All Issues
24,993 verified issues
Exception: EOF while parsing a value at line 1 column 0
Hello, I'm on Windows and installed with `pip install git+https://github.com/anthropics/anthropic-sdk-python.git` Seeing this issue when issuing a standard completion prompt. This is the command: [code block] Here is the complete error: [code block]
nodes
nodes
apt install postgresql-16-pgvector is not found
I got error [code block] of course I run this command before: [code block]
stream.get_final_message() does not return the correct usage of output_tokens
Like the title said, `stream.get_final_message()` always return the `output_tokens` with the value of `1`. running the exmaple code examples/messages_stream.py, the output would look like: [code block] However the actual `output_tokens` should be `6` according to the raw HTTP stream response [code block] So, is this a bug or a feature? I've seen someone in issue #417 using `stream.get_final_message()` to obtain the usage information. If `output_tokens ` always returns 1, this won't work properly, I guess.
Invalid directory /crypto
After installing twilio-node and using var client = require('twilio')(accountSid, authToken), this appears.
Error: Request failed with status code 400
Describe the bug Too much content will cause an error, It's not clear to me why that's true To Reproduce 1. Too much content Code snippets _No response_ OS windows Node version Node V18.x Library version openai v3.2.1
pageSize opts not working
Hello, I'm facing a wrong behaviour using the twilio-node sdk. If I try to retrieve the messages list from a channel setting a pageSize value, let's say equal to 25, the result contains all the messages like if the pageSize option is ignored. I tried using the REST api instead, specifying the `?PageSize=25` param, and all works fine since I get the first 25 messages and the link for the next page and so on. How can I solve this? Thanks. Is there also a way to specify the starting page? Thanks, Simone Version: 3.30.3 Code Snippet [code block]
Whether we should lock element when UpdateNeighborsInMemory ?
The following crash was triggered when we created the hnsw index using pgvector in GPDB: [code block] The crash is caused by the `neighborElement` is NULL in f4 UpdateNeighborsInMemory. But when we add some log when we find `neighborElement` is NULL and regain the `neighborElement`, it's not NULL, and it may change. We tried to understand the code of UpdateNeighborsInMemory, we think that we should require e->lock when we do `UpdateNeighborsInMemory`: [code block] because the `HnswElement e` has been added to Memory and may be neighbors of other elements, and thay may UpdateConnection of e during we `UpdateNeighborsInMemory` e. But we are not know much about the code, so initiate this discussion. --- Reproduction method: 1. create a table and insert some data 2. set max_parallel_maintenance_workers to 20; 3. CREATE INDEX hnsw_cosine_qa_data_bge_new ON qa_data_bge USING hnsw (embedding vector_cosine_ops) WITH (m = 100, ef_construction = 1000); 4. Ctrl-C stop `CREATE INDEX` after 5s if not crash, goto 3
Incompatible with 32-bit
While setting up Debian package builds for pgvector, we noticed it doesn't compile on 32-bit architectures (i386): [code block] The fix for this is easy: [code block] but then it still doesn't work: [code block] Is this fixable, or is 32-bit generally unsupported?
Performance Issue with Large Tables and HNSW Indexes
Hello, I'm currently facing performance challenges with pgvector on PostgreSQL, particularly with large tables and queries taking significant time to execute. I'd like to share my situation and seek advice on potential optimizations or configurations that could improve performance. Environment & Configuration: - PostgreSQL version: Using the Docker image with pgvector version 0.6.0 included, which is based on PostgreSQL 16. - Hardware: The server has 28 cores, 56 threads, and 256GB of RAM, but we're using HDDs instead of SSDs, which might be impacting performance. - Tables: We have around 10 tables, each with approximately 10 to 20 million rows. - Current settings: `shared_buffers` is set to 80GB, and `effective_cache_size` is set to 120GB. - Indexes: Utilizing HNSW indexes with cosine similarity. Issues & Observations: - Query Performance: Queries on these tables are taking at least 10 seconds each, which seems unusually high. - Considering Partitioning: I'm contemplating implementing partitioning to potentially improve performance and would appreciate any insights on whether partitioning might be beneficial in my case. Given the above configuration and the challenges faced, I have a few questions: 1. Are there any recommended configurations or optimizations specific to pgvector, especially when dealing with large tables and HNSW indexes on an HDD setup? 2. Could the use of HDD instead of SSD be the primary factor in the observed performance issues? Would transitioning t
Vertex "Could not resolve API token from the environment"
<img width="627" alt="Screenshot 2024-07-10 at 4 56 29 PM" src="https://github.com/anthropics/anthropic-sdk-python/assets/44094672/470faa05-144f-4ab8-892d-5ac8d839a2c5"> For some reasons after the update, Vertex now keeps asking for API Tokens but we are using GCP service account to authorize VertexAI and it was fine until this morning. Did the new release change or require something new?
validateExpressRequest not working correctly
Issue Summary There is a duality in the validator code for validateExpressRequest as validateRequest requires body parameter to be an object, but validateRequestWithBody requires body to be a string. validateRequestWithBody is also called with [code block] so it fails even when body is not present. Steps to Reproduce 1. call validateExpressRequest with a request which has a parsed body object or no body at all Exception If not before, exception occurs in getExpectedBodyHash because body is not a string Technical details: twilio-node version: 3.56.0 node version: 15.0.1
Unable to import Twilio
Issue Summary Fresh install of `twilio` on my node project. Documentation was using `require` but I use `import` in my project. When attempting to use `import` I am given this error message: [code block] Steps to Reproduce 1. `npm i twilio -S` 2. Run code snippet Code Snippet [code block] Exception/Log [code block] Technical details: twilio-node version: `5.0.3` node version: `v16.20.2`
bedrock: How to tokenizer and count tokenizer?
It seems that bedrock has lost a lot of features. such as: How to do tokenization and count tokenizer? And is there any api guide? I can find 2 simple code examples.
Shouldn't there be `restrict` keyword at parameters in `VectorInnerProduct()`?
https://github.com/pgvector/pgvector/blob/2627c5ff775ae6d7aef0c430121ccf857842d2f2/src/vector.c#L592-L602 [code block] https://en.wikipedia.org/wiki/Restrict
Opus 4.6 with adaptive thinking: Redundant text block (text -> think -> text)
[code block] [code block] Expected: [code block] There is no obvious way to distinguish the first text block.
Model can generate enormous amounts of whitespace/newlines and then the structured output is truncated
Confirm this is a Node library issue and not an underlying OpenAI API issue - [X] This is an issue with the Node library Describe the bug When using `json_schema`, sometimes the model outputs thousands of newlines. At some point it reaches the max output length and stops, causing it to sometimes return a non valid json object (it didn't finish writing it). Because of how this library is structured, the developer can't see the problem (the output is not logged). I've found that including [code block] will solve this. To Reproduce happens randomly when using `json_schema` Code snippets _No response_ OS irrelevant Node version irrelevant Library version 4.71.1
File descriptor leak when using Anthropic client
I have tested anthropic 0.3.11 and 0.2.9 , both might have File descriptor leak . code 1 : [code block] code 2 : [code block] Both code led to File descriptor leak eventually after 5000-10000 loops . I ever tried to remove the retry and the same File descriptor leak happened . When changed to use [code block] everything is fine . no File descriptor leak at all .
RestException Authentication Error is thrown twice and can not be catched (for flows.list())
Issue Summary With a twilio client connected with valid but incorrect sid and/or token when I try to list studio flows using `client.studio.v2.flows.list` I can catch a first `RestException [Error]: Authentication Error - invalid username` which is expected behaviour. Then the same error is thrown again inside some unknown async process. Since I have no acces to the hidden async process I can not catch this second error. The same goes for using the callback and awaiting the promise of `client.studio.v2.flows.list`. Steps to Reproduce 1. Create a client with valid but incorrect sid and token. 2. make an API call to list studio flows and catch any errors Code Snippet [code block] Exception/Log [code block] Technical details: twilio-node version: 4.11.0 node version: v18.14.2 * OS: Windows 10
No Function Arguments in toolCallDone Stream Event Hook
Confirm this is a Node library issue and not an underlying OpenAI API issue - [X] This is an issue with the Node library Describe the bug The "`.on('toolCallDone')` used on the stream returned by `ai.beta.threads.runs.stream`" does not return arguments (empty string), only function name: [code block] To Reproduce 1. Retrieve a run stream with `ai.beta.threads.runs.stream` 2. Add the `.on('toolCallDone')` hook. 3. Wait for the response, it does not return with what arguments should the function be called. Code snippets [code block] OS macOS Node version v20.11.1 Library version openai v4.36.0