PR Batch 7

[nponeccop]

Duplicates

• I have searched the existing issues

Summary 💡

No response

Closed 🌈

• data_ingestion.py 'no module named 'autogpt'" fix and ReadMe update #1679
• Add File Downloading Capabilities #1680
• install chrome/firefox for headless browing when running in docker co… #1723
• Add run scripts for shell #1743
• update Dockerfile to fix No module named 'autogpt' #1831
• fixes Weaviate index name to classname conversion #1836
• fixes #1821 by installing required drivers and adding options to chro… #1857
• minimall add pytest #1859
• Fix README #1868
• fix #1363 #1903
• Improve bug report template #1904
• Create run.sh for Linux environment #1910
• Fix naive json names find/replace #1915
• add utf-8 encoding to file handlers for logging #1916
• Fix README.md #1925
• remove duplicate milvus section #1927
• Fix .env.template documentation, incorrect default value for TEMPERATURE #1932
• Improve dev containers so autogpt can browse the web #1942
• Consolidate and fix workspace resolution #1947
• Make command speech sound more natural, and enable MacOS voices to be… #1954
• Improve the error logging for OAI Issues #1987
• internal resource request bug #2001
• feat: (aesthetic) add space on warning message #2003
• fix user input being modified #2007
• Added one space after period for better formatting #2022
• Clean up README #2040
• Implement new demo video into README.md #2041
• Unbound summary size #2056
• Fix split file to handle edge case where overlap size > last chunk size #2062
• memory object move to memory_add block #2093

Open

• Add LlamaIndex Memory module #1774
• Missing newline in many files #1792
• Use twitter v2 API instead of legacy. #1806
• Ensure Python 3.10 & 3.11 compatability #1815
• Add a kill switch feature: This will disable the agent running in con… #1824
• changed docker instructions in README to comply with changed installa… #1830
• Added constraints and evaluations #1874
• Option to disable working directory restrictions #1875
• Add AnalyticDB as a long-term memory backend. #1876
• Add ai_output_language_code env configuration add support logging with google translate #1880
• Gracefully handle non-image response content from HuggingFace #1888
• [Change]: Update docker-compose.yml introducing env file to Redis container. #1921
• Adjust test_json_parser file #1935
• Introduce the usage of langchain #1936
• feat: githook #1945
• fix: align docker user path issues and readme #1957
• ✨ [Feature] Sending Emails #1975
• Return error with hint for unknown key in AgentManager #1980
• Update docker-hub image push action #1986
• Add annoy option for local vector db #1996
• [feat]: Implements initial parameters for AI #1999
• Image Generator Naming Convention Enhancement #2010
• Fix: #2021 #2025
• Delete duplicate method declaration #2033
• Added default actions functionality #2037
• Truncate text before create_embedding_with_ada() #2039
• Attempt to prevent hallucinating reading search results #2059
• Chrome Browser Crash on Linux Fix #2086
• Fix split_text chunking bug #2088
• Add option for inputting an integer instead of only y -n #2109

Carried over from B6

• Ask GPT-4 to respond with a compliant machine-readable JSON document #1180
• Add memory backend using sqlite and zarr #1457
• Separate memory index for Pinecone, Redis and local cache memory backends #1461
• feat: Add support for running Chrome in Headless mode. #1473
• Image generation improvements #1477
• Pass command line args as list #1486
• Add Qdrant as a long memory backend. #1515
• downgrade version #1524
• Enable Google/OpenAI access for china mainland users #1541
• feat: log new-line so user can differentiate sections better in console #1569

Carried from B5

• Update .gitignore #882
• Delete unused folder /outputs/ #1130
• Circleci project setup #1159
• fix docker-compose setup #1198
• Make the docker setup consistent with local #1199
• Extract main loop into standalone function #1216
• Use async/await where applicable #1245
• Unused Functions removed from commands.py #1316

Conflicts from Earlier Batches

• fix(browse): exponential backoff when OpenAI throttles API calls #214
• Add 1/0 as an alternative to y/n for non-english users #766
• Semiautomatic update .env from env.template #889
• Use Chroma to augment and make LocalCache memory/embeddings pluggable #1027

Motivation 🔦

No response

[Wladastic]

This one is missing, it has the B7 label and works very well now:
#1135
I kept improving it as long as pr was open haha

[Androbin]

#1243 has the B7 label and is missing as well

[alreadydone]

Is there interest in using a "batch manager" such as https://bors.tech/? It's used in an open-source project on GitHub I participated in. Basically, once maintainers approve a PR, they can immediately send it to bors, and bors will merge a batch of multiple approved PRs into a temporary staging branch and run CI on it; if CI passes then the staging branch will be merged into master and bors will then work on the next batch in the queue, and if not then bors will split the batch in half, put one half in the staging branch and the other half (as a different batch) in the queue, and so on; any PRs approved in the meantime will also be put in the queue as a different batch.

[github-actions]

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

[github-actions]

This issue was closed automatically because it has been stale for 10 days with no activity.