Bugfix/ingest to embed message exchange #113
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gecBurton
commented
Mar 15, 2024
gecBurton
commented
Mar 15, 2024
| @@ -59,11 +59,12 @@ def ingest_file(self, file: File): | |||
| logging.info(f"written {len(items)} chunks to elasticsearch") | |||
|
|
|||
| for chunk in chunks: | |||
| queue_item = EmbedQueueItem(model=env.embedding_model, sentence=chunk.text) | |||
There was a problem hiding this comment.
this is the key change
gecBurton
commented
Mar 15, 2024
|
|
||
| poll_thread = threading.Thread(target=poll_queue_every, args=(queue_uri, queue_name, queue_poll_interval)) | ||
| poll_thread.start() | ||
| thread = threading.Thread(target=subscribe_to_queue) |
There was a problem hiding this comment.
i think we always want to run this thread?
gecBurton
commented
Mar 15, 2024
|
|
||
| connection = None | ||
|
|
||
| for i in range(max_connection_attempts): |
There was a problem hiding this comment.
pika already handles retries
gecBurton
commented
Mar 15, 2024
| @@ -171,62 +161,24 @@ def embed_sentences(model: str, sentences: list[str]): | |||
| return output | |||
|
|
|||
|
|
|||
| def poll_queue_every(queue_uri: str, queue_name: str, interval: int = 5): | |||
There was a problem hiding this comment.
ive tested this IRL, there is no need to poll as pika handles this via the callback mechanism. see guidance-for-review
gecBurton
commented
Mar 15, 2024
| ch.basic_ack(delivery_tag=method.delivery_tag) | ||
| ch.stop_consuming() | ||
| finally: | ||
| ch.basic_ack(delivery_tag=method.delivery_tag) |
There was a problem hiding this comment.
if this is basic_nack then the unprocessed items remain in the queue.... tbh i wasnt sure what we want to do here?
gecBurton
changed the title
lmwilkigov
approved these changes
Mar 15, 2024
|
|
||
| poll_thread = threading.Thread(target=poll_queue_every, args=(queue_uri, queue_name, queue_poll_interval)) | ||
| poll_thread.start() | ||
| thread = threading.Thread(target=subscribe_to_queue) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Context
In #108 I erroneously introduced an error where I put a
Chunkrather than aEmbedQueueItemmessage into the embed queueChanges proposed in this pull request
ingestapp i now put anEmbedQueueItemonto the embed queueGuidance to review
upload a file via: http://0.0.0.0:5002/docs#/file/create_upload_file_file_post
watch http://localhost:15672/#/queues and see that:
docker compose logs -f emebdRelevant links
n/a
Things to check