Release 6.0.0 (#182)

* feat: adding gemini support (#162)

* feat: adding gemini support

* chore: update package lock

* docs: update changelog for 5.2.0 release

* feat: adding vertexai instrumentation support (#165)

* feat: adding vertexai instrumentation support

* style: remove commented import

* chore: create types for vertexai

* docs: revert vercel ai py check

* docs: add mistral check

* style: remove new lines

* docs: add vertexai to changelog (#166)

* fix: allow manual patch for Gemini and VertexAI (#169)

* star github link

* feat: adding vertexai tools tracing support (#172)

* add mistral instrumentation

* support otel env vars

* bump version adn add chat stream method

* add examples

* update readme

* update package-lock

* Add sentry integration

* merge with dev

* llama index enhacements

* sentry to filter non langtrace exceptions

* Fix ingestion url (#181)

---------

Co-authored-by: darshit-s3 <[email protected]>
Co-authored-by: Darshit Suratwala <[email protected]>
Co-authored-by: Obinna Okafor <[email protected]>
Co-authored-by: obinnascale3 <[email protected]>
Co-authored-by: Rohit Kadhe <[email protected]>
Co-authored-by: Rohit Kadhe <[email protected]>

Author: 5 people

CHANGELOG.md

@@ -1,5 +1,16 @@
 # @langtrase/typescript-sdk
 
+## 6.0.0
+
+### Major Changes
+
+- Change ingestion endpoint to app.langtrace.ai as API domain is moved to the subdomain now
+
+## 5.4.0
+
+### Minor Changes
+
+- Support OTEL_EXPORTER_OTLP_ENDPOINT and OTEL_EXPORTER_OTLP_HEADERS env vars
 
 ## 5.3.2
 

README.md

@@ -73,6 +73,10 @@ import * as Langtrace from '@langtrase/typescript-sdk' // Must precede any llm m
 Langtrace.init({ custom_remote_exporter: <your_exporter>, batch:<true or false>})
 ```
 
+### Error Reporting to Langtrace
+
+By default all sdk errors are reported to langtrace via Sentry. This can be disabled by setting the following enviroment variable to `False` like so `LANGTRACE_ERROR_REPORTING=False`
+
 ## Additional Customization
 
 - [withLangTraceRootSpan](https://docs.langtrace.ai/features/grouptraces) - this function is designed to organize and relate different spans, in a hierarchical manner. When you're performing multiple operations that you want to monitor together as a unit, this function helps by establishing a "parent" (`LangtraceRootSpan` or whatever is passed to `name`) span. Then, any calls to the LLM APIs made within the given function (fn) will be considered "children" of this parent span. This setup is especially useful for tracking the performance or behavior of a group of operations collectively, rather than individually. See [example](https://docs.langtrace.ai/features/grouptraces)
@@ -150,7 +154,7 @@ Langtrace automatically captures traces from the following vendors:
 | Groq         | LLM             | :x:                | :white_check_mark:              |
 | Perplexity   | LLM             | :white_check_mark: | :white_check_mark:              |
 | Gemini       | LLM             | :white_check_mark: | :white_check_mark:              |
-| Mistral      | LLM             | :x:                | :white_check_mark:              |
+| Mistral      | LLM             | :white_check_mark: | :white_check_mark:              |
 | Langchain    | Framework       | :x:                | :white_check_mark:              |
 | LlamaIndex   | Framework       | :white_check_mark: | :white_check_mark:              |
 | Langgraph    | Framework       | :x:                | :white_check_mark:              |