Hey @Matt, is the 100 indexes limit will stay or is it just temporary? Our architecture is based on

J

Johnny•10/3/23, 11:05 PM

Is anyone else running into the issue of

env.VECTORIZE_INDEX

env.VECTORIZE_INDEX

env.VECTORIZE_INDEX

env.VECTORIZE_INDEX not being loaded into

env

env

object in a CF worker? Here's what my config looks like:

# package.json

"@cloudflare/workers-types": "^4.20230419.0",
"@types/node": "^20.5.7",
"@types/service-worker-mock": "^2.0.1",
"env-cmd": "^10.1.0",
"wrangler": "^3.0.0"

# .dev.vars
SOME_EXAMPLE_VAR = 'hello'

# wrangler.toml
name = "cf_worker"
main = "src/index.ts"
compatibility_date = "2023-10-02"
compatibility_flags = [ "nodejs_compat" ]
keep_vars = true

[[vectorize]]
binding = "VECTORIZE_INDEX" # i.e. available in your Worker on env.VECTORIZE_INDEX
index_name = "myindex"

# package.json

"@cloudflare/workers-types": "^4.20230419.0",
"@types/node": "^20.5.7",
"@types/service-worker-mock": "^2.0.1",
"env-cmd": "^10.1.0",
"wrangler": "^3.0.0"

# .dev.vars
SOME_EXAMPLE_VAR = 'hello'

# wrangler.toml
name = "cf_worker"
main = "src/index.ts"
compatibility_date = "2023-10-02"
compatibility_flags = [ "nodejs_compat" ]
keep_vars = true

[[vectorize]]
binding = "VECTORIZE_INDEX" # i.e. available in your Worker on env.VECTORIZE_INDEX
index_name = "myindex"

# package.json

"@cloudflare/workers-types": "^4.20230419.0",
"@types/node": "^20.5.7",
"@types/service-worker-mock": "^2.0.1",
"env-cmd": "^10.1.0",
"wrangler": "^3.0.0"

# .dev.vars
SOME_EXAMPLE_VAR = 'hello'

# wrangler.toml
name = "cf_worker"
main = "src/index.ts"
compatibility_date = "2023-10-02"
compatibility_flags = [ "nodejs_compat" ]
keep_vars = true

[[vectorize]]
binding = "VECTORIZE_INDEX" # i.e. available in your Worker on env.VECTORIZE_INDEX
index_name = "myindex"

# package.json

"@cloudflare/workers-types": "^4.20230419.0",
"@types/node": "^20.5.7",
"@types/service-worker-mock": "^2.0.1",
"env-cmd": "^10.1.0",
"wrangler": "^3.0.0"

# .dev.vars
SOME_EXAMPLE_VAR = 'hello'

# wrangler.toml
name = "cf_worker"
main = "src/index.ts"
compatibility_date = "2023-10-02"
compatibility_flags = [ "nodejs_compat" ]
keep_vars = true

[[vectorize]]
binding = "VECTORIZE_INDEX" # i.e. available in your Worker on env.VECTORIZE_INDEX
index_name = "myindex"

Am I doing something wrong?

JJohnny Is anyone else running into the issue of `env.VECTORIZE_INDEX` not being loaded ...

U

Unsmart•10/3/23, 11:09 PM

You need to be on wrangler 3.10.0 or higher

UUnsmart You need to be on wrangler 3.10.0 or higher

J

Johnny•10/3/23, 11:14 PM

So I upgraded my wrangler to 3.10.1 and I still seem to be having the same issue, the build looks like its working:

Using vars defined in .dev.vars
Your worker has access to the following bindings:
- Vectorize Indexes:
  - VECTORIZE_INDEX: myindex
- Vars:
  - ENV: "(hidden)"
  - APP_FIREBASE_API_KEY: "(hidden)"
  - APP_FIREBASE_APP_ID: "(hidden)"
  - APP_FIREBASE_AUTH_DOMAIN: "(hidden)"
  - APP_FIREBASE_MEASUREMENT_ID: "(hidden)"
  - APP_FIREBASE_MESSAGE_SENDER_ID: "(hidden)"
  - APP_FIREBASE_PROJECT_ID: "(hidden)"
  - APP_FIREBASE_STORAGE_BUCKET: "(hidden)"
  - OPENAI_API_KEY: "(hidden)"
⎔ Starting local server...
[mf:wrn] The latest compatibility date supported by the installed Cloudflare Workers Runtime is "2023-09-22",
but you've requested "2023-10-02". Falling back to "2023-09-22"...
[mf:inf] Ready on http://0.0.0.0:8788
[mf:inf] - http://127.0.0.1:8788
[mf:inf] - http://192.168.1.167:8788
[mf:inf] GET / 200 OK (3ms)
[mf:inf] GET /openapi.json 200 OK (12ms)

Using vars defined in .dev.vars
Your worker has access to the following bindings:
- Vectorize Indexes:
  - VECTORIZE_INDEX: myindex
- Vars:
  - ENV: "(hidden)"
  - APP_FIREBASE_API_KEY: "(hidden)"
  - APP_FIREBASE_APP_ID: "(hidden)"
  - APP_FIREBASE_AUTH_DOMAIN: "(hidden)"
  - APP_FIREBASE_MEASUREMENT_ID: "(hidden)"
  - APP_FIREBASE_MESSAGE_SENDER_ID: "(hidden)"
  - APP_FIREBASE_PROJECT_ID: "(hidden)"
  - APP_FIREBASE_STORAGE_BUCKET: "(hidden)"
  - OPENAI_API_KEY: "(hidden)"
⎔ Starting local server...
[mf:wrn] The latest compatibility date supported by the installed Cloudflare Workers Runtime is "2023-09-22",
but you've requested "2023-10-02". Falling back to "2023-09-22"...
[mf:inf] Ready on http://0.0.0.0:8788
[mf:inf] - http://127.0.0.1:8788
[mf:inf] - http://192.168.1.167:8788
[mf:inf] GET / 200 OK (3ms)
[mf:inf] GET /openapi.json 200 OK (12ms)

Using vars defined in .dev.vars
Your worker has access to the following bindings:
- Vectorize Indexes:
  - VECTORIZE_INDEX: myindex
- Vars:
  - ENV: "(hidden)"
  - APP_FIREBASE_API_KEY: "(hidden)"
  - APP_FIREBASE_APP_ID: "(hidden)"
  - APP_FIREBASE_AUTH_DOMAIN: "(hidden)"
  - APP_FIREBASE_MEASUREMENT_ID: "(hidden)"
  - APP_FIREBASE_MESSAGE_SENDER_ID: "(hidden)"
  - APP_FIREBASE_PROJECT_ID: "(hidden)"
  - APP_FIREBASE_STORAGE_BUCKET: "(hidden)"
  - OPENAI_API_KEY: "(hidden)"
⎔ Starting local server...
[mf:wrn] The latest compatibility date supported by the installed Cloudflare Workers Runtime is "2023-09-22",
but you've requested "2023-10-02". Falling back to "2023-09-22"...
[mf:inf] Ready on http://0.0.0.0:8788
[mf:inf] - http://127.0.0.1:8788
[mf:inf] - http://192.168.1.167:8788
[mf:inf] GET / 200 OK (3ms)
[mf:inf] GET /openapi.json 200 OK (12ms)

Using vars defined in .dev.vars
Your worker has access to the following bindings:
- Vectorize Indexes:
  - VECTORIZE_INDEX: myindex
- Vars:
  - ENV: "(hidden)"
  - APP_FIREBASE_API_KEY: "(hidden)"
  - APP_FIREBASE_APP_ID: "(hidden)"
  - APP_FIREBASE_AUTH_DOMAIN: "(hidden)"
  - APP_FIREBASE_MEASUREMENT_ID: "(hidden)"
  - APP_FIREBASE_MESSAGE_SENDER_ID: "(hidden)"
  - APP_FIREBASE_PROJECT_ID: "(hidden)"
  - APP_FIREBASE_STORAGE_BUCKET: "(hidden)"
  - OPENAI_API_KEY: "(hidden)"
⎔ Starting local server...
[mf:wrn] The latest compatibility date supported by the installed Cloudflare Workers Runtime is "2023-09-22",
but you've requested "2023-10-02". Falling back to "2023-09-22"...
[mf:inf] Ready on http://0.0.0.0:8788
[mf:inf] - http://127.0.0.1:8788
[mf:inf] - http://192.168.1.167:8788
[mf:inf] GET / 200 OK (3ms)
[mf:inf] GET /openapi.json 200 OK (12ms)

But then when I go to log out

Object.keys(env)

Object.keys(env)

Object.keys(env)

Object.keys(env) I get this:

Array(9) [ ENV, APP_FIREBASE_API_KEY, APP_FIREBASE_APP_ID, APP_FIREBASE_AUTH_DOMAIN, APP_FIREBASE_MEASUREMENT_ID, APP_FIREBASE_MESSAGE_SENDER_ID, APP_FIREBASE_PROJECT_ID, APP_FIREBASE_STORAGE_BUCKET, OPENAI_API_KEY ]

Array(9) [ ENV, APP_FIREBASE_API_KEY, APP_FIREBASE_APP_ID, APP_FIREBASE_AUTH_DOMAIN, APP_FIREBASE_MEASUREMENT_ID, APP_FIREBASE_MESSAGE_SENDER_ID, APP_FIREBASE_PROJECT_ID, APP_FIREBASE_STORAGE_BUCKET, OPENAI_API_KEY ]

Array(9) [ ENV, APP_FIREBASE_API_KEY, APP_FIREBASE_APP_ID, APP_FIREBASE_AUTH_DOMAIN, APP_FIREBASE_MEASUREMENT_ID, APP_FIREBASE_MESSAGE_SENDER_ID, APP_FIREBASE_PROJECT_ID, APP_FIREBASE_STORAGE_BUCKET, OPENAI_API_KEY ]

Array(9) [ ENV, APP_FIREBASE_API_KEY, APP_FIREBASE_APP_ID, APP_FIREBASE_AUTH_DOMAIN, APP_FIREBASE_MEASUREMENT_ID, APP_FIREBASE_MESSAGE_SENDER_ID, APP_FIREBASE_PROJECT_ID, APP_FIREBASE_STORAGE_BUCKET, OPENAI_API_KEY ]

Which does not contain

VECTORIZE_INDEX

VECTORIZE_INDEX

VECTORIZE_INDEX

VECTORIZE_INDEX

U

Unsmart•10/3/23, 11:15 PM

Try running with

--remote

--remote

might be a case where its not available locally yet

UUnsmart Try running with `--remote` might be a case where its not available locally yet

J

Johnny•10/3/23, 11:16 PM

Ahhh yep that was it

Appreciate the help

ZZak @ insertchat.com Hey @Matt, is the 100 indexes limit will stay or is it just temporary? Our archi...

M

Matt Silverlock•10/3/23, 11:16 PM

C

cosbgn•10/4/23, 12:19 PM

100 indexes is still fairly useless, or I'm not understanding how they should be used. Any normal app will have easily thousands+ users and thousands+ files. What am I supposed to use as index? maybe file/type but doesn't really help much. Metadata search is a must.

C

cosbgn•10/4/23, 12:21 PM

Just in case my message came out to strong, I love cloudflare

and the amazign work you are doing!! I actually love it that much that I'm trying to fully migrate everything to it! Being able to store vectors here it would be amazing

Ccosbgn 100 indexes is still fairly useless, or I'm not understanding how they should be...

M

Matt Silverlock•10/4/23, 12:44 PM

It’s not meant as a replacement. Some folks want more indexes for isolating different use-cases, and 10 was just where we started.

Ccosbgn 100 indexes is still fairly useless, or I'm not understanding how they should be...

M

Matt Silverlock•10/4/23, 12:45 PM

Hold tight on the metadata filtering. We’re working on it

N

nclevenger•10/4/23, 3:23 PM

Does anyone know what this error means:

VECTOR_QUERY_ERROR: Status + 500

VECTOR_QUERY_ERROR: Status + 500

VECTOR_QUERY_ERROR: Status + 500

VECTOR_QUERY_ERROR: Status + 500? I was running the exact query successfully earlier this morning, but now it is erroring.

Nnclevenger Does anyone know what this error means: `VECTOR_QUERY_ERROR: Status + 500`? I w...

J

Jerome•10/4/23, 3:26 PM

This means internal error, I can look in the internal log

JJerome This means internal error, I can look in the internal log

I

Isaac McFadyen•10/4/23, 3:27 PM

Just a heads-up that you can type

/cfrole

/cfrole

to get an orange Cloudflare role in the server

IIsaac McFadyen Just a heads-up that you can type `/cfrole` to get an orange Cloudflare role in ...

J

Jerome•10/4/23, 3:27 PM

yeah

JJerome This means internal error, I can look in the internal log

N

nclevenger•10/4/23, 3:28 PM

account id a826340b3b93189c9ebb7c0eaeba3c46 index blogs

IIsaac McFadyen Just a heads-up that you can type `/cfrole` to get an orange Cloudflare role in ...

J

Jerome•10/4/23, 3:28 PM

thx

JJerome 💥 thx

I

Isaac McFadyen•10/4/23, 3:28 PM

No problem!

IIsaac McFadyen Just a heads-up that you can type `/cfrole` to get an orange Cloudflare role in ...

O

Old Man Maker•10/4/23, 3:52 PM

What does that mean or refer to?

OOld Man Maker What does that mean or refer to?

J

Jerome•10/4/23, 3:53 PM

it's a command to mark one's discord account as belonging to an employee of cloudflare

O

Old Man Maker•10/4/23, 3:54 PM

oh I see

O

Old Man Maker•10/4/23, 3:54 PM

well now I'm just jealous

J

Jerome•10/4/23, 4:07 PM

@oldmanmeta have you seen my DM ?

J

Jerome•10/4/23, 4:11 PM

I mean: @nclevenger, have you seen my DM>

JJerome I mean: @nclevenger, have you seen my DM>

N

nclevenger•10/4/23, 4:23 PM

no ... I don't think i see it?

JJerome I mean: @nclevenger, have you seen my DM>

N

nclevenger•10/4/23, 4:25 PM

i found it - thanks!

O

Old Man Maker•10/4/23, 4:47 PM

I'm getting the same error as @nclevenger

VECTOR_QUERY_ERROR: Status + 404

VECTOR_QUERY_ERROR: Status + 404

VECTOR_QUERY_ERROR: Status + 404

VECTOR_QUERY_ERROR: Status + 404

O

Old Man Maker•10/4/23, 4:47 PM

just started happening

O

Old Man Maker•10/4/23, 4:54 PM

Account ID: 43310a46ee87ca6683a51510f7a57241

O

Old Man Maker•10/4/23, 4:55 PM

Can some please take a look for me.
The vectors are being created in the query correctly, calling <vectorize>.query() is failing

O

Old Man Maker•10/4/23, 4:56 PM

the index is ais-vec-bakedcontent-index

OOld Man Maker I'm getting the same error as @nclevenger ``` VECTOR_QUERY_ERROR: Status + 404...

J

Jerome•10/4/23, 5:08 PM

looking into it

JJerome looking into it

O

Old Man Maker•10/4/23, 5:09 PM

Thanks Sir

KKarl Hey, i'm playing around with vectorize and workers AI. Really impressed so far....

M

Matt Silverlock•10/5/23, 10:15 AM

You’d want some form of metadata filtering (we are working on it) for that.

MMatt Silverlock It’s not meant as a replacement. Some folks want more indexes for isolating diff...

Z

Zak @ insertchat.comOP•10/5/23, 11:24 AM

Yup, that's my case. Do you see any advantages/disadvantages to using one big index with all user vectors + metadata filtering by a user id vs. one index per user?

ZZak @ insertchat.com Yup, that's my case. Do you see any advantages/disadvantages to using one big in...

M

Matt Silverlock•10/5/23, 11:30 AM

It will depend on your index size. If the count of vectors per user is very small, and will remain so, a larger single index will remain “hot”

Z

Zak @ insertchat.comOP•10/5/23, 11:31 AM

Oh I see, there is a notion of hot/cold storage involved. What's your definition of small? Millions? Tens of millions? 1 billion?

ZZak @ insertchat.com Oh I see, there is a notion of hot/cold storage involved. What's your definition...

M

Matt Silverlock•10/5/23, 11:33 AM

per user or per index? Small would be thousands per user - over hundreds of thousands of users -> an index in the millions.

Z

Zak @ insertchat.comOP•10/5/23, 11:34 AM

I don't have more then a million vector per user

M

Matt Silverlock•10/5/23, 11:34 AM

To step back a second: it really doesn’t matter that much, and it probably doesn’t make a lot of sense to over engineer this right now

Z

Zak @ insertchat.comOP•10/5/23, 11:34 AM

The total in my db right now is between 5 and 10 millions vectors

M

Matt Silverlock•10/5/23, 11:35 AM

That’s fine.

M

Matt Silverlock•10/5/23, 11:36 AM

Write your raw embeddings to R2. If you want to change your approach, it’s much easier to repopulate an index vs a traditional RDBMS

Z

Zak @ insertchat.comOP•10/5/23, 11:39 AM

Will dump a few million vectors to Vectorize once we have filtering to see how it performs with a user id filter, if it's good then it's a go for production, and will see if we change it later to multiple indexes

Z

Zak @ insertchat.comOP•10/5/23, 12:35 PM

Can we also expect a way to CRUD a vector (row) directly by its id/uid?

ZZak @ insertchat.com Can we also expect a way to CRUD a vector (row) directly by its id/uid?

J

Jerome•10/5/23, 12:45 PM

there is

getByIds

getByIds

getByIds

getByIds and

deleteByIds

deleteByIds

deleteByIds

deleteByIds operations;

insert

insert

and

upsert

upsert

upsert

upsert take the id you provide as well

Z

Zak @ insertchat.comOP•10/5/23, 12:46 PM

I'm an API user, don't have those (I think)

Hey @Matt, is the 100 indexes limit will stay or is it just temporary? Our architecture is based on

Similar Threads

Similar Threads

Similar Threads