Some cells are failing in `L6_Multilingual_RAG_Search`

Short Course Q&A Vector Databases: from Embeddings to Applications
1

Hi Team,
I am facing issues in Lesson 6 of this course, where almost half of the cells are failing inside the notebook. I have quoted some instances as follows:

print(json.dumps(client.query.aggregate("Wikipedia").with_meta_count().do(), indent=2))

UnexpectedStatusCodeException: Query was not successful! Unexpected status code: 500, with response body: None.

response = (client.query
            .get("Wikipedia",['text','title','url','views','lang'])
            .with_near_text({"concepts": "Miejsca na wakacje w Kalifornii"})
            .with_where({
                "path" : ['lang'],
                "operator" : "Equal",
                "valueString":'en'
            })
            .with_limit(3)
            .do()
           )

json_print(response)

UnexpectedStatusCodeException: Query was not successful! Unexpected status code: 500, with response body: None.

prompt = "Write me a facebook ad about {title} using information inside {text}"
result = (
  client.query
  .get("Wikipedia", ["title","text"])
  .with_generate(single_prompt=prompt)
  .with_near_text({
    "concepts": ["Vacation spots in california"]
  })
  .with_limit(3)
).do()

json_print(result)

{
  "data": {
    "Get": {
      "Wikipedia": [
        {
          "_additional": {
            "generate": {
              "error": "connection to Cohere API failed with status: 400",
              "singleResult": null
            }
          },
          "text": "Many locals and tourists frequent the Southern California coast for its beaches. Some of southern California's most popular beaches are Malibu, Laguna Beach, La Jolla, Manhattan Beach, and Hermosa Beach. Southern California is also known for its mountain resort communities, such as Big Bear Lake, Lake Arrowhead, and Wrightwood, and their ski resorts, like Bear Mountain, Snow Summit, Snow Valley Mountain Resort, and Mountain High. The inland desert city of Palm Springs is also popular.",
          "title": "Southern California"
        },
        {
          "_additional": {
            "generate": {
              "error": "connection to Cohere API failed with status: 400",
              "singleResult": null
            }
          },
          "text": "Carbon Beach, Surfrider Beach, Westward Beach, Escondido Beach, Paradise Cove, Point Dume, Pirates Cove, Zuma Beach, Trancas and Encinal Bluffs are places along the coast in Malibu. Point Dume forms the northern end of the Santa Monica Bay, and Point Dume Headlands Park affords a vista stretching to the Palos Verdes Peninsula and Santa Catalina Island. Directly below the park, on the western side of the point, is Pirates Cove. Because of its relative seclusion, Pirates Cove was previously used as a nude beach, but since nudity is now illegal on all beaches in Los Angeles County, nude sunbathers are subject to fines and/or arrest.",
          "title": "Malibu, California"
        },
        {
          "_additional": {
            "generate": {
              "error": "connection to Cohere API failed with status: 400",
              "singleResult": null
            }
          },
          "text": "Les plages et parcs c\u00f4tiers principaux sont \"Trinidad State Beach\", \"Torrey Pines State Reserve\", le \"Cabrillo National Monument\". Les touristes se dirigent aussi vers les missions espagnoles, le \"Donner Memorial State Park\", le \"Bodie Historic State Park\", le parc national de Sequoia et le parc d'\u00c9tat de Humboldt Redwoods.",
          "title": "Californie"
        }
      ]
    }
  }
}

Can someone take a look at this notebook, and help me out as to how to resolve these errors. Thanks in advance.

Cheers,
Elemento

2

I have problems with this lesson too - step 2 doesn’t work, weaviate client is not initiated (kernel restart didn’t help). Error stack trace:

---------------------------------------------------------------------------
HTTPError                                 Traceback (most recent call last)
File /usr/local/lib/python3.9/site-packages/weaviate/connect/connection.py:650, in Connection.wait_for_weaviate(self, startup_period)
    649 try:
--> 650     requests.get(ready_url, headers=self._get_request_header()).raise_for_status()
    651     return

File /usr/local/lib/python3.9/site-packages/requests/models.py:1021, in Response.raise_for_status(self)
   1020 if http_error_msg:
-> 1021     raise HTTPError(http_error_msg, response=self)

HTTPError: 500 Server Error: Internal Server Error for url: http://jupyter-api-proxy.internal.dlai/rev-proxy/weaviate/v1/.well-known/ready

The above exception was the direct cause of the following exception:

WeaviateStartUpError                      Traceback (most recent call last)
Cell In[2], line 8
      4 _ = load_dotenv(find_dotenv()) # read local .env file
      6 auth_config = weaviate.auth.AuthApiKey(api_key=os.getenv("WEAVIATE_API_KEY"))
----> 8 client = weaviate.Client(
      9     url=os.getenv("WEAVIATE_API_URL"),
     10     auth_client_secret=auth_config,
     11     additional_headers={
     12         "X-Cohere-Api-Key": os.getenv("COHERE_API_KEY"),
     13         "X-Cohere-BaseURL": os.getenv("CO_API_URL")
     14     }
     15 )
     17 client.is_ready() #check if True

File /usr/local/lib/python3.9/site-packages/weaviate/client.py:150, in Client.__init__(self, url, auth_client_secret, timeout_config, proxies, trust_env, additional_headers, startup_period, embedded_options, additional_config)
    147 config = Config() if additional_config is None else additional_config
    148 url, embedded_db = self.__parse_url_and_embedded_db(url, embedded_options)
--> 150 self._connection = Connection(
    151     url=url,
    152     auth_client_secret=auth_client_secret,
    153     timeout_config=_get_valid_timeout_config(timeout_config),
    154     proxies=proxies,
    155     trust_env=trust_env,
    156     additional_headers=additional_headers,
    157     startup_period=startup_period,
    158     embedded_db=embedded_db,
    159     grcp_port=config.grpc_port_experimental,
    160     connection_config=config.connection_config,
    161 )
    162 self.classification = Classification(self._connection)
    163 self.schema = Schema(self._connection)

File /usr/local/lib/python3.9/site-packages/weaviate/connect/connection.py:166, in Connection.__init__(self, url, auth_client_secret, timeout_config, proxies, trust_env, additional_headers, startup_period, connection_config, embedded_db, grcp_port)
    164 if startup_period is not None:
    165     _check_positive_num(startup_period, "startup_period", int, include_zero=False)
--> 166     self.wait_for_weaviate(startup_period)
    168 self._create_sessions(auth_client_secret)
    169 self._add_adapter_to_session(connection_config)

File /usr/local/lib/python3.9/site-packages/weaviate/connect/connection.py:653, in Connection.wait_for_weaviate(self, startup_period)
    651     return
    652 except (RequestsHTTPError, RequestsConnectionError) as error:
--> 653     raise WeaviateStartUpError(
    654         f"Weaviate did not start up in {startup_period} seconds. Either the Weaviate URL {self.url} is wrong or Weaviate did not start up in the interval given in 'startup_period'."
    655     ) from error

WeaviateStartUpError: Weaviate did not start up in 5 seconds. Either the Weaviate URL http://jupyter-api-proxy.internal.dlai/rev-proxy/weaviate is wrong or Weaviate did not start up in the interval given in 'startup_period'.