the largest text content should be stored in the `text` key.
 
@@ -69,7 +69,7 @@ For example, a connector that returns documents about company expensing policy m
 ]
 ```
 
-Cohere's [co.chat](https://docs.cohere.com/reference/chat) API will query the connector and use these documents to generated answers with direct citations.
+Cohere's [Chat](https://docs.cohere.com/reference/chat) API will query the connector and use these documents to generated answers with direct citations.
 
 # Contributing
 

diff --git a/cockroach/dev/bbq.csv b/cockroach/dev/bbq.csv
diff --git a/cockroach/dev/load_data.py b/cockroach/dev/load_data.py
@@ -51,7 +51,7 @@ def load_data():
     conn = psycopg2.connect(COCKROACH_DATABASE_URL)
     cursor = conn.cursor()
 
-    with open("../../testdata/bbq.csv", "r") as csv_file:
+    with open("./dev/bbq.csv", "r") as csv_file:
         reader = csv.DictReader(csv_file)
         for row in reader:
             insert_query = """

diff --git a/confluence/dev/bbq.csv b/confluence/dev/bbq.csv
diff --git a/confluence/dev/load_data.py b/confluence/dev/load_data.py
@@ -14,7 +14,7 @@
 )
 space = os.environ.get("CONFLUENCE_SPACE_NAME")
 
-with open("../testdata/bbq.csv", "r") as csv_file:
+with open("./dev/bbq.csv", "r") as csv_file:
     reader = csv.DictReader(csv_file)
     for row in reader:
         title = row["Name"]

diff --git a/elastic/dev/bbq.csv b/elastic/dev/bbq.csv
diff --git a/elastic/docker-compose.yml b/elastic/docker-compose.yml
@@ -29,7 +29,7 @@ services:
     depends_on:
       - elasticsearch
     volumes:
-      - ../testdata/bbq.csv:/bbq.csv
+      - ./dev/bbq.csv:/bbq.csv
     command:
       - elasticdump
       - --input=csv:///bbq.csv

diff --git a/gdrive/README.md b/gdrive/README.md
@@ -38,7 +38,7 @@ The `GDRIVE_SERVICE_ACCOUNT_INFO` variable should contain the JSON content of th
 }
 ```
 
-4. Convert the JSON credentails to a string through `json.dumps(credentials)` and save the result in the `GDRIVE_SERVICE_ACCOUNT_INFO` environment variable.
+4. Convert the JSON credentials to a string through `json.dumps(credentials)` and save the result in the `GDRIVE_SERVICE_ACCOUNT_INFO` environment variable.
 5. Make sure to [share the folder(s) you want to search with the service account email address](https://support.google.com/a/answer/7337554?hl=en).
 
 #### `GDRIVE_CONNECTOR_API_KEY`
@@ -93,7 +93,7 @@ Create a virtual environment and install dependencies with poetry. We recommend
 Next, start up the search connector server:
 
 ```bash
-  $ poetry flask --app provider --debug run --port 5000
+  $ poetry run flask --app provider --debug run --port 5000
 ```
 
 and check with curl to see that everything works:

diff --git a/jira/dev/bbq.csv b/jira/dev/bbq.csv
diff --git a/jira/dev/load_data.py b/jira/dev/load_data.py
@@ -15,7 +15,7 @@
 )
 project_key = os.environ.get("JIRA_ISSUE_KEY")
 
-with open("../testdata/bbq.csv", "r") as csv_file:
+with open("./dev/bbq.csv", "r") as csv_file:
     reader = csv.DictReader(csv_file)
     for i, row in enumerate(reader, start=1):
         issue_key = f"{project_key}-{i}"

diff --git a/mongodb/dev/bbq.csv b/mongodb/dev/bbq.csv
diff --git a/mongodb/dev/load_data.py b/mongodb/dev/load_data.py
@@ -11,13 +11,12 @@
 
 load_dotenv()
 
-client = pymongo.MongoClient(
-    host=os.environ.get("MONGODB_HOST", "mongo"),
-    port=os.environ.get("MONGODB_PORT", 27017),
-    username=os.environ.get("MONGODB_ROOT_USERNAME", "root"),
-    password=os.environ.get("MONGODB_ROOT_PASSWORD", "example"),
+connection_string = os.environ.get(
+    "MONGODB_CONNECTION_STRING", "mongodb://root:example@mongo:27017"
 )
 
+client = pymongo.MongoClient(connection_string)
+
 fields = []
 
 db = client.bbq

diff --git a/mongodb/docker-compose.yml b/mongodb/docker-compose.yml
@@ -1,9 +1,9 @@
-version: "1"
+version: "3.8"
 services:
   mongo:
     image: mongo:latest
     container_name: mongo
-    restart: unless-stopped
+    restart: always
     ports:
       - 27017:27017
     environment:
@@ -18,8 +18,10 @@ services:
     container_name: data-loader
     depends_on:
       - mongo
+    environment:
+      MONGODB_CONNECTION_STRING: mongodb://root:example@mongo:27017
     volumes:
-      - ../testdata/bbq.csv:/bbq.csv
+      - ./dev/bbq.csv:/bbq.csv
       - ./dev/load_data.py:/load_data.py
     command: sh -c "pip install pymongo python-dotenv && python3 /load_data.py"
     profiles: